arXiv cs.AI· Xiaoya Tang, Shilong Liu, Daniel Smolyak, Xiwen Li, Quynh Nguyen, Tolga Tasdizen·· 3 天前AI 评分22
ReConV：用表示重建实现视觉 token 压缩
Bottlenecked semantic compression by representation reconstruction
AI 导读
研究者提出视觉 token 压缩框架 ReConV，用紧凑的 Summary Bank（SMB）汇总完整视觉序列，并依据重建残差保留 SMB 未能充分捕捉的 token，每个压缩层由轻量位置条件解码器重建当前 token。在 ImageNet 上，ReConV 以少 48% GMACs 超过未压缩基线，并支持可复用的图像级表示以加速多轮推理。代码已发布于 TokenDrop。
正文 · 原文
Abstract:Vision Transformers incur high computational costs when processing long visual token sequences. Existing reduction methods typically rank tokens independently and discard those deemed unimportant or redundant. We propose a reconstruction-guided framework for visual token condensation (ReConV), which summarizes the complete visual sequence with a compact Summary Bank (SMB) and retains tokens whose information is not adequately captured by the SMB, as indicated by their reconstruction residuals. At each compression layer, a lightweight position-conditioned decoder reconstructs the current tokens, leaving shared information compressed in the SMB while explicitly preserving poorly reconstructed details. Experiments on image classification and multimodal understanding demonstrate favorable performance-efficiency trade-offs: ReConV surpasses the uncompressed baseline with 48\% fewer GMACs on ImageNet and enables reusable image-level representations for efficient multi-turn inference. Code is available at TokenDrop.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.17412 [cs.CV] |
| (or arXiv:2610.17412v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.17412 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Xiaoya Tang [view email]
[v1]
Mon, 12 Oct 2026 21:24:38 UTC (35,199 KB)
来源：arXiv cs.AI · arxiv.org