Papers with Code 아카이브
Long-tail Learning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 20
- 보존된 평가 기록
- 421
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.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Long-Tailed Recognition Using Class-Balanced Experts
From Generalized zero-shot learning to long-tail with class descriptors
M2m: Imbalanced Classification via Major-to-minor Translation
Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective
Equalization Loss for Long-Tailed Object Recognition
Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classification
BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition
Decoupling Representation and Classifier for Long-Tailed Recognition
Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss
Large-Scale Long-Tailed Recognition in an Open World
Multi-Label Image Recognition with Graph Convolutional Networks
Class-Balanced Loss Based on Effective Number of Samples
Focal Loss for Dense Object Detection
Relay Backpropagation for Effective Learning of Deep Convolutional Neural Networks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.