paper-with-me

Papers

Context-Aware Token Pruning and Discriminative Selective Attention for Transformer Tracking

2025-11-25 · Janani Kugarajeevan, Thanikasalam Kokul, Amirthalingam Ramanan, Subha Fernando arxiv

One-stream Transformer-based trackers have demonstrated remarkable performance by concatenating template and search region tokens, thereby enabling joint attention across all tokens. However, enabling an excessive proportion of background search tokens to attend to the target template tokens weakens the tracker's discriminative capability. Several token pruning methods have been proposed to mitigate background interference; however, they often remove tokens near the target, leading to the loss of essential contextual information and degraded tracking performance. Moreover, the presence of distractors within the search tokens further reduces the tracker's ability to accurately identify the target. To address these limitations, we propose CPDATrack, a novel tracking framework designed to suppress interference from background and distractor tokens while enhancing computational efficiency. First, a learnable module is integrated between two designated encoder layers to estimate the probability of each search token being associated with the target. Based on these estimates, less-informative background tokens are pruned from the search region while preserving the contextual cues surrounding the target. To further suppress background interference, a discriminative selective attention mechanism is employed that fully blocks search-to-template attention in the early layers. In the subsequent encoder layers, high-probability target tokens are selectively extracted from a localized region to attend to the template tokens, thereby reducing the influence of background and distractor tokens. The proposed CPDATrack achieves state-of-the-art performance across multiple benchmarks, particularly on GOT-10k, where it attains an average overlap of 75.1 percent.

📄 PDF Abstract BibTeX arXiv:2511.19928

Code (0)

등록된 구현이 없습니다.

Tasks

Computational Efficiency

Similar Papers 제목 키워드 기반

Neighbor-Aware Token Reduction via Hilbert Curve for Vision Transformers

2025-12-28 · Yunge Li, Lanyu Xu arxiv

Vision Transformers (ViTs) have achieved remarkable success in visual recognition tasks, but redundant token representations limit their computational efficiency. Existing token merging and pruning strategies often overl…

Computational Efficiency

Constraint-aware and Ranking-distilled Token Pruning for Efficient Transformer Inference

2023-06-26 · Junyan Li, Li Lyna Zhang, Jiahang Xu, Yujing Wang 외

Deploying pre-trained transformer models like BERT on downstream tasks in resource-constrained scenarios is challenging due to their high inference cost, which grows rapidly with input sequence length. In this work, we p…

CPUModel Compression

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models

2026-05-13 · Mingzhe Huang, Weijun Wang, Xin Ding, Liang Mi 외 arxiv

In Vision-Language Models (VLMs), processing a massive number of visual tokens incurs prohibitive computational overhead. While recent training-aware pruning methods attempt to selectively discard redundant tokens, they …

Reinforcement Learning

SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents

2026-01-23 · Yuhang Wang, Yuling Shi, Mo Yang, Rongrui Zhang 외 arxiv

LLM agents have demonstrated remarkable capabilities in software development, but their performance is hampered by long interaction contexts, which incur high API costs and latency. While various context compression appr…

VLM-Pruner: Buffering for Spatial Sparsity in an Efficient VLM Centrifugal Token Pruning Paradigm

2025-12-02 · Zhenkai Wu, Xiaowen Ma, Zhenliang Ni, Dengming Zhang 외 arxiv

Vision-language models (VLMs) excel at image understanding tasks, but the large number of visual tokens imposes significant computational costs, hindering deployment on mobile devices. Many pruning methods rely solely on…