paper-with-me

홈 › Papers

CompTrack: Information Bottleneck-Guided Low-Rank Dynamic Token Compression for Point Cloud Tracking

2025-11-19 · Sifan Zhou, Yichao Cao, Jiahao Nie, Yuqian Fu, Ziyu Zhao, Xiaobo Lu, Shuo Wang arxiv

3D single object tracking (SOT) in LiDAR point clouds is a critical task in computer vision and autonomous driving. Despite great success having been achieved, the inherent sparsity of point clouds introduces a dual-redundancy challenge that limits existing trackers: (1) vast spatial redundancy from background noise impairs accuracy, and (2) informational redundancy within the foreground hinders efficiency. To tackle these issues, we propose CompTrack, a novel end-to-end framework that systematically eliminates both forms of redundancy in point clouds. First, CompTrack incorporates a Spatial Foreground Predictor (SFP) module to filter out irrelevant background noise based on information entropy, addressing spatial redundancy. Subsequently, its core is an Information Bottleneck-guided Dynamic Token Compression (IB-DTC) module that eliminates the informational redundancy within the foreground. Theoretically grounded in low-rank approximation, this module leverages an online SVD analysis to adaptively compress the redundant foreground into a compact and highly informative set of proxy tokens. Extensive experiments on KITTI, nuScenes and Waymo datasets demonstrate that CompTrack achieves top-performing tracking performance with superior efficiency, running at a real-time 90 FPS on a single RTX 3090 GPU.

📄 PDF Abstract BibTeX arXiv:2511.15580

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous DrivingObject TrackingPoint Clouds

Similar Papers 제목 키워드 기반

Enhancing Phrase Representation by Information Bottleneck Guided Text Diffusion Process for Keyphrase Extraction

2023-08-17 · Yuanzhen Luo, Qingyu Zhou, Feng Zhou

Keyphrase extraction (KPE) is an important task in Natural Language Processing for many scenarios, which aims to extract keyphrases that are present in a given document. Many existing supervised methods treat KPE as sequ…

Keyphrase Extraction

Not All Directions Matter: Towards Structured and Task-Aware Low-Rank Model Adaptation

2026-03-15 · Xi Xiao, Chenrui Ma, Yunbei Zhang, Chen Liu 외 arxiv

Low-Rank Adaptation (LoRA) has become a cornerstone of parameter-efficient fine-tuning (PEFT). Yet, its efficacy is hampered by two fundamental limitations: semantic drift, by treating all update directions with equal im…

parameter-efficient fine-tuning

Multimodal Conditional Information Bottleneck for Generalizable AI-Generated Image Detection

2025-05-21 · Haotian Qin, Dongliang Chang, Yueying Gao, Bingyao Yu 외

Although existing CLIP-based methods for detecting AI-generated images have achieved promising results, they are still limited by severe feature redundancy, which hinders their generalization ability. To address this iss…

Unsupervised Landmark Discovery Using Consistency Guided Bottleneck

2023-09-19 · Mamona Awan, Muhammad Haris Khan, Sanoojan Baliah, Muhammad Ahmad Waseem 외

We study a challenging problem of unsupervised discovery of object landmarks. Many recent methods rely on bottlenecks to generate 2D Gaussian heatmaps however, these are limited in generating informed heatmaps while trai…

Image Reconstruction

Optimizing EEG Graph Structure for Seizure Detection: An Information Bottleneck and Self-Supervised Learning Approach

2026-04-02 · Lincan Li, Rikuto Kotoge, Xihao Piao, Zheng Chen 외 arxiv

Seizure detection from EEG signals is highly challenging due to complex spatiotemporal dynamics and extreme inter-patient variability. To model them, recent methods construct dynamic graphs via statistical correlations, …

Self-Supervised LearningRepresentation LearningSeizure Detection