AI Paper Atlas

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

VICAL: Vicinal Consistency Alignment for Long-Tailed Visual Recognition

Jianggang Zhu, Zheng Wang, Bin Zhu, Yi-Ping Phoebe Chen, Jingjing Chen

ECCV 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Decoupled and calibrated long-tail training · 0 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 self-consistency learning (SC) to multi-expert model (ablation)multi-expert baseline · CIFAR-100-LT (IF=100)top-1 accuracy: 55.6 -> 57.8Improved
add deep ensemble distillation (DED) (ablation)ME + SC · CIFAR-100-LT (IF=100)top-1 accuracy: 57.8 -> 58.6Improved
add conflicting knowledge filter (CKF) (ablation)ME + SC + DED · CIFAR-100-LT (IF=100)top-1 accuracy: 58.6 -> 59.1Improved
use low-resolution view for DED instead of full-resolution (ablation)DED · CIFAR-100-LT (IF=100)top-1 accuracy: 58.1 -> 59.1Improved
add low-pass filter to full-resolution input for DED (ablation)DED · CIFAR-100-LT (IF=100)top-1 accuracy: 58.1 -> 58.6Improved
add high-pass filter to full-resolution input for DED (ablation)DED · CIFAR-100-LT (IF=100)top-1 accuracy: 58.1 -> 58.1No clear effect
distill only on samples where teacher is wrong and student correct (ablation)DED without CKF · CIFAR-100-LT (IF=100)top-1 accuracy: 57.7 -> 53.2Hurt
use CKF instead of distilling on all samples (ablation)DED · CIFAR-100-LT (IF=100)top-1 accuracy: 58.6 -> 59.1Improved
use SC instead of vanilla self-distillation for a single expert (ablation)single expert · CIFAR-100-LT (200 epochs)top-1 accuracy: 51.7 -> 53.6Improved
train longer (400 vs 155 epochs) (ablation)VICAL · CIFAR-100-LT (IF=100)top-1 accuracy: 57.6 -> 59.7Improved
increase diversity regularizer weight lambda from 0 to 2 (ablation)MDCS-style multi-expert · CIFAR-100-LT (IF=100)top-1 accuracy: 49.9 -> 49.9No clear effect
use target network for inference instead of online network (ablation)VICAL · CIFAR-100-LT (IF=100)top-1 accuracyImproved

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