Arrow Research search

Author name cluster

Yin Li

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.

14 papers
2 author rows

Possible papers

14

AAAI Conference 2026 Conference Paper

SAM2MOT: A Novel Paradigm of Multi-Object Tracking by Segmentation

  • Junjie Jiang
  • Zelin Wang
  • Manqi Zhao
  • Yin Li
  • Dongsheng Jiang

Inspired by Segment Anything 2, which generalizes segmentation from images to videos, we propose SAM2MOT—a novel segmentation-driven paradigm for multi-object tracking that breaks away from the conventional detection-association framework. In contrast to previous approaches that treat segmentation as auxiliary information, SAM2MOT places it at the heart of the tracking process, systematically tackling challenges like false positives and occlusions. Its effectiveness has been thoroughly validated on major MOT benchmarks. Furthermore, SAM2MOT integrates pre-trained detector, pre-trained segmentor with tracking logic into a zero-shot MOT system that requires no fine-tuning. This significantly reduces dependence on labeled data and paves the way for transitioning MOT research from task-specific solutions to general-purpose systems. Experiments on DanceTrack, UAVDT, and BDD100K show state-of-the-art results. Notably, SAM2MOT outperforms existing methods on DanceTrack by +2.1 HOTA and +4.5 IDF1, highlighting its effectiveness in MOT.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Visual Bridge: Universal Visual Perception Representations Generating

  • Yilin Gao
  • Shuguang Dou
  • Junzhou Li
  • Zhiheng Yu
  • Yin Li
  • Dongsheng Jiang
  • Shugong Xu

Recent advances in diffusion models have achieved remarkable success in isolated computer vision tasks such as text-to-image generation, depth estimation, and optical flow. However, these models are often restricted by a ``single-task-single-model'' paradigm, severely limiting their generalizability and scalability in multi-task scenarios. Motivated by the cross-domain generalization ability of large language models, we propose a universal visual perception framework based on flow matching that can generate diverse visual representations across multiple tasks. Our approach formulates the process as a universal flow-matching problem from image patch tokens to task-specific representations rather than an independent generation or regression problem. By leveraging a strong self-supervised foundation model as the anchor and introducing a multi-scale, circular task embedding mechanism, our method learns a universal velocity field to bridge the gap between heterogeneous tasks, supporting efficient and flexible representation transfer. Extensive experiments on classification, detection, segmentation, depth estimation, and image-text retrieval demonstrate that our model achieves competitive performance in both zero-shot and fine-tuned settings, outperforming prior generalist and several specialist models. Ablation studies further validate the robustness, scalability, and generalization of our framework. Our work marks a significant step towards general-purpose visual perception, providing a solid foundation for future research in universal vision modeling.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Computation and Memory-Efficient Model Compression with Gradient Reweighting

  • Zhiwei Li
  • Yuesen Liao
  • Binrui Wu
  • Yuquan Zhou
  • Xupeng Shi
  • Dongsheng Jiang
  • Yin Li
  • Weizhong Zhang

Pruning is a commonly employed technique for deep neural networks (DNNs) aiming at compressing the model size to reduce computational and memory costs during inference. In contrast to conventional neural networks, large language models (LLMs) pose a unique challenge regarding pruning efficiency due to their substantial computational and memory demands. Existing methods, particularly optimization-based ones, often require considerable computational resources in gradient estimation because they cannot effectively leverage weight sparsity of the intermediate pruned network to lower compuation and memory costs in each iteration. The fundamental challenge lies in the need to frequently instantiate intermediate pruned sub-models to achieve these savings, a task that becomes infeasible even for moderately sized neural networks. To this end, this paper proposes a novel pruning method for DNNs that is both computationally and memory-efficient. Our key idea is to develop an effective reweighting mechanism that enables us to estimate the gradient of the pruned network in current iteration via reweigting the gradient estimated on an outdated intermediate sub-model instantiated at an earlier stage, thereby significantly reducing model instantiation frequency. We further develop a series of techniques, e. g. , clipping and preconditioning matrix, to reduce the variance of gradient estimation and stabilize the optimization process. We conducted extensive experimental validation across various domains. Our approach achieves 50\% sparsity and a 1. 58$\times$ speedup in forward pass on Llama2-7B model with only 6 GB of memory usage, outperforming state-of-the-art methods with respect to both perplexity and zero-shot performance. As a by-product, our method is highly suited for distributed sparse training and can achieve a 2 $\times$ speedup over the dense distributed baselines.

PDF Details

NeurIPS Conference 2025 Conference Paper

Instant Video Models: Universal Adapters for Stabilizing Image-Based Networks

  • Matthew Dutson
  • Nathan Labiosa
  • Yin Li
  • Mohit Gupta

When applied sequentially to video, frame-based networks often exhibit temporal inconsistency—for example, outputs that flicker between frames. This problem is amplified when the network inputs contain time-varying corruptions. In this work, we introduce a general approach for adapting frame-based models for stable and robust inference on video. We describe a class of stability adapters that can be inserted into virtually any architecture and a resource-efficient training process that can be performed with a frozen base network. We introduce a unified conceptual framework for describing temporal stability and corruption robustness, centered on a proposed accuracy-stability-robustness loss. By analyzing the theoretical properties of this loss, we identify the conditions where it produces well-behaved stabilizer training. Our experiments validate our approach on several vision tasks including denoising (NAFNet), image enhancement (HDRNet), monocular depth (Depth Anything v2), and semantic segmentation (DeepLabv3+). Our method improves temporal stability and robustness against a range of image corruptions (including compression artifacts, noise, and adverse weather), while preserving or improving the quality of predictions.

PDF Details

ICLR Conference 2023 Conference Paper

InPL: Pseudo-labeling the Inliers First for Imbalanced Semi-supervised Learning

  • Zhuoran Yu
  • Yin Li
  • Yong Jae Lee

Recent state-of-the-art methods in imbalanced semi-supervised learning (SSL) rely on confidence-based pseudo-labeling with consistency regularization. To obtain high-quality pseudo-labels, a high confidence threshold is typically adopted. However, it has been shown that softmax-based confidence scores in deep networks can be arbitrarily high for samples far from the training data, and thus, the pseudo-labels for even high-confidence unlabeled samples may still be unreliable. In this work, we present a new perspective of pseudo-labeling for imbalanced SSL. Without relying on model confidence, we propose to measure whether an unlabeled sample is likely to be "in-distribution''; i.e., close to the current training data. To decide whether an unlabeled sample is "in-distribution'' or "out-of-distribution'', we adopt the energy score from out-of-distribution detection literature. As training progresses and more unlabeled samples become in-distribution and contribute to training, the combined labeled and pseudo-labeled data can better approximate the true class distribution to improve the model. Experiments demonstrate that our energy-based pseudo-labeling method, InPL, albeit conceptually simple, significantly outperforms confidence-based methods on imbalanced SSL benchmarks. For example, it produces a 4-6% absolute accuracy improvement on CIFAR10-LT when the imbalance ratio is higher than 50. When combined with state-of-the-art long-tailed SSL methods, further improvements are attained. In particular, in one of the most challenging scenarios, InPL achieves a 6.9% accuracy improvement over the best competitor.

Details

NeurIPS Conference 2022 Conference Paper

mRI: Multi-modal 3D Human Pose Estimation Dataset using mmWave, RGB-D, and Inertial Sensors

  • Sizhe An
  • Yin Li
  • Umit Ogras

The ability to estimate 3D human body pose and movement, also known as human pose estimation (HPE), enables many applications for home-based health monitoring, such as remote rehabilitation training. Several possible solutions have emerged using sensors ranging from RGB cameras, depth sensors, millimeter-Wave (mmWave) radars, and wearable inertial sensors. Despite previous efforts on datasets and benchmarks for HPE, few dataset exploits multiple modalities and focuses on home-based health monitoring. To bridge the gap, we present mRI, a multi-modal 3D human pose estimation dataset with mmWave, RGB-D, and Inertial Sensors. Our dataset consists of over 160k synchronized frames from 20 subjects performing rehabilitation exercises and supports the benchmarks of HPE and action detection. We perform extensive experiments using our dataset and delineate the strength of each modality. We hope that the release of mRI can catalyze the research in pose estimation, multi-modal learning, and action understanding, and more importantly facilitate the applications of home-based health monitoring.

PDF Details

AAAI Conference 2021 Conference Paper

Nyströmformer: A Nyström-based Algorithm for Approximating Self-Attention

  • Yunyang Xiong
  • Zhanpeng Zeng
  • Rudrasis Chakraborty
  • Mingxing Tan
  • Glenn Fung
  • Yin Li
  • Vikas Singh

Transformers have emerged as a powerful tool for a broad range of natural language processing tasks. A key component that drives the impressive performance of Transformers is the self-attention mechanism that encodes the influence or dependence of other tokens on each specific token. While beneficial, the quadratic complexity of self-attention on the input sequence length has limited its application to longer sequences – a topic being actively studied in the community. To address this limitation, we propose Nyströmformer – a model that exhibits favorable scalability as a function of sequence length. Our idea is based on adapting the Nyström method to approximate standard self-attention with O(n) complexity. The scalability of Nyströmformer enables application to longer sequences with thousands of tokens. We perform evaluations on multiple downstream tasks on the GLUE benchmark and IMDB reviews with standard sequence length, and find that our Nyströmformer performs comparably, or in a few cases, even slightly better, than standard self-attention. On longer sequence tasks in the Long Range Arena (LRA) benchmark, Nyströmformer performs favorably relative to other efficient self-attention methods. Our code is available at https: //github. com/mlpen/Nystromformer.

PDF Details

NeurIPS Conference 2018 Conference Paper

Beyond Grids: Learning Graph Representations for Visual Recognition

  • Yin Li
  • Abhinav Gupta

We propose learning graph representations from 2D feature maps for visual recognition. Our method draws inspiration from region based recognition, and learns to transform a 2D image into a graph structure. The vertices of the graph define clusters of pixels ("regions"), and the edges measure the similarity between these clusters in a feature space. Our method further learns to propagate information across all vertices on the graph, and is able to project the learned graph representation back into 2D grids. Our graph representation facilitates reasoning beyond regular grids and can capture long range dependencies among regions. We demonstrate that our model can be trained from end-to-end, and is easily integrated into existing networks. Finally, we evaluate our method on three challenging recognition tasks: semantic segmentation, object detection and object instance segmentation. For all tasks, our method outperforms state-of-the-art methods.

PDF Details

IJCAI Conference 2018 Conference Paper

Densely Cascaded Shadow Detection Network via Deeply Supervised Parallel Fusion

  • Yupei Wang
  • Xin Zhao
  • Yin Li
  • Xuecai Hu
  • Kaiqi Huang

Shadow detection is an important and challenging problem in computer vision. Recently, single image shadow detection had achieved major progress with the development of deep convolutional networks. However, existing methods are still vulnerable to background clutters, and often fail to capture the global context of an input image. These global contextual and semantic cues are essential for accurately localizing the shadow regions. Moreover, rich spatial details are required to segment shadow regions with precise shape. To this end, this paper presents a novel model characterized by a deeply supervised parallel fusion (DSPF) network and a densely cascaded learning scheme. The DSPF network achieves a comprehensive fusion of global semantic cues and local spatial details by multiple stacked parallel fusion branches, which are learned in a deeply supervised manner. Moreover, the densely cascaded learning scheme is employed to refine the spatial details. Our method is evaluated on two widely used shadow detection benchmarks. Experimental results show that our method outperforms state-of-the-arts by a large margin.

PDF Details

RLDM Conference 2013 Conference Abstract

Activity of anterior and posterior cingulate cortex during an adap- tive learning task

  • Yin Li
  • Matt Nassar
  • Joshua Gold

Many environments are characterized by periods of stability punctuated by sudden changes. A rational agent navigating such a dynamic environment should adaptively adjust the relative influence of newly acquired and previously accrued information in making decisions. The goal of this study is to identify neural correlates of this adaptive learning process in the anterior cingulate cortex (ACC) and the posterior cingulate cortex (PCC), two brain regions known to play roles in reward processing and task control. We recorded from the ACC of two monkeys and the PCC of one monkey while they performed a ten-alternative saccadic-choice task. This task involved static fluctuations (noise) as well as abrupt changes (changepoints) in the identity of the rewarded target. Performance of the monkeys indicated that they learned to adjust the influence of feedback on individual trials in an adaptive manner. We found units in both ACC and PCC that responded preferentially to reward or error feedback. Both areas also contained units with baseline activity that reflected the noise condition. Suggestively, a significant fraction of units in both areas differentiated between errors in the high-noise condition and errors in the low-noise condition, just as the monkeys treated errors differently in the two noise conditions. These results are consistent with the involvement of ACC and PCC in signaling contexts appropriate for adaptive adjustment of learning in a dynamic environment.

PDF Details