TIPS Over Tricks: Simple Prompts for Effective Zero-shot Anomaly Detection

Alireza Salehi, Ehsan Karami, Sepehr Noey, Sahand Noey, Makoto Yamada +2 more
2/3/2026
cs.CV

No official code found. Best implementation: AlirezaSalehy/Tipsomaly (12 stars, MIT, last commit 2026-02-25).

Abstract

Anomaly detection identifies departures from expected behavior in safety-critical settings. When target-domain normal data are unavailable, zero-shot anomaly detection (ZSAD) leverages vision-language models (VLMs). However, CLIP's coarse image-text alignment limits both localization and detection due to (i) spatial misalignment and (ii) weak sensitivity to fine-grained anomalies; prior works compensate with complex auxiliary modules yet largely overlook the choice of backbone. We revisit the backbone and use TIPS-a VLM trained with spatially aware objectives. While TIPS alleviates CLIP's issues, it exposes a distributional gap between global and local features. We address this with decoupled prompts-fixed for image-level detection and learnable for pixel-level localization-and by injecting local evidence into the global score. Without CLIP-specific tricks, our TIPS-based pipeline improves image-level performance by 1.1-3.9% and pixel-level by 1.5-6.9% across seven industrial datasets, delivering strong generalization with a lean architecture. Code is available at github.com/AlirezaSalehy/Tipsomaly.

View on arXivView PDF

Code Implementations(1)

AlirezaSalehy/TipsomalyCommunity67%
MIT

This is an extended version of the paper “TIPS Over Tricks: Simple Prompts for Effective Zero-shot Anomaly Detection,” accepted at ICASSP 2026 and scheduled to be publicly available in May. Author contributions may vary between versions.

120HTML, SCSSFeb 1, 20267 months agoMIT
anomaly-detectionsiglip2tipstransformersvision-language-model+1 more

Similar Papers

Do LLMs Understand Visual Anomalies? Uncovering LLM's Capabilities in Zero-shot Anomaly Detection

86% match2024

Analyzing VLM-Based Approaches for Anomaly Classification and Segmentation

85% match2026

AnomalyVFM -- Transforming Vision Foundation Models into Zero-Shot Anomaly Detectors

85% match2026

Crane: Context-Guided Prompt Learning and Attention Refinement for Zero-Shot Anomaly Detection

85% match1 repo362025

Towards Fine-Grained Vision-Language Alignment for Few-Shot Anomaly Detection

84% match1 repo12025

FiLo++: Zero-/Few-Shot Anomaly Detection by Fused Fine-Grained Descriptions and Deformable Localization

84% match1 repo892025

Cite this paper

@article{salehi2026tips,
  title  = {TIPS Over Tricks: Simple Prompts for Effective Zero-shot Anomaly Detection},
  author = {Alireza Salehi and Ehsan Karami and Sepehr Noey and Sahand Noey and Makoto Yamada and Reshad Hosseini and Mohammad Sabokrou},
  year   = {2026},
  eprint = {2602.03594},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2602.03594v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2602.03594.svg)](https://codeofpaper.com/paper/2602.03594)

Discussion