- [-] Rebalanced Siamese Contrastive Mining for Long-Tailed Recognition
- [-] You Only Need End-to-End Training for Long-Tailed Recognition ^
- [-] Margin Calibration for Long-Tailed Visual Recognition
- [-] Pure Noise to the Rescue of Insufficient Data: Improving Imbalanced Classification by Training on Random Noise Images ^
- [-] A Simple Long-Tailed Recognition Baseline via Vision-Language Model *
- [-] VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognition *
- [√] Deep Long-Tailed Learning: A Survey
- [-] Long-tail Recognition via Compositional Knowledge Transfer
- [-] Targeted Supervised Contrastive Learning for Long-Tailed Recognition
- [-] Nested Collaborative Learning for Long-Tailed Visual Recognition [code]
- [-] BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learning [code]
- [√] [*] Long-Tailed Recognition via Weight Balancing [code]
- [-] Balanced MSE for Imbalanced Visual Regression
- [√] Balanced Contrastive Learning for Long-Tailed Visual Recognition
- [√] Long-tail Recognition via Compositional Knowledge Transfer
- [-] The Majority Can Help the Minority: Context-rich Minority Oversampling for Long-tailed Classification
- [-] Long-tailed Visual Recognition via Gaussian Clouded Logit Adjustment
- [-] A Re-Balancing Strategy for Class-Imbalanced Classification Based on Instance Difficulty
- [-] Retrieval Augmented Classification for Long-Tail Visual Recognition
- [√] Cross-Domain Empirical Risk Minimization for Unbiased Long-tailed Classification (TA) [code]
- [-] Memory-based Jitter: Improving Visual Recognition on Long-tailed Data with Diversity In Memory
- [-] Class-Balanced Distillation for Long-Tailed Visual Recognition
- [-] Improving Contrastive Learning on Imbalanced Seed Data via Open-World Sampling
- [-] Topology-Imbalance Learning for Semi-Supervised Node Classification
- [√] [*] Towards Calibrated Model for Long-tailed Visual Recognition from Prior Perspective [code]
- [-] ABC: Auxiliary Balanced Classifier for Class-imbalanced Semi-supervised Learning
- [√] Influence-Balanced Loss for Imbalanced Visual Classification (IB loss)
- [√] [*] Parametric Contrastive Learning (PaCo) [code]
- [√] [*] Test-Agnostic Long-Tailed Recognition by Test-Time Aggregating Diverse Experts with Self-Supervision (TADE) * (TA) [code]
- [-] Distilling Virtual Examples for Long-tailed Recognition
- [-] VideoLT: Large-scale Long-tailed Video Recognition
- [-] Ace: Ally complementary experts for solving long-tailed recognition in one-shot.
- [√] MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition [code]
- [√] [*] Improving Calibration for Long-Tailed Recognition (MASLIS) [code]
- [√] Disentangling Label Distribution for Long-tailed Visual Recognition (LDAE) [code]
- [-] PML: Progressive Margin Loss for Long-tailed Age Classification
- [-] Distribution Alignment: A Unified Framework for Long-tail Visual Recognition [code]
- [√] Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification
- [-] Distributional Robustness Loss for Long-tail Learning [code]
- [√] Regularizing Deep Networks with Semantic-Data Augmentation
- [√] From Generalized zero-shot learning to long-tail with class descriptors
- [√] [*] Bag of Tricks for Long-Tailed Visual Recognition with Deep Convolutional Neural Networks [code]
- [√] ResLT: Residual Learning for Long-tailed Recognition
- [√] [*] Long-Tail Learning via Logit Adjustment [code]
- [-] Natural World Distribution via Adaptive Confusion Energy Regularization
- [-] EXPLORING BALANCED FEATURE SPACES FOR REPRESENTATION LEARNING
- [√] Balanced Meta-Softmax for Long-Tailed Visual Recognition [code]
- [√] Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect [code]
- [√] Rethinking the Value of Labels for Improving Class-Imbalanced Learning [code]
- [√] Identifying and Compensating for Feature Deviation in Imbalanced Deep Learning
- Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets
- [√] Feature Space Augmentation for Long-Tailed Data
- [-] Learning From Multiple Experts- Self-paced Knowledge Distillation for Long-tailed Classification
- [-] Solving Long-tailed Recognition with Deep Realistic Taxonomic Classifier
- [√] The Devil is in Classification- A Simple Framework for Long-tail Instance Segmentation
- [√] Remix: Rebalanced Mixup
- [√] Long-Tailed Recognition Using Class-Balanced Experts
- [√] BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition
- [-] Deep Representation Learning on Long-tailed Data - A Learnable Embedding Augmentation Perspective
- [-] Deep Generative Model for Robust Imbalance Classification
- [-] Domain Balancing- Face Recognition on Long-Tailed Domains
- [√] ELF- An Early-Exiting Framework for Long-Tailed Classification
- [√] Equalization Loss for Long-Tailed Object Recognition
- [√] Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax
- [√] Inflated Episodic Memory with Region Self-Attention for Long-Tailed Visual Recognition
- [-] Large-Scale Object Detection in the Wild from Imbalanced Multi-Labels
- [√] M2m: Imbalanced Classification via Major-to-minor Translation
- [√] Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective
- [-] Range Loss for Deep Face Recognition with Long-Tailed Training Data
- [-] Large Scale Long-tailed Product Recognition System at Alibaba
- [√] [*] DECOUPLING REPRESENTATION AND CLASSIFIER FOR LONG-TAILED RECOGNITION
- EXTREME CLASSIFICATION VIA ADVERSARIAL SOFTMAX APPROXIMATION
- [√] [*] Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss
- [√] [*] Class-Balanced Loss Based on Effective Number of Samples
- [√] Libra R-CNN: Towards Balanced Learning for Object Detection
- [√] Large-Scale Long-Tailed Recognition in an Open World
- [√] Striking the Right Balance with Uncertainty
- [√] AdaptiveFace: Adaptive Margin and Sampling for Face Recognition
- [√] Focal Loss for Dense Object Detection
- [√] The iNaturalist Species Classification and Detection Dataset
- [√] LVIS: A Dataset for Large Vocabulary Instance Segmentation
- [√] Gradient Harmonized Single-Stage Detector
- [√] Learning to Model the Tail
- [√] Improving Negative Sampling for Word Representation using Self-embedded Features
*:indicates high perferance.
^:indicates weird perferance.
TA: indicates Test-Agnostic.