AI Paper Atlas

Research map / Continual learning / Class-incremental

Spectral-Aware Analytic Class-Incremental Learning for Long-Tailed Distributions

Quyen Tran, Ngoc-Hai Nguyen, Minh Quan Dao, Zhuowei Li, Nam Hai, Trung Le, Dimitris N. Metaxas

ECCV 2026 · Continual learning › Class-incremental · approach: Exemplar-efficient class-incremental learning · 3 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 GSR to GACLGACL (DINO-v2) · Split CIFAR-100 (long-tailed)Last accuracy: 48.78 -> 65.81Improved
add GSR to AnaCPAnaCP (DINO-v2) · Split CIFAR-100 (long-tailed)Last accuracy: 72.90 -> 82.51Improved
add GSR to AnaCPAnaCP (MoCo-v3) · Split CIFAR-100 (long-tailed)Last accuracy: 57.38 -> 66.01Improved
add GSR to AnaCPAnaCP (MoCo-v3) · Split ImageNet-R (long-tailed)Last accuracy: 36.84 -> 37.21No clear effect
use linear mixup instead of Standard Ridge (ablation)GACL · Split CUB-200 (DINO-v2)Last accuracy: 80.73 -> 77.85Hurt
replace linear mixup with spherical mixup (ablation)GACL + mixup · Split CUB-200 (DINO-v2)Last accuracy: 77.85 -> 82.01Improved
add adaptive mixing alpha_c (ablation)GACL + spherical mixup · Split CUB-200 (DINO-v2)Last accuracy: 82.01 -> 82.46Improved
add spherical mixup (GSR) on MoCo-v3 (ablation)GACL · Split CUB-200 (MoCo-v3)Last accuracy: 34.48 -> 48.33Improved
add GSR at imbalance ratio 10GACL · Split CIFAR-100 rho=10Last accuracy: 81.23 -> 85.22 (+3.99)Improved
add GSR at imbalance ratio 150GACL · Split CIFAR-100 rho=150Last accuracy: 38.60 -> 55.50 (+16.9)Improved
add GSR to GACL, tail classesGACL · Split CIFAR-100 tail classesTail accuracy: 12.50 -> 38.00Improved
add GSR to GACL, head classesGACL · Split CIFAR-100 head classesHead accuracy: 95.38 -> 95.25No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 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