Research map / Label-efficient and robust learning
Recognition and long-tail: research map
4,953 accepted papers on Recognition and long-tail in Label-efficient and robust learning, from ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026), grouped into 6 clusters and 27 approaches. The busiest year so far is 2026.
Within Label-efficient and robust learning, its share held steady from 43.7% in 2023–24 to 42.9% in 2025–26 (1,253 → 1,312 papers at ICML, NeurIPS, CVPR and AAAI, the venues with data for all four years).
Explore Recognition and long-tail 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
representations · transfer · unsupervised · 2,547 papers
Approaches in this cluster:
- Contrastive representation theory (495 papers)
Analyzes unsupervised and contrastive representation learning, disentanglement and invariance. - Correspondence and causal representation learning (447 papers)
Learns visual correspondence and transportable representations by matching multiple representations. - Dense features and foundation priors (482 papers)
Learns dense or tabular features using synthetic priors, hierarchical contrast and feature re-embedding. - Data augmentation and generalization bias (409 papers)
Studies augmentation, data properties and influence-based fixes for generalization and dataset bias. - Multilingual language representation pretraining (507 papers)
Pretrains cross-lingual language models and augmentation for transferable text representations. - Recommendation representation learning (207 papers)
Improves embeddings for recommender systems via multi-interest, inductive and collapse-aware modeling.
Most cited and most cited since 2024:
- Unsupervised Feature Learning via Non-Parametric Instance Discrimination (CVPR 2018 · 3,635 citations)
- Deep Metric Learning via Lifted Structured Feature Embedding (CVPR 2016 · 1,740 citations)
- Depth Anything V2 (NeurIPS 2024 · 525 citations)
- RoMa: Robust Dense Feature Matching (CVPR 2024 · 263 citations)
label · classification · classifier · 1,314 papers
Approaches in this cluster:
- Partial and multi-label learning (345 papers)
Learns from partially annotated labels using class-aware, margin-based and representation blending approaches. - Loss design and classifier theory (273 papers)
Proposes margin losses, hierarchy-aware objectives and generative versus discriminative classifier analysis. - Group-robust classification (251 papers)
Improves worst-group and subclass performance via distribution balancing, priors and invariant augmentation. - Learning from unlabeled and positive-unlabeled data (240 papers)
Trains classifiers from positive-unlabeled or multiple unlabeled datasets with consistent risk estimators. - Confidence calibration objectives (129 papers)
Calibrates network confidence with soft objectives, pairwise constraints and ensemble methods. - Deep active learning (76 papers)
Selects informative samples for labeling using ensembles, submodular measures and supervision-level optimization.
Most cited and most cited since 2024:
- ChestX-ray8: Hospital-Scale Chest X-Ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases (CVPR 2017 · 3,529 citations)
- Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics (CVPR 2018 · 3,007 citations)
- Adaptive Multi-Modal Cross-Entropy Loss for Stereo Matching (CVPR 2024 · 36 citations)
- Multi-Label Supervised Contrastive Learning (AAAI 2024 · 35 citations)
face · person identification · facial · 421 papers
Approaches in this cluster:
- Margin-based face recognition losses (124 papers)
Shapes face embeddings with angular margins, adaptive margins and quality-aware losses. - Supervised person re-identification (108 papers)
Learns discriminative person features with similarity learning, part features and bias removal. - Cross-modality and occlusion re-identification (82 papers)
Handles infrared, occluded and training-free matching for person re-identification. - Fair and quality-aware face recognition (66 papers)
Uses quality-adaptive margins, unified thresholds and fairness adapters in face recognition. - Uncertainty-aware facial expression recognition (41 papers)
Models label ambiguity and bias for facial expression recognition.
Most cited and most cited since 2024:
- ArcFace: Additive Angular Margin Loss for Deep Face Recognition (CVPR 2019 · 7,708 citations)
- SphereFace: Deep Hypersphere Embedding for Face Recognition (CVPR 2017 · 3,010 citations)
- Implicit Discriminative Knowledge Learning for Visible-Infrared Person Re-Identification (CVPR 2024 · 76 citations)
- Shallow-Deep Collaborative Learning for Unsupervised Visible-Infrared Person Re-Identification (CVPR 2024 · 69 citations)
explanations · concept · interpretable · 379 papers
Approaches in this cluster:
- Self-explaining and visual explanation networks (108 papers)
Builds networks that produce explanations through spatial attention, self-explaining design and explanation-based augmentation. - Prototype and concept dictionary models (104 papers)
Uses prototypical parts and sparse concept dictionaries for interpretable predictions. - Post-hoc explanation analysis (86 papers)
Evaluates and improves post-hoc explanations to expose spurious features and user needs. - Feature attribution methods (51 papers)
Formalizes and tests feature attribution through necessity, sufficiency and gradient-based tests. - Concept bottleneck models (30 papers)
Predicts through human-interpretable concept layers, including interactive, probabilistic and language-guided variants.
Most cited and most cited since 2024:
- Network Dissection: Quantifying Interpretability of Deep Visual Representations (CVPR 2017 · 1,404 citations)
- This Looks Like That: Deep Learning for Interpretable Image Recognition (NeurIPS 2019 · 560 citations)
- Deep Unfolded Network with Intrinsic Supervision for Pan-Sharpening (AAAI 2024 · 37 citations)
- SLICE: Stabilized LIME for Consistent Explanations for Image Classification (CVPR 2024 · 17 citations)
long tailed · classes · tailed recognition · 162 papers
Approaches in this cluster:
- Decoupled and calibrated long-tail training (82 papers)
Rebalances optimization and calibrates statistics between head and tail classes. - Classifier rebalancing and margin losses (58 papers)
Separates representation and classifier learning and applies balancing margins or weight rebalancing. - Contrastive learning for imbalanced data (22 papers)
Uses contrastive and anchor-based regularization for imbalanced and multi-label long-tailed data.
Most cited and most cited since 2024:
- Class-Balanced Loss Based on Effective Number of Samples (CVPR 2019 · 2,852 citations)
- Large-Scale Long-Tailed Recognition in an Open World (CVPR 2019 · 1,159 citations)
- Feature Fusion from Head to Tail for Long-Tailed Visual Recognition (AAAI 2024 · 52 citations)
- SFC: Shared Feature Calibration in Weakly Supervised Semantic Segmentation (AAAI 2024 · 51 citations)
multi view · views · view clustering · 130 papers
Approaches in this cluster:
- Uncertainty-aware multi-view learning (95 papers)
Fuses views using uncertainty estimates, consensus networks and openness-aware designs. - Incomplete multi-view multi-label learning (35 papers)
Imputes embeddings and shares label-guided representations for incomplete multi-view multi-label data.
Most cited and most cited since 2024:
- COMPLETER: Incomplete Multi-View Clustering via Contrastive Prediction (CVPR 2021 · 441 citations)
- Multi-Level Feature Learning for Contrastive Multi-View Clustering (CVPR 2022 · 388 citations)
- Incomplete Contrastive Multi-View Clustering with High-Confidence Guiding (AAAI 2024 · 109 citations)
- Decoupled Contrastive Multi-View Clustering with High-Order Random Walks (AAAI 2024 · 92 citations)