AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

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

Jingru Tan, Bo Li, Xin Lu, Yongqiang Yao, Fengwei Yu, Tong He, Wanli Ouyang

TPAMI 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Open-set and unknown object detection · 37 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add objectness branch (ablation)Sigmoid-EQL on Mask R-CNN · LVIS v1 val (1x)AP: 16.1 -> 18.1Improved
add negative gradient reweighting (ablation)Sigmoid-EQL (with obj) · LVIS v1 val (1x)AP: 18.1 -> 19.7Improved
add positive gradient reweighting (ablation)Sigmoid-EQL (with obj) · LVIS v1 val (1x)AP: 18.1 -> 23.3Improved
add negative reweighting on top of obj+pos (ablation)Sigmoid-EQL · LVIS v1 val (1x)AP: 23.3 -> 23.7Improved
use sigmoid-like mapping instead of exp mapping (ablation)Sigmoid-EQL · LVIS v1 val (neg+pos)AP: 23.2 -> 23.7Improved
use sigmoid-like mapping instead of sqrt mapping (ablation)Sigmoid-EQL · LVIS v1 val (neg+pos)AP_r: 6.2 -> 14.9Improved
add Sigmoid-EQL to CE baseline, 3x scheduleMask R-CNN R50 · LVIS v1 val (3x)AP: 20.5 -> 26.2Improved
add focusing factor (ablation)EFL baseline · LVIS v1 valAP: 25.7 -> 26.2Improved
add weighting factor (ablation)EFL baseline · LVIS v1 valAP: 25.7 -> 26.1Improved
add both factors (EFL) to improved baselineATSS baseline · LVIS v1 val R50AP: 25.7 -> 27.5Improved
raise scale s from 8 to 12 (ablation)EFL · LVIS v1 valAP: 27.5 -> 26.5Hurt
train EFL with ResNet-101 instead of ResNet-50EFL · LVIS v1 valAP_r: 20.2 -> 23.5Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy