AI Paper Atlas

Research map / Continual learning / Online and replay-based

DiL: Discrete-anchored Representation Alignment for Semi-Supervised Continual Learning

Nanyi Wang, Chaojie Chen, Zuoqi Tang, Jinxiang Lai, Xingcai Wu, Qi Wang

ICML 2026 · Continual learning › Online and replay-based · approach: Unified and unsupervised continual frameworks

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
replace direct full-prototype distillation (DPD) with channel-selective DCD (ablation)iCaRL&Fix · CIFAR10-30 (5 tasks)Last accuracy: 64.78 -> 68.2Improved
add confusion-matrix-guided block assignment (Mconf) in CACE (ablation)iCaRL&Fix+DCD+CACE · CIFAR10-30 (5 tasks)Last accuracy: 69.26 -> 71.55Improved
add CACE to DCD (ablation)iCaRL&Fix · CIFAR10-30 (5 tasks)Last accuracy: 68.2 -> 69.26Improved
add DCD distillation on top of CACE+Mconf (ablation)iCaRL&Fix · CIFAR10-30 (5 tasks)Last accuracy: 64.96 -> 71.55Improved
use DCD instead of feature KD or logit KD (ablation)DiL · CIFAR10-30 (5 tasks)accuracy on unlabeled dataImproved
replace CACE with random or clustering-based anchor initialization, or remove CACE (ablation)DiL · CIFAR100-20 (10 tasks)base-class accuracy and center driftHurt
use DiL instead of USP with small replay buffer 250 (ablation)iCaRL&Fix · CIFAR10-30 (5 tasks)Last accuracy: 59.93 -> 65.06Improved
use DiL instead of USP with 20K buffer on iCaRL&Fix, CIFAR100-125iCaRL&Fix · CIFAR100-125, buffer 20KLast accuracy: 55.17 -> 54.04Hurt
use DiL instead of USP with 20K buffer on ImageNet100-100 (iCaRL&Fix)iCaRL&Fix · ImageNet100-100, buffer 20KLast accuracy: 51.73 -> 68.06Improved
use DiL instead of USP with DER&Fix on CIFAR10-30DER&Fix · CIFAR10-30 (5 tasks)Last accuracy: 73.65 -> 73.32No clear effect
use DiL instead of USP on 11-task CUB-200UaD-CIE · CUB-200 11-task few-shotAvg base-novel accuracy gap: above 10% -> 3.18%Improved

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