Author name cluster

Bahram Zonooz

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

23 papers

2 author rows

TMLR Journal 2026 Journal Article

Parameter Efficient Continual Learning with Dynamic Low- Rank Adaptation

Prashant Shivaram Bhat
Shakib Yazdani
Elahe Arani
Bahram Zonooz

Catastrophic forgetting has remained a critical challenge for deep neural networks in Continual Learning (CL) as it undermines consolidated knowledge when learning new tasks. Parameter efficient fine-tuning CL techniques are gaining traction for their effectiveness in addressing catastrophic forgetting with lightweight training schedule while avoiding degradation of consolidated knowledge in pre-trained models. However, low-rank adapters (LoRA) in these approaches are highly sensitive to rank selection as it can lead to sub-optimal resource allocation and performance. To this end, we introduce PEARL, a rehearsal-free CL framework that entails dynamic rank allocation for LoRA components during CL training. Specifically, PEARL leverages reference task weights and adaptively determines the rank of task-specific LoRA components based on the current task’s proximity to reference task weights in parameter space. To demonstrate the versatility of PEARL, we evaluate PEARL across three vision architectures (ResNet, Separable Convolutional Network, and Vision Transformer) and a multitude of CL scenarios, and show that PEARL outperforms all considered baselines by a large margin.

PDF Details

TMLR Journal 2025 Journal Article

Consistency Aware Robust Learning under Noisy Labels

Fahad Sarfraz
Bahram Zonooz
Elahe Arani

Deep neural networks (DNNs) often struggle with noisy supervision, a common challenge in real-world datasets where high-quality annotations are scarce. While DNNs tend to memorize noisy labels, the human brain excels at learning in noisy environments by modulating sensitivity to errors based on their magnitude and consistency. Inspired by this, we propose Consistency-Aware Robust Learning (CARoL), which maintains a memory of past predictions and errors to quantify consistency and guide the learning process. CARoL employs a principled mechanism to distinguish clean from noisy samples and modulates rate of adaptation based on prediction consistency. Furthermore, it integrates multiple learning pathways to fully utilize the dataset, adapting to sample characteristics as training progresses. Our empirical evaluation shows that CARoL achieves high precision in noisy label detection, enhances robustness, and performs reliably under severe noise, highlighting the potential of biologically inspired approaches for robust learning.

PDF Details

ICLR Conference 2025 Conference Paper

Semantic Aware Representation Learning for Lifelong Learning

Fahad Sarfraz
Elahe Arani
Bahram Zonooz

The human brain excels at lifelong learning by not only encoding information in sparse activation codes but also leveraging rich semantic structures and relationships between newly encountered and previously learned objects. This ability to utilize semantic similarities is crucial for efficient learning and knowledge consolidation, yet is often underutilized in current continual learning approaches. To bridge this gap, we propose Semantic-Aware Representation Learning (SARL) which employs sparse activations and a principled approach to evaluate similarities between objects encountered across different tasks and subsequently uses them to guide representation learning. Using these relationships, SARL enhances the reusability of features and reduces interference between tasks. This approach empowers the model to adapt to new information while maintaining stability, significantly improving performance in complex incremental learning scenarios. Our analysis demonstrates that SARL achieves a superior balance between plasticity and stability by harnessing the underlying semantic structure.

Details

ICLR Conference 2024 Conference Paper

Conserve-Update-Revise to Cure Generalization and Robustness Trade-off in Adversarial Training

Shruthi Gowda
Bahram Zonooz
Elahe Arani

Adversarial training improves the robustness of neural networks against adversarial attacks, albeit at the expense of the trade-off between standard and robust generalization. To unveil the underlying factors driving this phenomenon, we examine the layer-wise learning capabilities of neural networks during the transition from a standard to an adversarial setting. Our empirical findings demonstrate that selectively updating specific layers while preserving others can substantially enhance the network's learning capacity. We, therefore, propose CURE, a novel training framework that leverages a gradient prominence criterion to perform selective conservation, updating, and revision of weights. Importantly, CURE is designed to be dataset- and architecture-agnostic, ensuring its applicability across various scenarios. It effectively tackles both memorization and overfitting issues, thus enhancing the trade-off between robustness and generalization and additionally, this training approach also aids in mitigating "robust overfitting". Furthermore, our study provides valuable insights into the mechanisms of selective adversarial training and offers a promising avenue for future research.

Details

NeurIPS Conference 2024 Conference Paper

Dynamic Neural Regeneration: Enhancing Deep Learning Generalization on Small Datasets

Vijaya R. Ramkumar
Elahe Arani
Bahram Zonooz

The efficacy of deep learning techniques is contingent upon access to large volumes of data (labeled or unlabeled). However, in practical domains such as medical applications, data availability is often limited. This presents a significant challenge: How can we effectively train deep neural networks on relatively small datasets while improving generalization? Recent works have explored evolutionary or iterative training paradigms, which reinitialize a subset of parameters to enhance generalization performance for small datasets. However, these methods typically rely on randomly selected parameter subsets and maintain fixed masks throughout training, potentially leading to suboptimal outcomes. Inspired by neurogenesis in the brain, we propose a novel iterative training framework, Dynamic Neural Regeneration (DNR), that employs a data-aware dynamic masking scheme to eliminate redundant connections by estimating their significance. This approach increases the model's capacity for further learning through random weight reinitialization. Experimental results demonstrate that our approach outperforms existing methods in accuracy and robustness, highlighting its potential for real-world applications where data collection is challenging.

PDF Details DOI

ICML Conference 2024 Conference Paper

Gradual Divergence for Seamless Adaptation: A Novel Domain Incremental Learning Method

Kishaan Jeeveswaran
Elahe Arani
Bahram Zonooz

Domain incremental learning (DIL) poses a significant challenge in real-world scenarios, as models need to be sequentially trained on diverse domains over time, all the while avoiding catastrophic forgetting. Mitigating representation drift, which refers to the phenomenon of learned representations undergoing changes as the model adapts to new tasks, can help alleviate catastrophic forgetting. In this study, we propose a novel DIL method named DARE, featuring a three-stage training process: Divergence, Adaptation, and REfinement. This process gradually adapts the representations associated with new tasks into the feature space spanned by samples from previous tasks, simultaneously integrating task-specific decision boundaries. Additionally, we introduce a novel strategy for buffer sampling and demonstrate the effectiveness of our proposed method, combined with this sampling strategy, in reducing representation drift within the feature encoder. This contribution effectively alleviates catastrophic forgetting across multiple DIL benchmarks. Furthermore, our approach prevents sudden representation drift at task boundaries, resulting in a well-calibrated DIL model that maintains the performance on previous tasks.

Details

TMLR Journal 2024 Journal Article

IMEX-Reg: Implicit-Explicit Regularization in the Function Space for Continual Learning

Prashant Shivaram Bhat
Bharath Chennamkulam Renjith
Elahe Arani
Bahram Zonooz

Continual learning (CL) remains one of the long-standing challenges for deep neural networks due to catastrophic forgetting of previously acquired knowledge. Although rehearsal-based approaches have been fairly successful in mitigating catastrophic forgetting, they suffer from overfitting on buffered samples and prior information loss, hindering generalization under low-buffer regimes. Inspired by how humans learn using strong inductive biases, we propose \textbf{IMEX-Reg} to improve the generalization performance of experience rehearsal in CL under low buffer regimes. Specifically, we employ a two-pronged implicit-explicit regularization approach using contrastive representation learning (CRL) and consistency regularization. To further leverage the global relationship between representations learned using CRL, we propose a regularization strategy to guide the classifier toward the activation correlations in the unit hypersphere of the CRL. Our results show that IMEX-Reg significantly improves generalization performance and outperforms rehearsal-based approaches in several CL scenarios. It is also robust to natural and adversarial corruptions with less task-recency bias. Additionally, we provide theoretical insights to support our design decisions further.

PDF Details

ICLR Conference 2024 Conference Paper

The Effectiveness of Random Forgetting for Robust Generalization

Vijaya Raghavan T. Ramkumar
Bahram Zonooz
Elahe Arani

Deep neural networks are susceptible to adversarial attacks, which can compromise their performance and accuracy. Adversarial Training (AT) has emerged as a popular approach for protecting neural networks against such attacks. However, a key challenge of AT is robust overfitting, where the network's robust performance on test data deteriorates with further training, thus hindering generalization. Motivated by the concept of active forgetting in the brain, we introduce a novel learning paradigm called "Forget to Mitigate Overfitting (FOMO)". FOMO alternates between the forgetting phase, which randomly forgets a subset of weights and regulates the model's information through weight reinitialization, and the relearning phase, which emphasizes learning generalizable features. Our experiments on benchmark datasets and adversarial attacks show that FOMO alleviates robust overfitting by significantly reducing the gap between the best and last robust test accuracy while improving the state-of-the-art robustness. Furthermore, FOMO provides a better trade-off between the standard and robust accuracy outperforming baseline adversarial methods. Finally, our framework is robust to AutoAttacks and increases generalization in many real-world scenarios.

Details

TMLR Journal 2023 Journal Article

A Study of Biologically Plausible Neural Network: The Role and Interactions of Brain-Inspired Mechanisms in Continual Learning

Fahad Sarfraz
Elahe Arani
Bahram Zonooz

Humans excel at continually acquiring, consolidating, and retaining information from an ever-changing environment, whereas artificial neural networks (ANNs) exhibit catastrophic forgetting. There are considerable differences in the complexity of synapses, the processing of information, and the learning mechanisms in biological neural networks and their artificial counterparts, which may explain the mismatch in performance. We consider a biologically plausible framework that constitutes separate populations of exclusively excitatory and inhibitory neurons that adhere to Dale's principle, and the excitatory pyramidal neurons are augmented with dendritic-like structures for context-dependent processing of stimuli. We then conduct a comprehensive study on the role and interactions of different mechanisms inspired by the brain, including sparse non-overlapping representations, Hebbian learning, synaptic consolidation, and replay of past activations that accompanied the learning event. Our study suggests that the employing of multiple complementary mechanisms in a biologically plausible architecture, similar to the brain, may be effective in enabling continual learning in ANNs. \footnote{We will make the code available upon acceptance.

PDF Details

ICML Conference 2023 Conference Paper

BiRT: Bio-inspired Replay in Vision Transformers for Continual Learning

Kishaan Jeeveswaran
Prashant Shivaram Bhat
Bahram Zonooz
Elahe Arani

The ability of deep neural networks to continually learn and adapt to a sequence of tasks has remained challenging due to catastrophic forgetting of previously learned tasks. Humans, on the other hand, have a remarkable ability to acquire, assimilate, and transfer knowledge across tasks throughout their lifetime without catastrophic forgetting. The versatility of the brain can be attributed to the rehearsal of abstract experiences through a complementary learning system. However, representation rehearsal in vision transformers lacks diversity, resulting in overfitting and consequently, performance drops significantly compared to raw image rehearsal. Therefore, we propose BiRT, a novel representation rehearsal-based continual learning approach using vision transformers. Specifically, we introduce controllable noises at various stages of the vision transformer and enforce consistency in predictions with respect to an exponential moving average of the working model. Our method provides consistent performance gain over raw image and vanilla representation rehearsal on several challenging CL benchmarks while being memory efficient and robust to natural and adversarial corruptions.

Details

TMLR Journal 2023 Journal Article

Dual Cognitive Architecture: Incorporating Biases and Multi-Memory Systems for Lifelong Learning

Shruthi Gowda
Bahram Zonooz
Elahe Arani

Artificial neural networks (ANNs) exhibit a narrow scope of expertise on stationary independent data. However, the data in the real world is continuous and dynamic, and ANNs must adapt to novel scenarios while also retaining the learned knowledge to become lifelong learners. The ability of humans to excel at these tasks can be attributed to multiple factors ranging from cognitive computational structures, cognitive biases, and the multi-memory systems in the brain. We incorporate key concepts from each of these to design a novel framework, Dual Cognitive Architecture (DUCA), which includes multiple sub-systems, implicit and explicit knowledge representation dichotomy, inductive bias, and a multi-memory system. DUCA shows improvement across different settings and datasets, and it also exhibits reduced task recency bias, without the need for extra information. To further test the versatility of lifelong learning methods on a challenging distribution shift, we introduce a novel domain-incremental dataset DN4IL. In addition to improving performance on existing benchmarks, DUCA also demonstrates superior performance on this complex dataset.

PDF Details

ICLR Conference 2023 Conference Paper

Error Sensitivity Modulation based Experience Replay: Mitigating Abrupt Representation Drift in Continual Learning

Fahad Sarfraz
Elahe Arani
Bahram Zonooz

Humans excel at lifelong learning, as the brain has evolved to be robust to distribution shifts and noise in our ever-changing environment. Deep neural networks (DNNs), however, exhibit catastrophic forgetting and the learned representations drift drastically as they encounter a new task. This alludes to a different error-based learning mechanism in the brain. Unlike DNNs, where learning scales linearly with the magnitude of the error, the sensitivity to errors in the brain decreases as a function of their magnitude. To this end, we propose "ESMER" which employs a principled mechanism to modulate error sensitivity in a dual-memory rehearsal-based system. Concretely, it maintains a memory of past errors and uses it to modify the learning dynamics so that the model learns more from small consistent errors compared to large sudden errors. We also propose "Error-Sensitive Reservoir Sampling" to maintain episodic memory, which leverages the error history to pre-select low-loss samples as candidates for the buffer, which are better suited for retaining information. Empirical results show that ESMER effectively reduces forgetting and abrupt drift in representations at the task boundary by gradually adapting to the new task while consolidating knowledge. Remarkably, it also enables the model to learn under high levels of label noise, which is ubiquitous in real-world data streams.

Details

ICRA Conference 2023 Conference Paper

Image Masking for Robust Self-Supervised Monocular Depth Estimation

Hemang Chawla
Kishaan Jeeveswaran
Elahe Arani
Bahram Zonooz

Self-supervised monocular depth estimation is a salient task for 3D scene understanding. Learned jointly with monocular ego-motion estimation, several methods have been proposed to predict accurate pixel-wise depth without using labeled data. Nevertheless, these methods focus on improving performance under ideal conditions without natural or digital corruptions. The general absence of occlusions is assumed even for object-specific depth estimation. These methods are also vulnerable to adversarial attacks, which is a pertinent concern for their reliable deployment in robots and autonomous driving systems. We propose MIMDepth, a method that adapts masked image modeling (MIM) for self-supervised monocular depth estimation. While MIM has been used to learn generalizable features during pre-training, we show how it could be adapted for direct training of monocular depth estimation. Our experiments show that MIMDepth is more robust to noise, blur, weather conditions, digital artifacts, occlusions, as well as untargeted and targeted adversarial attacks.

Details

TMLR Journal 2023 Journal Article

Learn, Unlearn and Relearn: An Online Learning Paradigm for Deep Neural Networks

Vijaya Raghavan T Ramkumar
Elahe Arani
Bahram Zonooz

Deep neural networks (DNNs) are often trained on the premise that the complete training data set is provided ahead of time. However, in real-world scenarios, data often arrive in chunks over time. This leads to important considerations about the optimal strategy for training DNNs, such as whether to fine-tune them with each chunk of incoming data (warm-start) or to retrain them from scratch with the entire corpus of data whenever a new chunk is available. While employing the latter for training can be resource-intensive, recent work has pointed out the lack of generalization in warm-start models. Therefore, to strike a balance between efficiency and generalization, we introduce "Learn, Unlearn, and Relearn (LURE)" an online learning paradigm for DNNs. LURE interchanges between the unlearning phase, which selectively forgets the undesirable information in the model through weight reinitialization in a data-dependent manner, and the relearning phase, which emphasizes learning on generalizable features. We show that our training paradigm provides consistent performance gains across datasets in both classification and few-shot settings. We further show that it leads to more robust and well-calibrated models.

PDF Details

ICML Conference 2023 Conference Paper

Multi-Task Structural Learning using Local Task Similarity induced Neuron Creation and Removal

NareshKumar Gurulingan
Bahram Zonooz
Elahe Arani

Multi-task learning has the potential to improve generalization by maximizing positive transfer between tasks while reducing task interference. Fully achieving this potential is hindered by manually designed architectures that remain static throughout training. On the contrary, learning in the brain occurs through structural changes that are in tandem with changes in synaptic strength. Thus, we propose Multi-Task Structural Learning (MTSL) that simultaneously learns the multi-task architecture and its parameters. MTSL begins with an identical single-task network for each task and alternates between a task-learning phase and a structural-learning phase. In the task learning phase, each network specializes in the corresponding task. In each of the structural learning phases, starting from the earliest layer, locally similar task layers first transfer their knowledge to a newly created group layer before being removed. MTSL then uses the group layer in place of the corresponding removed task layers and moves on to the next layers. Our empirical results show that MTSL achieves competitive generalization with various baselines and improves robustness to out-of-distribution data.

Details

AAAI Conference 2023 Conference Paper

Sparse Coding in a Dual Memory System for Lifelong Learning

Fahad Sarfraz
Elahe Arani
Bahram Zonooz

Efficient continual learning in humans is enabled by a rich set of neurophysiological mechanisms and interactions between multiple memory systems. The brain efficiently encodes information in non-overlapping sparse codes, which facilitates the learning of new associations faster with controlled interference with previous associations. To mimic sparse coding in DNNs, we enforce activation sparsity along with a dropout mechanism which encourages the model to activate similar units for semantically similar inputs and have less overlap with activation patterns of semantically dissimilar inputs. This provides us with an efficient mechanism for balancing the reusability and interference of features, depending on the similarity of classes across tasks. Furthermore, we employ sparse coding in a multiple-memory replay mechanism. Our method maintains an additional long-term semantic memory that aggregates and consolidates information encoded in the synaptic weights of the working model. Our extensive evaluation and characteristics analysis show that equipped with these biologically inspired mechanisms, the model can further mitigate forgetting. Code available at \url{https://github.com/NeurAI-Lab/SCoMMER}.

PDF Details DOI

ICLR Conference 2023 Conference Paper

Task-Aware Information Routing from Common Representation Space in Lifelong Learning

Prashant Shivaram Bhat
Bahram Zonooz
Elahe Arani

Intelligent systems deployed in the real world suffer from catastrophic forgetting when exposed to a sequence of tasks. Humans, on the other hand, acquire, consolidate, and transfer knowledge between tasks that rarely interfere with the consolidated knowledge. Accompanied by self-regulated neurogenesis, continual learning in the brain is governed by the rich set of neurophysiological processes that harbor different types of knowledge which are then integrated by the conscious processing. Thus, inspired by Global Workspace Theory of conscious information access in the brain, we propose TAMiL, a continual learning method that entails task-attention modules to capture task-specific information from the common representation space. We employ simple, undercomplete autoencoders to create a communication bottleneck between the common representation space and the global workspace, allowing only the task-relevant information to the global workspace, thereby greatly reducing task interference. Experimental results show that our method outperforms state-of-the-art rehearsal-based and dynamic sparse approaches and bridges the gap between fixed capacity and parameter isolation approaches while being scalable. We also show that our method effectively mitigates catastrophic forgetting while being well-calibrated with reduced task-recency bias.

Details

NeurIPS Conference 2023 Conference Paper

TriRE: A Multi-Mechanism Learning Paradigm for Continual Knowledge Retention and Promotion

Preetha Vijayan
Prashant Bhat
Bahram Zonooz
Elahe Arani

Continual learning (CL) has remained a persistent challenge for deep neural networks due to catastrophic forgetting (CF) of previously learned tasks. Several techniques such as weight regularization, experience rehearsal, and parameter isolation have been proposed to alleviate CF. Despite their relative success, these research directions have predominantly remained orthogonal and suffer from several shortcomings, while missing out on the advantages of competing strategies. On the contrary, the brain continually learns, accommodates, and transfers knowledge across tasks by simultaneously leveraging several neurophysiological processes, including neurogenesis, active forgetting, neuromodulation, metaplasticity, experience rehearsal, and context-dependent gating, rarely resulting in CF. Inspired by how the brain exploits multiple mechanisms concurrently, we propose TriRE, a novel CL paradigm that encompasses retaining the most prominent neurons for each task, revising and solidifying the extracted knowledge of current and past tasks, and actively promoting less active neurons for subsequent tasks through rewinding and relearning. Across CL settings, TriRE significantly reduces task interference and surpasses different CL approaches considered in isolation.

PDF Details

TMLR Journal 2022 Journal Article

A Comprehensive Study of Real-Time Object Detection Networks Across Multiple Domains: A Survey

Elahe Arani
Shruthi Gowda
Ratnajit Mukherjee
Omar Magdy
Senthilkumar Sockalingam Kathiresan
Bahram Zonooz

Deep neural network based object detectors are continuously evolving and are used in a multitude of applications, each having its own set of requirements. While safety-critical applications need high accuracy and reliability, low-latency tasks need resource and energy-efficient networks. Real-time detection networks, which are a necessity in high-impact real-world applications, are continuously proposed but they overemphasize the improvements in accuracy and speed while other capabilities such as versatility, robustness, resource, and energy efficiency are omitted. A reference benchmark for existing networks does not exist nor does a standard evaluation guideline for designing new networks, which results in ambiguous and inconsistent comparisons. We, therefore, conduct a comprehensive study on multiple real-time detection networks (anchor-based, keypoint-based, and transformer-based) on a wide range of datasets and report results on an extensive set of metrics. We also study the impact of variables such as image size, anchor dimensions, confidence thresholds, and architecture layers on the overall performance. We analyze the robustness of detection networks against distribution shift, natural corruptions, and adversarial attacks. Also, we provide the calibration analysis to gauge the reliability of the predictions. Finally, to highlight the real-world impact, we conduct two unique case studies, on autonomous driving and healthcare application. To further gauge the capability of networks in critical real-time applications, we report the performance after deploying the detection networks on edge devices. Our extensive empirical study can act as a guideline for the industrial community to make an informed choice on the existing networks. We also hope to inspire the research community towards a new direction of design and evaluation of networks that focuses on the bigger and holistic overview for a far-reaching impact.

PDF Details

IROS Conference 2022 Conference Paper

Adversarial Attacks on Monocular Pose Estimation

Hemang Chawla
Arnav Varma
Elahe Arani
Bahram Zonooz

Advances in deep learning have resulted in steady progress in computer vision with improved accuracy on tasks such as object detection and semantic segmentation. Nevertheless, deep neural networks are vulnerable to adversarial attacks, thus presenting a challenge in reliable deployment. Two of the prominent tasks in 3D scene-understanding for robotics and advanced driver assistance systems are monocular depth and pose estimation, often learned together in an unsupervised manner. While studies evaluating the impact of adversarial attacks on monocular depth estimation exist, a systematic demonstration and analysis of adversarial perturbations against pose estimation are lacking. We show how additive imperceptible perturbations can not only change predictions to increase the trajectory drift but also catastrophically alter its geometry. We also study the relation between adversarial perturbations targeting monocular depth and pose estimation networks, as well as the transferability of perturbations to other networks with different architectures and losses. Our experiments show how the generated perturbations lead to notable errors in relative rotation and translation predictions and elucidate vulnerabilities of the networks. 1 1 Code can be found at https://github.com/NeurAI-Lab/mono-pose-attack.

Details

ICLR Conference 2022 Conference Paper

Learning Fast, Learning Slow: A General Continual Learning Method based on Complementary Learning System

Elahe Arani
Fahad Sarfraz
Bahram Zonooz

Humans excel at continually learning from an ever-changing environment whereas it remains a challenge for deep neural networks which exhibit catastrophic forgetting. The complementary learning system (CLS) theory suggests that the interplay between rapid instance-based learning and slow structured learning in the brain is crucial for accumulating and retaining knowledge. Here, we propose CLS-ER, a novel dual memory experience replay (ER) method which maintains short-term and long-term semantic memories that interact with the episodic memory. Our method employs an effective replay mechanism whereby new knowledge is acquired while aligning the decision boundaries with the semantic memories. CLS-ER does not utilize the task boundaries or make any assumption about the distribution of the data which makes it versatile and suited for ``general continual learning''. Our approach achieves state-of-the-art performance on standard benchmarks as well as more realistic general continual learning settings.

Details

ICRA Conference 2021 Conference Paper

Multimodal Scale Consistency and Awareness for Monocular Self-Supervised Depth Estimation

Hemang Chawla
Arnav Varma
Elahe Arani
Bahram Zonooz

Dense depth estimation is essential to scene-understanding for autonomous driving. However, recent self-supervised approaches on monocular videos suffer from scale-inconsistency across long sequences. Utilizing data from the ubiquitously copresent global positioning systems (GPS), we tackle this challenge by proposing a dynamically-weighted GPS-to-Scale (g2s) loss to complement the appearance-based losses. We emphasize that the GPS is needed only during the multimodal training, and not at inference. The relative distance between frames captured through the GPS provides a scale signal that is independent of the camera setup and scene distribution, resulting in richer learned feature representations. Through extensive evaluation on multiple datasets, we demonstrate scale-consistent and -aware depth estimation during inference, improving the performance even when training with low-frequency GPS data.

Details

IROS Conference 2020 Conference Paper

Crowdsourced 3D Mapping: A Combined Multi-View Geometry and Self-Supervised Learning Approach

Hemang Chawla
Matti Jukola
Terence Brouns
Elahe Arani
Bahram Zonooz

The ability to efficiently utilize crowd-sourced visual data carries immense potential for the domains of large scale dynamic mapping and autonomous driving. However, state-of-the-art methods for crowdsourced 3D mapping assume prior knowledge of camera intrinsics. In this work we propose a framework that estimates the 3D positions of semantically meaningful landmarks such as traffic signs without assuming known camera intrinsics, using only monocular color camera and GPS. We utilize multi-view geometry as well as deep learning based self-calibration, depth, and ego-motion estimation for traffic sign positioning, and show that combining their strengths is important for increasing the map coverage. To facilitate research on this task, we construct and make available a KITTI based 3D traffic sign ground truth positioning dataset. Using our proposed framework, we achieve an average single-journey relative and absolute positioning accuracy of 39cm and 1. 26m respectively, on this dataset.

Details