6 papers
HAD: Heterogeneity-Aware Distillation for Lifelong Heterogeneous Learning
Xuerui Zhang, Xuehao Wang, Zhan Zhuang +5
Lifelong learning aims to preserve knowledge acquired from previous tasks while incorporating knowledge from a sequence of new tasks. However, most prior work explores only streams…
Enhanced Continual Learning of Vision-Language Models with Model Fusion
Haoyuan Gao, Zicong Zhang, Yuqi Wei +6
Vision-Language Models (VLMs) represent a significant breakthrough in artificial intelligence by integrating visual and textual modalities to achieve impressive zero-shot capabilit…
VISA: Group-wise Visual Token Selection and Aggregation via Graph Summarization for Efficient MLLMs Inference
Pengfei Jiang, Hanjun Li, Linglan Zhao +4
In this study, we introduce a novel method called group-wise \textbf{VI}sual token \textbf{S}election and \textbf{A}ggregation (VISA) to address the issue of inefficient inference…
Ambiguity-Guided Learnable Distribution Calibration for Semi-Supervised Few-Shot Class-Incremental Learning
Fan Lyu, Linglan Zhao, Chengyan Liu +5
Few-Shot Class-Incremental Learning (FSCIL) focuses on models learning new concepts from limited data while retaining knowledge of previous classes. Recently, many studies have sta…
CALA: A Class-Aware Logit Adapter for Few-Shot Class-Incremental Learning
Chengyan Liu, Linglan Zhao, Fan Lyu +3
Few-Shot Class-Incremental Learning (FSCIL) defines a practical but challenging task where models are required to continuously learn novel concepts with only a few training samples…
SAFE: Slow and Fast Parameter-Efficient Tuning for Continual Learning with Pre-Trained Models
Linglan Zhao, Xuerui Zhang, Ke Yan +2
Continual learning aims to incrementally acquire new concepts in data streams while resisting forgetting previous knowledge. With the rise of powerful pre-trained models (PTMs), th…