Research map / Label-efficient and robust learning / OOD and anomaly detection
Intra-Image Mining and Symmetric Maximum Concept Matching for Few Shot Out-of-Distribution Detection
Kaixiang Chen, Pengfei Fang, Hui Xue
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add hard negative mining (ablation) | IIM · ImageNet-500-Hard, 4-shot | FPR95: 31.37 -> 30.17 | Improved |
| add negative prompts without Lneg (ablation) | IIM · ImageNet-500-Hard, 4-shot | FPR95: 30.17 -> 30.02 | No clear effect |
| add Lneg on ID-like OOD patches with negative prompts (ablation) | IIM · ImageNet-500-Hard, 4-shot | FPR95: 30.17 -> 28.33 | Improved |
| add diversity regularization Ldiv (ablation) | IIM · ImageNet-500-Hard, 4-shot | FPR95: 28.33 -> 27.81 | Improved |
| replace image-to-text evaluators with S-MCM (adds text-to-image score) (ablation) | IIM · ImageNet-1k, 16-shot | FPR95: 32.9 (GL-MCM) -> 21.4 (S-MCM) | Improved |
| use negative prompts at test time in S-MCM (ablation) | IIM · ImageNet-100 | FPR95 | Hurt |
| replace Local-Prompt with IIM | few-shot OOD detectors · ImageNet-500-Hard, 4-shot | FPR95: 37.85 -> 27.81 | Improved |
| replace Local-Prompt with IIM | few-shot OOD detectors · ImageNet-1k, 4-shot, iNaturalist | FPR95: 9.65 -> 9.98 | Hurt |
| replace Local-Prompt with IIM | few-shot OOD detectors · ImageNet-1k, training time | training time: 275 min -> 26 min | Improved |
| set top-k to extremes (too small or too large) (ablation) | IIM · ImageNet-500-Hard, 4-shot | FPR95 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- Local-Prompt — Local-Prompt: Extensible Local Prompts for Few-Shot Out-of-Distribution Detection (ICLR 2025) · better on 8 of 9 shared results
- LoCoOp — LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learning (NeurIPS 2023) · better on 4 of 5 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Delving into Out-of-Distribution Detection with Vision-Language Representations (NeurIPS 2022 · similarity 0.92)
- GL-MCM: Global and Local Maximum Concept Matching for Zero-Shot Out-of-Distribution Detection (IJCV 2025 · similarity 0.90)
- Conjugated Semantic Pool Improves OOD Detection with Pre-trained Vision-Language Models (NeurIPS 2024 · similarity 0.90)
- Image Background Serves as Good Proxy for Out-of-distribution Data (ICLR 2024 · similarity 0.87)
- A Systematic Analysis of Out-of-Distribution Detection Under Representation and Training Paradigm Shifts (NeurIPS 2026 · similarity 0.87)
- Rethinking the Evaluation of Out-of-Distribution Detection: A Sorites Paradox (NeurIPS 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
