剪掉93%的图片token，检索反而更准
多向量检索模型（如ColPali）用大量图片token保留细节，但存储和计算成本高。现有压缩方法会误删关键物体证据。这篇提出SaMer：训练时用物体标注（无需推理时检测器）指导token合并，把图片token压缩到64个代表点，保留每个物体独立证据。结果：剪掉93%的token，存储缩小16倍，检索准确率反而提升。核心洞察：不是token越少越好，而是保留未来查询可能需要的物体证据。它不是你明天能用上的，但指明了高效检索的新方向：压缩必须“物体感知”。
📄 原文摘要(英文)
Multi-vector vision-language retrieval preserves fine-grained visual evidence through maximum-similarity late interaction, but dense image-side tokens make storage and scoring expensive. Existing token compression methods reduce this cost, yet they can remove or collapse object- and region-level evidence that future query tokens may need to select. We propose SaMer, an object-aware token merging framework that compresses image-side post-projector tokens into K representative centroids while preserving the original late-interaction interface. SaMer uses object annotations only during training as a merge prior to discourage cross-instance mixing, requires no ground-truth bounding boxes or detectors at inference time, and adapts only the shared projection layer with frozen vision and language backbones. With K=64, SaMer removes more than 93% of image-side tokens and reduces ColPali storage by 16.09times, while improving R@1 on Flickr30K and MSCOCO. These gains arise because object-aware merging preserves query-selectable object evidence that pruning or feature-only pooling can remove or collapse. SaMer also outperforms compression baselines and shows stronger phrase-level grounding, suggesting that efficient multi-vector retrieval depends not only on reducing token count, but on preserving the evidence future query tokens need to select.