Papers with Code 아카이브

Long-tailed Object Detection

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

하위 태스크: 0
평가표: 1
보존된 평가 기록: 1

The training dataset obeys a long-tailed distribution, i.e., the head categories occupy most samples whereas the tail categories only own a few samples. However, the testing dataset is balanced across categories.

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/JialianW/Forest_RCNN

공식 코드

Forest R-CNN: Large-Vocabulary Long-Tailed Object Detection and Instance Segmentation

https://github.com/MengLcool/RichSem

공식 코드

Learning from Rich Semantics and Coarse Locations for Long-tailed Object Detection

https://github.com/OpenGVLab/M3I-Pretraining

공식 코드

Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information

https://github.com/czhang0528/MosaicOS

공식 코드

MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection

https://github.com/erikvalle/consensus-focus-for-object-detection

공식 코드

Consensus Focus for Object Detection and minority classes

https://github.com/fcjian/loce

공식 코드

Exploring Classification Equilibrium in Long-Tailed Object Detection

https://github.com/idea-research/dino-x-api

공식 코드

DINO-X: A Unified Vision Model for Open-World Object Detection and Understanding

https://github.com/janghyuncho/ecm-loss

공식 코드

Long-tail Detection with Effective Class-Margins

https://github.com/kostas1515/FRACAL

공식 코드

Fractal Calibration for long-tailed object detection

https://github.com/lexisnexis-risk-open-source/simltd

공식 코드

SimLTD: Simple Supervised and Semi-Supervised Long-Tailed Object Detection

https://github.com/modeltc/eod

공식 코드

Equalized Focal Loss for Dense Long-Tailed Object Detection

https://github.com/modeltc/united-perception

공식 코드

The Equalization Losses: Gradient-Driven Training for Long-tailed Object Recognition

https://github.com/tianhao-qi/bacl

공식 코드

Balanced Classification: A Unified Framework for Long-Tailed Object Detection

https://github.com/tydpan/NorCal

공식 코드

On Model Calibration for Long-Tailed Object Detection and Instance Segmentation

https://github.com/tztztztztz/eqlv2

공식 코드

Equalization Loss v2: A New Gradient Balance Approach for Long-tailed Object Detection

https://github.com/waveboo/clis

공식 코드

Improving Long-tailed Object Detection with Image-Level Supervision by Multi-Task Collaborative Learning

https://github.com/we1pingyu/DSHNet

공식 코드

Towards Resolving the Challenge of Long-tail Distribution in UAV Images for Object Detection

https://github.com/yuhangzang/cascadematch

공식 코드

Semi-Supervised and Long-Tailed Object Detection with CascadeMatch

https://github.com/FenHua/Robust_Logo_Detection

Equalization Loss v2: A New Gradient Balance Approach for Long-tailed Object Detection

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.