AI Paper Atlas

Research map / Continual learning / Online and replay-based

Instance and Category Supervision are Alternate Learners for Continual Learning

Xudong Tian, Zhizhong Zhang, Xin Tan, Jun Liu, Chengjie Wang, Yanyun Qu, Guannan Jiang, Yuan Xie

ICCV 2023 · Continual learning › Online and replay-based · approach: Unified and unsupervised continual frameworks · 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 a supervised branch to the self-supervised learner without alternation (ablation)SSL continual learner · TinyImageNet 20-split (task-incremental)avg. forgetting: 3.54 -> 5.29Hurt
add alternate learner inner loop to SSL+SL (ablation)SSL+SL · CIFAR-100 10-split (task-incremental)avg. accuracy: 69.1 -> 75.8Improved
apply outer-loop momentum update only to SSL (ablation)SSL · CIFAR-100 10-split (task-incremental)avg. accuracy: 68.4 -> 68.9No clear effect
combine SSL and SL with DualNet-style rigid combination (ablation)SSL+SL · TinyImageNet 20-split (task-incremental)avg. accuracy: 77.52 -> 78.41No clear effect
use full alternate learner (inner + outer loop) instead of ALin (ablation)SSL+SL+AL · CIFAR-100 10-split (task-incremental)avg. accuracy: 75.8 -> 77.5Improved
add the proposed disentangled SSL losses (Eq. 4 and Eq. 5) (ablation)alternate learner · CIFAR-100 10-split (task-incremental)avg. accuracy: 77.5 -> 80.0Improved
add the proposed SSL losses to SL on TinyImageNet (ablation)alternate learner · TinyImageNet 20-split (task-incremental)avg. accuracy: 81.43 -> 82.81Improved
use too few SSL iterations (e_SSL = 5) (ablation)alternate learner · CIFAR-100 10-splitavg. accuracy: below the 68.4 baselineHurt
use too many SSL iterations (ablation)alternate learner · CIFAR-100 10-splitavg. accuracyHurt
use larger embedding dimension without the proposed SSL losses (ablation)baseline SSL · CIFAR-100 10-splitavg. accuracyImproved
use proposed SSL losses with compact 128-d embedding rather than 2048-d (ablation)alternate learner · CIFAR-100 10-splitavg. 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