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.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/solapark/da_yolo
https://github.com/solapark/darknet_interpark
https://github.com/solapark/darknet_partdet
https://github.com/solapark/darknet_partdet_tmp
https://github.com/srihari-humbarwadi/retinanet-tensorflow2.x
https://github.com/srihari-humbarwadi/tensorflow_retinanet
https://github.com/statsu1990/yoto_class_balanced_loss
https://github.com/stevenzhou2017/darknet_AlexeyAB
https://github.com/sudharavali/objectDetectionYOLO
https://github.com/sulasen/race-events-recognition-1
https://github.com/taited/clip-score
Learning Transferable Visual Models From Natural Language Supervision
https://github.com/tallysprado/myDarknet
https://github.com/teemoeric/projet
https://github.com/tensorflow/models
https://github.com/tiagoCuervo/JapaNet
https://github.com/tianhai123/yolov3
https://github.com/toufiksk/darknet
https://github.com/towhee-io/towhee
Learning Transferable Visual Models From Natural Language Supervision
https://github.com/travismyers19/Vulnerable_Buildings
https://github.com/trongnghia00/darknet
https://github.com/tryolabs/luminoth
https://github.com/unites-lab/vpns
https://github.com/unsky/RetinaNet
https://github.com/unsky/focal-loss
https://github.com/vandit15/Class-balanced-loss-pytorch
https://github.com/vantupham/darknet
https://github.com/viethungluu/OCRetina
https://github.com/vuongtrannguyenkhoi/darknet
https://github.com/wang22ti/DDC
https://github.com/wangxianhao/Improved-YOLOv3-for-UAV
https://github.com/wgcban/apt
https://github.com/williamccondori/YOLO-NFPA
https://github.com/witwickey/darknet
https://github.com/wodyjowski/colab-training
https://github.com/xiamenwcy/extended-caffe
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.