AI Paper Atlas

Research map / Continual learning / Online and replay-based

Mitigate Modality-Asymmetric Forgetting via Stabilizing Visual Representations in CLIP-Based Class-Incremental Learning

Yuanhong Zhang, Yanan Chen, Xin Zhang, Zhaoyang Wang, Weizhan Zhang, Muyao Yuan, Hongjin Niu, LAN MA, Yuan Gao, Joey Tianyi Zhou

ECCV 2026 · Continual learning › Online and replay-based · approach: Theoretical analysis of forgetting · 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 VRRM to LoRA baseline (ablation)CLIP + LoRA · CIFAR100 B10_Inc10Avg accuracy (%): 84.81 -> 86.90Improved
add VRRM to LoRA baseline (ablation)CLIP + LoRA · ImageNet-R B20_Inc20Avg accuracy (%): 84.01 -> 87.24Improved
add structural distillation loss L_distill (ablation)CLIP + LoRA · CIFAR100 B10_Inc10Last accuracy (%): 77.33 -> 78.93Improved
add L_distill on top of VRRM (ablation)VRRM · CIFAR100 B10_Inc10Last accuracy (%): 79.35 -> 80.40Improved
add VRRM on top of L_distill (ablation)L_distill · ImageNet-R B20_Inc20Last accuracy (%): 82.32 -> 82.83Improved
use second-order self-similarity attention instead of QK or KK attention (ablation)VRRM · CIFAR100Avg accuracy (%)Improved
text-aware layer weighting instead of last-layer or uniform average (ablation)VRRM · CIFAR100Avg accuracy (%)Improved
replace KL/MSE/CKC distillation with matrix-entropy structural distillation (ablation)L_distill · CIFAR100Avg accuracy (%)Improved
integrate VRRM into other distillation losses (ablation)KL/MSE/CKC distillation · CIFAR100Avg accuracy (%)Improved
vary distillation weight lambda and fusion coefficient beta away from 0.5 and 0.1 (ablation)VAST · CIFAR100 B10_Inc10Avg accuracy (%): 87.40 at peak, 86.76-87.33 elsewhere (grid in Fig. 7a)Mixed
choose self-similarity layer M (ablation)VRRM · CIFAR100 B10_Inc10Avg accuracy (%)No clear effect
apply VAST vs LoRA baseline for visual feature separabilityCLIP + LoRA · CIFAR100FDR after Task 1: 2.08 -> 2.97Improved

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