All Projects → xialeiliu → Awesome-LongTailed-Recognition

xialeiliu / Awesome-LongTailed-Recognition

Licence: MIT license
No description, website, or topics provided.

Awesome Long-Tailed Recognition/ Imbalanced Learning

Feel free to contact me if you find any interesting paper is missing.

Existing Awesome Imbalanced Learning

Papers

2020

  • Rethinking the Value of Labels for Improving Class-Imbalanced Learning (NeurIPS2020) [paper] [code]
  • Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classification (ECCV2020) [paper]
  • Solving Long-tailed Recognition with Deep Realistic Taxonomic Classifier (ECCV2020) [paper]
  • Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets (ECCV2020) [paper]
  • The Devil is in Classification: A Simple Framework for Long-tail Instance Segmentation (ECCV2020) [paper]
  • Feature Space Augmentation for Long-Tailed Data (ECCV2020) [paper]
  • Deep Representation Learning on Long-Tailed Data: A Learnable Embedding Augmentation Perspective (CVPR2020) [paper]
  • Inflated Episodic Memory With Region Self-Attention for Long-Tailed Visual Recognition (CVPR2020) [paper]
  • Deep Representation Domain Balancing: Face Recognition on Long-Tailed Domains (CVPR2020) [paper]
  • Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition From a Domain Adaptation Perspective (CVPR2020) [paper]
  • BBN: Bilateral-Branch Network With Cumulative Learning for Long-Tailed Visual Recognition (CVPR2020) [paper]
  • Overcoming Classifier Imbalance for Long-Tail Object Detection With Balanced Group Softmax (CVPR2020) [paper]
  • Equalization Loss for Long-Tailed Object Recognition (CVPR2020) [paper]
  • M2m: Imbalanced Classification via Major-to-Minor Translation (CVPR2020) [paper]
  • Deep Generative Model for Robust Imbalance Classification (CVPR2020) [paper]
  • Large-Scale Object Detection in the Wild from Imbalanced Multi-Labels (CVPR2020) [paper]
  • Decoupling Representation and Classifier for Long-Tailed Recognition (ICLR2020) [paper]
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].