Long-tail Learning
92 papers with code • 20 benchmarks • 16 datasets
Long-tailed learning, one of the most challenging problems in visual recognition, aims to train well-performing models from a large number of images that follow a long-tailed class distribution.
Benchmarks
These leaderboards are used to track progress in Long-tail Learning
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Long-tail Learning models and implementationsDatasets
CIFAR-10
CIFAR-100
CelebA
Kinetics
iNaturalist
ImageNet-LT
EGTEA
Animal Kingdom
Most implemented papers
Focal Loss for Dense Object Detection
facebookresearch/detectron
•
•
ICCV 2017
Our novel Focal Loss focuses training on a sparse set of hard examples and prevents the vast number of easy negatives from overwhelming the detector during training.
Learning Transferable Visual Models From Natural Language Supervision
openai/CLIP
•
•
State-of-the-art computer vision systems are trained to predict a fixed set of predetermined object categories.
Class-Balanced Loss Based on Effective Number of Samples
richardaecn/class-balanced-loss
•
•
CVPR 2019
We design a re-weighting scheme that uses the effective number of samples for each class to re-balance the loss, thereby yielding a class-balanced loss.
Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss
kaidic/LDAM-DRW
•
•
NeurIPS 2019
Deep learning algorithms can fare poorly when the training dataset suffers from heavy class-imbalance but the testing criterion requires good generalization on less frequent classes.
Visual Prompt Tuning
KMnP/vpt
•
•
The current modus operandi in adapting pre-trained models involves updating all the backbone parameters, ie, full fine-tuning.
ResLT: Residual Learning for Long-tailed Recognition
jiequancui/ResLT
•
•
From this perspective, the trivial solution utilizes different branches for the head, medium, and tail classes respectively, and then sums their outputs as the final results is not feasible.
Improving Calibration for Long-Tailed Recognition
Jia-Research-Lab/MiSLAS
•
•
CVPR 2021
Motivated by the fact that predicted probability distributions of classes are highly related to the numbers of class instances, we propose label-aware smoothing to deal with different degrees of over-confidence for classes and improve classifier learning.
Parametric Contrastive Learning
dvlab-research/parametric-contrastive-learning
•
•
ICCV 2021
In this paper, we propose Parametric Contrastive Learning (PaCo) to tackle long-tailed recognition.
Decoupling Representation and Classifier for Long-Tailed Recognition
facebookresearch/classifier-balancing
•
•
ICLR 2020
The long-tail distribution of the visual world poses great challenges for deep learning based classification models on how to handle the class imbalance problem.
Generalized Parametric Contrastive Learning
dvlab-research/parametric-contrastive-learning
•
•
Based on theoretical analysis, we observe that supervised contrastive loss tends to bias high-frequency classes and thus increases the difficulty of imbalanced learning.
