Research map / Label-efficient and robust learning
OOD and anomaly detection: research map
614 accepted papers on OOD and anomaly detection in Label-efficient and robust learning, from ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026), grouped into 2 clusters and 8 approaches. The busiest year so far is 2026.
Within Label-efficient and robust learning, its share grew from 7.4% in 2023–24 to 8.5% in 2025–26 (212 → 259 papers at ICML, NeurIPS, CVPR and AAAI, the venues with data for all four years).
Explore OOD and anomaly detection in the interactive map
Working on something in this topic? Describe your idea in scime atlas to see which approach it falls under, the closest papers by meaning and how crowded the spot has become.
Approaches and key papers
ood detection · distribution ood · distribution detection · 414 papers
Approaches in this cluster:
- Provable and feature-based OOD detection (122 papers)
Designs OOD scores and outlier training with theoretical guarantees using typical features and prototypes. - Spurious-aware OOD detection (109 papers)
Addresses spurious correlations and scaling in OOD detection with gradients and prototypes. - Out-of-distribution generalization theory (71 papers)
Analyzes and improves OOD generalization via invariance, sharpness and causal learning. - Uncertainty and misclassification detection (56 papers)
Detects errors and OOD inputs using baseline scores, generative models and outlier mixing. - Robust fine-tuning for OOD generalization (56 papers)
Fine-tunes vision-language models while preserving pretrained robustness using energy and calibration objectives.
Most cited and most cited since 2024:
- A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks (ICLR 2017 · 1,577 citations)
- Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks (ICLR 2018 · 634 citations)
- Transcending Forgery Specificity with Latent Space Augmentation for Generalizable Deepfake Detection (CVPR 2024 · 152 citations)
- Debiasing Multimodal Sarcasm Detection with Contrastive Learning (AAAI 2024 · 35 citations)
anomaly detection · normal · anomalies · 200 papers
Approaches in this cluster:
- Unified multi-class anomaly detection (86 papers)
Trains one anomaly detector across classes using reconstruction, cross-modal constraints and class-generalizable features. - Anomaly detection with contaminated data (64 papers)
Handles noisy training data and distribution shifts using clustering, ensembles and outlier exposure. - Deep one-class and tabular anomaly detection (50 papers)
Applies one-class objectives, self-supervision and reinforcement learning to tabular and general data.
Most cited and most cited since 2024:
- CutPaste: Self-Supervised Learning for Anomaly Detection and Localization (CVPR 2021 · 1,006 citations)
- Deep One-Class Classification (ICML 2018 · 847 citations)
- RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detection (CVPR 2024 · 198 citations)
- PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detection (CVPR 2024 · 135 citations)
Related topics in Label-efficient and robust learning
- Noisy labels (462)
- Zero-/few-shot and meta-learning (784)
- Test-time adaptation (359)
- Recognition and long-tail (4,953)
- Semi-supervised learning (623)
- Self-supervised and contrastive (988)
- Domain adaptation and generalization (1,330)
- Knowledge distillation (544)