arXiv Machine Learning
Visual Branch is What You Need for CLIP-based Class-Incremental Learning
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
4d ago
Dual-Mode Low-Rank Learner with Bridge-Prototype Ensemble for Vision-Language Class-Incremental Learning
arXiv:2609.36759v1 Announce Type: cross Abstract: Benefiting from transferable visual-textual alignment, CLIP has been widely adopted for class-incremental learning (CIL). However, existing learners...
arXiv Machine Learning
Jun 25
BOFA: Bridge-Layer Orthogonal Low-Rank Fusion for CLIP-Based Class-Incremental Learning
arXiv:2511. 11421v2 Announce Type: replace-cross Abstract: Class-Incremental Learning (CIL) aims to continually learn new categories without forgetting previously acquired knowledge.
arXiv AI
Aug 13
A Simple Efficiency Incremental Learning Framework via Vision-Language Model with Nonlinear Multi-Adapters
arXiv:2603. 11211v3 Announce Type: replace-cross Abstract: Incremental Learning (IL) aims to learn new tasks while preserving previously acquired knowledge.
Hugging Face Trending Papers
Aug 11
When Vision Becomes Text: Visual Token Pruning via Cross-Modal Residual Guidance in VLMs
Abundant visual information strengthens vision-language model (VLM) perception, yet massive visual tokens raise inference costs. Existing visual token pruning methods rely on similarity-based guidance, which exploits pairwise text-vision and vision-vision token correlations for compression.
arXiv Computer Vision
4d ago
Reprogramming Vision-Language Models via Structured Prompt Reparameterization
arXiv:2609.36680v1 Announce Type: new Abstract: Visual reprogramming adapts pretrained models to downstream tasks by modifying their input and output interfaces while keeping the backbone fixed. In v...
arXiv Computer Vision
Sep 16
HyCal: A Training-Free Prototype Calibration Method for Cross-Discipline Few-Shot Class-Incremental Learning
arXiv:2604.15678v2 Announce Type: replace Abstract: Pretrained Vision-Language Models (VLMs) like CLIP show promise in continual learning, but existing Few-Shot Class-Incremental Learning (FSCIL) met...