线性子空间
计算机科学
安全性令牌
异常检测
子空间拓扑
集合(抽象数据类型)
语义学(计算机科学)
光学(聚焦)
人工智能
遮罩(插图)
视觉空间
空格(标点符号)
可视化
计算机视觉
平面图(考古学)
异常(物理)
适应(眼睛)
模式识别(心理学)
路径(计算)
理论计算机科学
数据集
图像(数学)
作者
Qihang Zhou,Binbin Gao,Guansong Pang,Xin Wang,Jiming Chen,Shibo He
标识
DOI:10.48550/arxiv.2510.21171
摘要
Adapting CLIP for anomaly detection on unseen objects has shown strong potential in a zero-shot manner. However, existing methods typically rely on a single textual space to align with visual semantics across diverse objects and domains. The indiscriminate alignment hinders the model from accurately capturing varied anomaly semantics. We propose TokenCLIP, a token-wise adaptation framework that enables dynamic alignment between visual and learnable textual spaces for fine-grained anomaly learning. Rather than mapping all visual tokens to a single, token-agnostic textual space, TokenCLIP aligns each token with a customized textual subspace that represents its visual characteristics. Explicitly assigning a unique learnable textual space to each token is computationally intractable and prone to insufficient optimization. We instead expand the token-agnostic textual space into a set of orthogonal subspaces, and then dynamically assign each token to a subspace combination guided by semantic affinity, which jointly supports customized and efficient token-wise adaptation. To this end, we formulate dynamic alignment as an optimal transport problem, where all visual tokens in an image are transported to textual subspaces based on semantic similarity. The transport constraints of OT ensure sufficient optimization across subspaces and encourage them to focus on different semantics. Solving the problem yields a transport plan that adaptively assigns each token to semantically relevant subspaces. A top-k masking is then applied to sparsify the plan and specialize subspaces for distinct visual regions. Extensive experiments demonstrate the superiority of TokenCLIP.
科研通智能强力驱动
Strongly Powered by AbleSci AI