# Res2CLIP: Few-Shot Generalist Anomaly Detection with Residual-to-Residual Alignment

arXiv: https://arxiv.org/abs/2605.16171 · HTML: https://mlsanity.com/paper/2605.16171/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 38 references that are in the map.
- First posted on arXiv 15 May 2026.

## Builds on (most cited first, 28 of 28)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Towards Total Recall in Industrial Anomaly Detection](https://mlsanity.com/paper/2106.08265/) (2021)
- [PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization](https://mlsanity.com/paper/2011.08785/) (2020)
- [Anomaly Detection via Reverse Distillation from One-Class Embedding](https://mlsanity.com/paper/2201.10703/) (2022)
- [SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation](https://mlsanity.com/paper/2207.14315/) (2022)
- [From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification](https://mlsanity.com/paper/1602.02068/) (2016)
- [CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flows](https://mlsanity.com/paper/2107.12571/) (2021)
- [WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation](https://mlsanity.com/paper/2303.14814/) (2023)
- [AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection](https://mlsanity.com/paper/2310.18961/) (2023)
- [A Unified Model for Multi-class Anomaly Detection](https://mlsanity.com/paper/2206.03687/) (2022)
- [VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localization](https://mlsanity.com/paper/2104.10036/) (2021)
- [Registration based Few-Shot Anomaly Detection](https://mlsanity.com/paper/2207.07361/) (2022)
- [APRIL-GAN: A Zero-/Few-Shot Anomaly Classification and Segmentation Method for CVPR 2023 VAND Workshop Challenge Tracks 1&2: 1st Place on Zero-shot AD and 4th Place on Few-shot AD](https://mlsanity.com/paper/2305.17382/) (2023)
- [AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detection](https://mlsanity.com/paper/2407.15795/) (2024)
- [PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detection](https://mlsanity.com/paper/2404.05231/) (2024)
- [Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Prompts](https://mlsanity.com/paper/2403.06495/) (2024)
- [AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIP](https://mlsanity.com/paper/2503.06661/) (2025)
- [ReContrast: Domain-Specific Anomaly Detection via Contrastive Reconstruction](https://mlsanity.com/paper/2306.02602/) (2023)
- [VCP-CLIP: A visual context prompting model for zero-shot anomaly segmentation](https://mlsanity.com/paper/2407.12276/) (2024)
- [Bayesian Prompt Flow Learning for Zero-Shot Anomaly Detection](https://mlsanity.com/paper/2503.10080/) (2025)
- [AdaptCLIP: Adapting CLIP for Universal Visual Anomaly Detection](https://mlsanity.com/paper/2505.09926/) (2025)
- [MSFlow: Multi-Scale Flow-based Framework for Unsupervised Anomaly Detection](https://mlsanity.com/paper/2308.15300/) (2023)
- [ResAD: A Simple Framework for Class Generalizable Anomaly Detection](https://mlsanity.com/paper/2410.20047/) (2024)
- [MetaUAS: Universal Anomaly Segmentation with One-Prompt Meta-Learning](https://mlsanity.com/paper/2505.09265/) (2025)
- [DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup](https://mlsanity.com/paper/2508.13560/) (2025)
- [Unlocking the Potential of Reverse Distillation for Anomaly Detection](https://mlsanity.com/paper/2412.07579/) (2024)
- [MRAD: Zero-Shot Anomaly Detection with Memory-Driven Retrieval](https://mlsanity.com/paper/2602.00522/) (2026)
- [Foundation Visual Encoders Are Secretly Few-Shot Anomaly Detectors](https://mlsanity.com/paper/2510.01934/) (2025)

## Abstract (arXiv)

Few-shot Generalist Anomaly Detection requires models to generalize to novel categories without retraining, posing significant challenges in real-world scenarios with scarce samples and rapidly changing categories. Existing CLIP-based methods face two major challenges: coarse-grained unified text prompts struggle to adapt to fine-grained foreground-background differences, causing cross-granularity mismatch; and fine-tuning on auxiliary datasets disrupts CLIP's inherent open-world generalization due to domain shift, leading to cross-category generalization degradation. To address these, we propose to shift multimodal alignment entirely into a unified residual space, where residual representations naturally eliminate fine-grained normal feature differences across regions and class-specific biases, simultaneously resolving both problems. Based on this insight, Res2CLIP, the first residual-to-residual alignment framework that symmetrically bridges visual and text modalities within CLIP's residual space, is designed. The framework is developed from a residual perspective into three branches: a text prompt-based branch, a visual prompt-based branch, and a novel residual-to-residual alignment branch. All learnable optimizations are constrained within the residual domain, and the residual alignment optimization objectives are designed to force the model to focus on relative anomaly deviations rather than optimizing class-specific features. Experiments on multiple datasets demonstrate the effectiveness of our architecture. The code is available at https://github.com/hito2448/Res2CLIP.