AI Paper Atlas

Research map / Continual learning / Class-incremental

Teacher Agent: A Knowledge Distillation-Free Framework for Rehearsal-Based Video Incremental Learning

Shengqin Jiang, Yaoyu Fang, Haokui Zhang, Qingshan Liu, Yuankai Qi, Yang Yang, Peng Wang

IJCV 2026 · Continual learning › Class-incremental · approach: Class-balanced knowledge retention · 2 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 teacher agent (distillation-free) to baseline with sampler (ablation)video incremental baseline · UCF101accuracy: 69.88 -> 85.53Improved
add unified sampler to low-resolution baseline (ablation)low-res vCLIMB_TC · UCF101accuracy: 67.32 -> 69.88Improved
add unified sampler to low-resolution baseline (ablation)low-res vCLIMB_TC · Something-Something V1accuracy: 8.23 -> 14.48Improved
reduce input resolution to 112x112 without other changes (ablation)vCLIMB_TC · UCF101accuracy: 75.82 -> 67.32Hurt
use teacher-agent soft labels instead of one-hot ground truth (ablation)Ours · UCF101accuracy: 82.74 -> 85.53Improved
freeze calibration parameters (Ours vs Ours(para)) (ablation)Ours · UCF101accuracy: 85.40 -> 85.53Improved
use frozen parameters instead of random vectors for calibration input (ablation)Ours · UCF101accuracy: 84.87 -> 85.53Improved
eliminate gradient of misclassified exemplars in baseline (ablation)Baseline · UCF101accuracy: 67.32 -> 68.67Improved
add T-agent to image CIL model MEMO (ablation)MEMO · CIFAR-100 10 tasksaccuracy: 57.52 -> 58.18Improved
add T-agent to WA on Tiny ImageNet 10 tasks (ablation)WA · Tiny ImageNet 10 tasksaccuracy: 39.61 -> 40.62Improved
increase stored exemplars to four timesOurs · UCF101accuracy: 85.53 -> 95.56Improved
halve input resolution (reduction effect) for Ours vs benchmark (ablation)Ours · UCF101accuracy: 88.55 -> 85.53Hurt

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