通过去除确定性高的冗余令牌，提升视觉基础模型在伪装目标检测中的效率。
Certainty Is Redundant: Token Sparsification for Efficient Camouflaged Object Detection with Vision Foundation Models
- 根据前景背景确定性动态剪枝高置信度令牌
- 计算量减少同时仅损失少量精度（如4.3%）
- 适合资源受限场景下的高效伪装目标检测
伪装目标检测（COD）旨在分割与环境高度相似的物体。视觉基础模型（VFMs）为COD提供了强大的可迁移表征，但其大规模架构和全令牌处理带来巨大计算开销。为此，本文提出确定性感知令牌稀疏化（CATS），不评估通用令牌重要性，而是根据每个令牌的前景-背景确定性判断是否仍需深层优化。高确定性令牌被逐步终止独立更新，仅保留模糊令牌继续推理，从而缩短编码器各阶段的活跃令牌序列。由于计算冗余不代表信息无关，进一步引入双路径特征补偿（DPFC），将移除的前景与背景令牌分别压缩为紧凑的确定性加权原型。在多个VFMs、骨干网络规模、COD架构及基准数据集上的实验表明，该方法显著降低计算成本，精度下降仅约4.3%，展现出良好的精度-效率权衡。代码将公开。
原文摘要 · Abstract (English)
Camouflaged object detection (COD) aims to segment objects that closely resemble their surrounding environments. Vision foundation models (VFMs) provide strong transferable representations for COD, but their large-scale architectures and full-token processing incur substantial computational overhead. To address this issue, we propose Certainty-Aware Token Sparsification (CATS) for efficient VFM-based COD. Rather than estimating general token importance, CATS determines whether each token still requires deeper refinement according to its foreground--background certainty. It progressively terminates the independent updates of high-certainty tokens while retaining ambiguous tokens for further reasoning, thereby shortening the active token sequence across encoder stages. Since computational redundancy does not imply informational irrelevance, we further introduce Dual-Path Feature Compensation (DPFC), which separately compresses removed foreground and background tokens into compact certainty-weighted prototypes. Extensive experiments across multiple VFMs, backbone scales, COD architectures, and benchmark datasets show that our method significantly reduces computational cost with only marginal accuracy degradation, suggesting a favorable accuracy--efficiency trade-off for VFM-based COD. The code will be released.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。