CVOct 24, 2025

TokenCLIP: Token-wise Prompt Learning for Zero-shot Anomaly Detection

arXiv:2510.21171v21 citationsh-index: 12
AI Analysis

This work addresses fine-grained anomaly detection for unseen objects in computer vision, representing an incremental improvement over existing CLIP-based methods.

The paper tackles the problem of aligning visual and textual semantics for zero-shot anomaly detection by proposing TokenCLIP, a token-wise adaptation framework that dynamically assigns visual tokens to customized textual subspaces, achieving state-of-the-art results in experiments.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes