AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Class-Difficulty Based Methods for Long-Tailed Visual Recognition

Saptarshi Sinha, Hiroki Ohashi, Katsuyuki Nakamura

IJCV 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Decoupled and calibrated long-tail training · 47 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 CDB class-difficulty weighting to focal lossFocal loss · ImageNet-LT (imbalance 256)classification error (%): 69.50 -> 66.30Improved
replace class-frequency sampling with CDB-SCFS · CIFAR100-LT (imbalance 100)classification error (%): 61.07 -> 58.03Improved
use sigmoidal instead of linear dynamic tau (ablation)CDB-W-CE · CIFAR100-LT (imbalance 100)classification error (%): 58.40 -> 57.41Improved
raise fixed tau from 1.5 to 5.0 (ablation)CDB-W-CE · CIFAR100-LT (imbalance 100)classification error (%): 57.30 -> 59.38Hurt
use sigmoidal dynamic tau instead of best fixed tau (ablation)CDB-W-CE · CIFAR100-LT (imbalance 100)classification error (%): 57.30 -> 57.41No clear effect
use class-level CDB-W-CE instead of instance-level focal lossFocal loss · CIFAR100-LT (imbalance 100) (imbalance 200 analysis)classification accuracy: 5.11% and 7.26% on medium-shot and few-shot; overall 1.74%Improved
use CDB-S rather than class-aware sampling in cRT stage 2 (CE stage 1) (ablation)cRT decoupled learning · CIFAR100-LT (imbalance 100)classification error (%): 57.06 -> 56.49Improved
use CDB-W-CE weighting rather than class-aware sampling in cRT stage 2 (CE stage 1) (ablation)cRT decoupled learning · CIFAR100-LT (imbalance 100)classification error (%): 57.06 -> 57.44Hurt
use CDB-W-CE instead of CE in stage 1 with CDB-S stage 2 (cRT) (ablation)cRT decoupled learning · CIFAR100-LT (imbalance 100)classification error (%): 56.49 -> 56.24Improved
train detector with CDB-W-CE instead of CEFaster R-CNN · LVIS v0.5 val (detection)mAP / APr: 21.19 -> 23.37 mAP; 3.05 -> 9.83 APrImproved
initialize BAGS-cls from CDB-W-CE pretrained modelBAGS-cls · LVIS v0.5 val (detection)mAP / APr: 25.96 -> 26.01 mAP; 17.65 -> 15.47 APrMixed
initialize LRW-cls from CDB-W-CE pretrained modelLRW-cls · LVIS v0.5 val (detection)mAP: 24.66 -> 25.52Improved

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