AI Paper Atlas

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

ACE: Ally Complementary Experts for Solving Long-Tailed Recognition in One-Shot

Jiarui Cai, Yizhou Wang, Jenq-Neng Hwang

ICCV 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Decoupled and calibrated long-tail training · 152 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 the complementary loss L_com (ablation)ACE (3 experts), CIFAR100-LT IF=100 · CIFAR100-LT IF=100top-1 accuracy: 47.2 -> 49.4Improved
add the complementary loss L_com (many-shot) (ablation)ACE (3 experts), CIFAR100-LT IF=100 · CIFAR100-LT IF=100many-shot accuracy: 71.5 -> 66.1Hurt
add the complementary loss L_com (few-shot) (ablation)ACE (3 experts), CIFAR100-LT IF=100 · CIFAR100-LT IF=100few-shot accuracy: 17.5 -> 23.5Improved
use soft complementary loss instead of split-specific classifiers (SSC) (ablation)ACE (3 experts), CIFAR100-LT IF=100 · CIFAR100-LT IF=100top-1 accuracy: 43.4 -> 49.4Improved
use linear learning-rate scaling instead of uniform learning rate across experts (ablation)ACE (3 experts), CIFAR100-LT IF=100 · CIFAR100-LT IF=100top-1 accuracy: 41.7 -> 49.4Improved
use linear scaling instead of square-root scaling (ablation)ACE (3 experts), CIFAR100-LT IF=100 · CIFAR100-LT IF=100top-1 accuracy: 49.1 -> 49.4No clear effect
use group average with scaling instead of group max (ablation)ACE (3 experts), CIFAR100-LT IF=100 · CIFAR100-LT IF=100top-1 accuracy: 43.4 -> 49.4Improved
use group average with scaling instead of group concat (ablation)ACE (3 experts), CIFAR100-LT IF=100 · CIFAR100-LT IF=100top-1 accuracy: 37.7 -> 49.4Improved
add logit scaling to group average aggregation (ablation)ACE (3 experts), CIFAR100-LT IF=100 · CIFAR100-LT IF=100top-1 accuracy: 46.7 -> 49.4Improved
add logit scaling to group average aggregation (few-shot) (ablation)ACE (3 experts), CIFAR100-LT IF=100 · CIFAR100-LT IF=100few-shot accuracy: 36.5 -> 23.5Hurt
use Mixup alpha 0.3 instead of no Mixup (alpha 0) (ablation)ACE (3 experts), CIFAR100-LT IF=100 · CIFAR100-LT IF=100top-1 accuracy: 48.6 -> 49.4No clear effect
increase from 3 to 4 expertsACE · CIFAR100-LT IF=100top-1 accuracy: 49.4 -> 49.6No clear effect

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