Long-tail Learning
84 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 |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Datasets
CIFAR-10
CIFAR-100
CelebA
Kinetics
iNaturalist
ImageNet-LT
EGTEA
Animal Kingdom
Most implemented papers
Long-tail learning via logit adjustment
google-research/google-research
•
•
ICLR 2021
Real-world classification problems typically exhibit an imbalanced or long-tailed label distribution, wherein many labels are associated with only a few samples.
Class-Balanced Distillation for Long-Tailed Visual Recognition
google-research/google-research
•
•
An effective and simple approach to long-tailed visual recognition is to learn feature representations and a classifier separately, with instance and class-balanced sampling, respectively.
Multi-Label Image Recognition with Graph Convolutional Networks
megvii-research/ml-gcn
•
•
CVPR 2019
The task of multi-label image recognition is to predict a set of object labels that present in an image.
Large-Scale Long-Tailed Recognition in an Open World
zhmiao/OpenLongTailRecognition-OLTR
•
•
CVPR 2019
We define Open Long-Tailed Recognition (OLTR) as learning from such naturally distributed data and optimizing the classification accuracy over a balanced test set which include head, tail, and open classes.
Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect
KaihuaTang/Long-Tailed-Recognition.pytorch
•
•
NeurIPS 2020
On one hand, it has a harmful causal effect that misleads the tail prediction biased towards the head.
Long-tailed Recognition by Routing Diverse Distribution-Aware Experts
frank-xwang/RIDE-LongTailRecognition
•
•
ICLR 2021
We take a dynamic view of the training data and provide a principled model bias and variance analysis as the training data fluctuates: Existing long-tail classifiers invariably increase the model variance and the head-tail model bias gap remains large, due to more and larger confusion with hard negatives for the tail.
Disentangling Label Distribution for Long-tailed Visual Recognition
hyperconnect/LADE
•
•
CVPR 2021
Although this method surpasses state-of-the-art methods on benchmark datasets, it can be further improved by directly disentangling the source label distribution from the model prediction in the training phase.
Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition
Existing long-tailed recognition methods, aiming to train class-balanced models from long-tailed data, generally assume the models would be evaluated on the uniform test class distribution.
Trustworthy Long-Tailed Classification
lblaoke/tlc
•
•
CVPR 2022
To address these issues, we propose a Trustworthy Long-tailed Classification (TLC) method to jointly conduct classification and uncertainty estimation to identify hard samples in a multi-expert framework.
A Simple Episodic Linear Probe Improves Visual Recognition in the Wild
akira-l/ELP
•
•
CVPR 2022
In this paper, we propose an episodic linear probing (ELP) classifier to reflect the generalization of visual representations in an online manner.
