SOTAVerified

Long-tailed Object Detection

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.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 11–20 of 25 papers

TitleStatusHype
Semi-Supervised and Long-Tailed Object Detection with CascadeMatchCode0
Boosting Long-tailed Object Detection via Step-wise Learning on Smooth-tail Data—0
Instance-Aware Repeat Factor Sampling for Long-Tailed Object Detection—0
Long-tail Detection with Effective Class-MarginsCode1
Towards All-in-one Pre-training via Maximizing Multi-modal Mutual InformationCode1
Improving Long-tailed Object Detection with Image-Level Supervision by Multi-Task Collaborative LearningCode0
The Equalization Losses: Gradient-Driven Training for Long-tailed Object RecognitionCode2
Equalized Focal Loss for Dense Long-Tailed Object DetectionCode2
Adaptive Hierarchical Representation Learning for Long-Tailed Object Detection—0
Exploring Classification Equilibrium in Long-Tailed Object DetectionCode1
Show:102550
← PrevPage 2 of 3Next →

No leaderboard results yet.