Author name cluster

Motasem Alfarra

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.

11 papers

2 author rows

TMLR Journal 2026 Journal Article

Forget Less, Retain More: A Lightweight Regularizer for Rehearsal-Based Continual Learning

Lama Alssum
Hasan Abed Al Kader Hammoud
Motasem Alfarra
Juan C Leon Alcazar
Bernard Ghanem

Deep neural networks suffer from catastrophic forgetting, where performance on previous tasks degrades after training on a new task. This issue arises due to the model’s tendency to overwrite previously acquired knowledge with new information. We present a novel approach to address this challenge, focusing on the intersection of memory-based methods and regularization approaches. We formulate a regularization strategy, termed Information Maximization (IM) regularizer, for memory-based continual learning methods, which is based exclusively on the expected label distribution, thus making it class-agnostic. As a consequence, IM regularizer can be directly integrated into various rehearsal-based continual learning methods, reducing forgetting and favoring faster convergence. Our empirical validation shows that, across datasets and regardless of the number of tasks, our proposed regularization strategy consistently improves baseline performance at the expense of a minimal computational overhead. The lightweight nature of IM ensures that it remains a practical and scalable solution, making it applicable to real-world continual learning scenarios where efficiency is paramount. Finally, we demonstrate the data-agnostic nature of our regularizer by applying it to video data, which presents additional challenges due to its temporal structure and higher memory requirements. Despite the significant domain gap, our experiments show that IM regularizer also improves the performance of video continual learning methods.

PDF Details

ICLR Conference 2025 Conference Paper

Test-Time Adaptation for Combating Missing Modalities in Egocentric Videos

Merey Ramazanova
Alejandro Pardo
Bernard Ghanem
Motasem Alfarra

Understanding videos that contain multiple modalities is crucial, especially in egocentric videos, where combining various sensory inputs significantly improves tasks like action recognition and moment localization. However, real-world applications often face challenges with incomplete modalities due to privacy concerns, efficiency needs, or hardware issues. Current methods, while effective, often necessitate retraining the model entirely to handle missing modalities, making them computationally intensive, particularly with large training datasets. In this study, we propose a novel approach to address this issue at test time without requiring retraining. We frame the problem as a test-time adaptation task, where the model adjusts to the available unlabeled data at test time. Our method, MiDl~(Mutual information with self-Distillation), encourages the model to be insensitive to the specific modality source present during testing by minimizing the mutual information between the prediction and the available modality. Additionally, we incorporate self-distillation to maintain the model's original performance when both modalities are available. MiDl represents the first self-supervised, online solution for handling missing modalities exclusively at test time. Through experiments with various pretrained models and datasets, MiDl demonstrates substantial performance improvement without the need for retraining.

Details

TMLR Journal 2025 Journal Article

Test-Time Adaptation with Source Based Auxiliary Tasks

Motasem Alfarra
Alvaro Correia
Bernard Ghanem
Christos Louizos

This work tackles a key challenge in Test Time Adaptation~(TTA): adapting on limited data. This challenge arises naturally from two scenarios. (i) Current TTA methods are limited by the bandwidth with which the stream reveals data, since conducting several adaptation steps on each revealed batch from the stream will lead to overfitting. (ii) In many realistic scenarios, the stream reveals insufficient data for the model to fully adapt to a given distribution shift. We tackle the first scenario problem with auxiliary tasks where we leverage unlabeled data from the training distribution. In particular, we propose distilling the predictions of an originally pretrained model on clean data during adaptation. We found that our proposed auxiliary task significantly accelerates the adaptation to distribution shifts. We report a performance improvement over the state of the art by 1.5\% and 6\% on average across all corruptions on ImageNet-C under episodic and continual evaluation, respectively. To combat the second scenario of limited data, we analyze the effectiveness of combining federated adaptation with our proposed auxiliary task across different models even when different clients observe different distribution shifts. We find that not only federated averaging enhances adaptation, but combining it with our auxiliary task provides a notable 6\% performance gains over previous TTA methods.

PDF Details

ICML Conference 2024 Conference Paper

Evaluation of Test-Time Adaptation Under Computational Time Constraints

Motasem Alfarra
Hani Itani
Alejandro Pardo
Shyma Alhuwaider
Merey Ramazanova
Juan Camilo Pérez
Zhipeng Cai 0003
Matthias Müller 0011

This paper proposes a novel online evaluation protocol for Test Time Adaptation (TTA) methods, which penalizes slower methods by providing them with fewer samples for adaptation. TTA methods leverage unlabeled data at test time to adapt to distribution shifts. Though many effective methods have been proposed, their impressive performance usually comes at the cost of significantly increased computation budgets. Current evaluation protocols overlook the effect of this extra computation cost, affecting their real-world applicability. To address this issue, we propose a more realistic evaluation protocol for TTA methods, where data is received in an online fashion from a constant-speed data stream, thereby accounting for the method’s adaptation speed. We apply our proposed protocol to benchmark several TTA methods on multiple datasets and scenarios. Extensive experiments shows that, when accounting for inference speed, simple and fast approaches can outperform more sophisticated but slower methods. For example, SHOT from 2020, outperforms the state-of-the-art method SAR from 2023 under our online setting. Our results reveal the importance of developing practical TTA methods that are both accurate and efficient.

Details

AAAI Conference 2024 Conference Paper

SimCS: Simulation for Domain Incremental Online Continual Segmentation

Motasem Alfarra
Zhipeng Cai
Adel Bibi
Bernard Ghanem
Matthias Müller

Continual Learning is a step towards lifelong intelligence where models continuously learn from recently collected data without forgetting previous knowledge. Existing continual learning approaches mostly focus on image classification in the class-incremental setup with clear task boundaries and unlimited computational budget. This work explores the problem of Online Domain-Incremental Continual Segmentation (ODICS), where the model is continually trained over batches of densely labeled images from different domains, with limited computation and no information about the task boundaries. ODICS arises in many practical applications. In autonomous driving, this may correspond to the realistic scenario of training a segmentation model over time on a sequence of cities. We analyze several existing continual learning methods and show that they perform poorly in this setting despite working well in class-incremental segmentation. We propose SimCS, a parameter-free method complementary to existing ones that uses simulated data to regularize continual learning. Experiments show that SimCS provides consistent improvements when combined with different CL methods.

PDF Details DOI

ICML Conference 2024 Conference Paper

Towards Interpretable Deep Local Learning with Successive Gradient Reconciliation

Yibo Yang
Xiaojie Li
Motasem Alfarra
Hasan Abed Al Kader Hammoud
Adel Bibi
Philip H. S. Torr
Bernard Ghanem

Relieving the reliance of neural network training on a global back-propagation (BP) has emerged as a notable research topic due to the biological implausibility and huge memory consumption caused by BP. Among the existing solutions, local learning optimizes gradient-isolated modules of a neural network with local errors and has been proved to be effective even on large-scale datasets. However, the reconciliation among local errors has never been investigated. In this paper, we first theoretically study non-greedy layer-wise training and show that the convergence cannot be assured when the local gradient in a module w. r. t. its input is not reconciled with the local gradient in the previous module w. r. t. its output. Inspired by the theoretical result, we further propose a local training strategy that successively regularizes the gradient reconciliation between neighboring modules without breaking gradient isolation or introducing any learnable parameters. Our method can be integrated into both local-BP and BP-free settings. In experiments, we achieve significant performance improvements compared to previous methods. Particularly, our method for CNN and Transformer architectures on ImageNet is able to attain a competitive performance with global BP, saving more than 40% memory consumption.

Details

TMLR Journal 2023 Journal Article

Generalizability of Adversarial Robustness Under Distribution Shifts

Kumail Alhamoud
Hasan Abed Al Kader Hammoud
Motasem Alfarra
Bernard Ghanem

Recent progress in empirical and certified robustness promises to deliver reliable and deployable Deep Neural Networks (DNNs). Despite that success, most existing evaluations of DNN robustness have been done on images sampled from the same distribution on which the model was trained on. However, in the real world, DNNs may be deployed in dynamic environments that exhibit significant distribution shifts. In this work, we take a first step towards thoroughly investigating the interplay between empirical and certified adversarial robustness on one hand and domain generalization on another. To do so, we train robust models on multiple domains and evaluate their accuracy and robustness on an unseen domain. We observe that: (1) both empirical and certified robustness generalize to unseen domains, and (2) the level of generalizability does not correlate well with input visual similarity, measured by the FID between source and target domains. We also extend our study to cover a real-world medical application, in which adversarial augmentation significantly boosts the generalization of robustness with minimal effect on clean data accuracy.

PDF Details

TMLR Journal 2022 Journal Article

ANCER: Anisotropic Certification via Sample-wise Volume Maximization

Francisco Eiras
Motasem Alfarra
Philip Torr
M. Pawan Kumar
Puneet K. Dokania
Bernard Ghanem
Adel Bibi

Randomized smoothing has recently emerged as an effective tool that enables certification of deep neural network classifiers at scale. All prior art on randomized smoothing has focused on isotropic $\ell_p$ certification, which has the advantage of yielding certificates that can be easily compared among isotropic methods via $\ell_p$-norm radius. However, isotropic certification limits the region that can be certified around an input to worst-case adversaries, i.e., it cannot reason about other "close", potentially large, constant prediction safe regions. To alleviate this issue, (i) we theoretically extend the isotropic randomized smoothing $\ell_1$ and $\ell_2$ certificates to their generalized anisotropic counterparts following a simplified analysis. Moreover, (ii) we propose evaluation metrics allowing for the comparison of general certificates - a certificate is superior to another if it certifies a superset region - with the quantification of each certificate through the volume of the certified region. We introduce ANCER, a framework for obtaining anisotropic certificates for a given test set sample via volume maximization. We achieve it by generalizing memory-based certification of data-dependent classifiers. Our empirical results demonstrate that ANCER achieves state-of-the-art $\ell_1$ and $\ell_2$ certified accuracy on CIFAR-10 and ImageNet in the data-dependence setting, while certifying larger regions in terms of volume, highlighting the benefits of moving away from isotropic analysis.

PDF Details

AAAI Conference 2022 Conference Paper

Combating Adversaries with Anti-adversaries

Motasem Alfarra
Juan C. Perez
Ali Thabet
Adel Bibi
Philip H.S. Torr
Bernard Ghanem

Deep neural networks are vulnerable to small input perturbations known as adversarial attacks. Inspired by the fact that these adversaries are constructed by iteratively minimizing the confidence of a network for the true class label, we propose the anti-adversary layer, aimed at countering this effect. In particular, our layer generates an input perturbation in the opposite direction of the adversarial one and feeds the classifier a perturbed version of the input. Our approach is trainingfree and theoretically supported. We verify the effectiveness of our approach by combining our layer with both nominally and robustly trained models and conduct large-scale experiments from black-box to adaptive attacks on CIFAR10, CIFAR100, and ImageNet. Our layer significantly enhances model robustness while coming at no cost on clean accuracy.

PDF Details

UAI Conference 2022 Conference Paper

Data dependent randomized smoothing

Motasem Alfarra
Adel Bibi
Philip H. S. Torr
Bernard Ghanem

Randomized smoothing is a recent technique that achieves state-of-art performance in training certifiably robust deep neural networks. While the smoothing family of distributions is often connected to the choice of the norm used for certification, the parameters of these distributions are always set as global hyper parameters independent from the input data on which a network is certified. In this work, we revisit Gaussian randomized smoothing and show that the variance of the Gaussian distribution can be optimized at each input so as to maximize the certification radius for the construction of the smooth classifier. Since the data dependent classifier does not directly enjoy sound certification with existing approaches, we propose a memory-enhanced data dependent smooth classifier that is certifiable by construction. This new approach is generic, parameter-free, and easy to implement. In fact, we show that our data dependent framework can be seamlessly incorporated into 3 randomized smoothing approaches, leading to consistent improved certified accuracy. When this framework is used in the training routine of these approaches followed by a data dependent certification, we achieve 9% and 6% improvement over the certified accuracy of the strongest baseline for a radius of 0. 5 on CIFAR10 and ImageNet.

Details

AAAI Conference 2022 Conference Paper

DeformRS: Certifying Input Deformations with Randomized Smoothing

Motasem Alfarra
Adel Bibi
Naeemullah Khan
Philip H.S. Torr
Bernard Ghanem

Deep neural networks are vulnerable to input deformations in the form of vector fields of pixel displacements and to other parameterized geometric deformations e. g. translations, rotations, etc. Current input deformation certification methods either (i) do not scale to deep networks on large input datasets, or (ii) can only certify a specific class of deformations, e. g. only rotations. We reformulate certification in randomized smoothing setting for both general vector field and parameterized deformations and propose DEFORMRS-VF and DEFORMRS-PAR, respectively. Our new formulation scales to large networks on large input datasets. For instance, DEFORMRS-PAR certifies rich deformations, covering translations, rotations, scaling, affine deformations, and other visually aligned deformations such as ones parameterized by Discrete-Cosine-Transform basis. Extensive experiments on MNIST, CIFAR10, and ImageNet show competitive performance of DEFORMRS-PAR achieving a certified accuracy of 39% against perturbed rotations in the set [−10◦, 10◦ ] on ImageNet.

PDF Details