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.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Pursuing Better Decision Boundaries for Long-Tailed Object Detection via Category Information Amount
SimLTD: Simple Supervised and Semi-Supervised Long-Tailed Object Detection
DINO-X: A Unified Vision Model for Open-World Object Detection and Understanding
Long-Tailed Object Detection Pre-training: Dynamic Rebalancing Contrastive Learning with Dual Reconstruction
Fractal Calibration for long-tailed object detection
Rectify the Regression Bias in Long-Tailed Object Detection
Consensus Focus for Object Detection and minority classes
Learning from Rich Semantics and Coarse Locations for Long-tailed Object Detection
Balanced Classification: A Unified Framework for Long-Tailed Object Detection
Semi-Supervised and Long-Tailed Object Detection with CascadeMatch
Boosting Long-tailed Object Detection via Step-wise Learning on Smooth-tail Data
Instance-Aware Repeat Factor Sampling for Long-Tailed Object Detection
Long-tail Detection with Effective Class-Margins
Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information
The Equalization Losses: Gradient-Driven Training for Long-tailed Object Recognition
Improving Long-tailed Object Detection with Image-Level Supervision by Multi-Task Collaborative Learning
Equalized Focal Loss for Dense Long-Tailed Object Detection
Exploring Classification Equilibrium in Long-Tailed Object Detection
On Model Calibration for Long-Tailed Object Detection and Instance Segmentation
MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection
Equalization Loss v2: A New Gradient Balance Approach for Long-tailed Object Detection
Towards Resolving the Challenge of Long-tail Distribution in UAV Images for Object Detection
Forest R-CNN: Large-Vocabulary Long-Tailed Object Detection and Instance Segmentation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.