2 citations · 3 across the 10 of their papers we have counts for
5 papers · 1 filter
Multi-Stage Knowledge Integration of Vision-Language Models for Continual Learning
Hongsheng Zhang, Zhong Ji, Jingren Liu +2
Vision Language Models (VLMs), pre-trained on large-scale image-text datasets, enable zero-shot predictions for unseen data but may underperform on specific unseen tasks. Continual…
A Fresh Look at Generalized Category Discovery through Non-negative Matrix Factorization
Zhong Ji, Shuo Yang, Jingren Liu +2
Generalized Category Discovery (GCD) aims to classify both base and novel images using labeled base data. However, current approaches inadequately address the intrinsic optimizatio…
Parameter-Efficient Fine-Tuning for Continual Learning: A Neural Tangent Kernel Perspective
Jingren Liu, Zhong Ji, YunLong Yu +4
Parameter-efficient fine-tuning for continual learning (PEFT-CL) has shown promise in adapting pre-trained models to sequential tasks while mitigating catastrophic forgetting probl…
Raformer: Redundancy-Aware Transformer for Video Wire Inpainting
Zhong Ji, Yimu Su, Yan Zhang +3
Video Wire Inpainting (VWI) is a prominent application in video inpainting, aimed at flawlessly removing wires in films or TV series, offering significant time and labor savings co…
NTK-Guided Few-Shot Class Incremental Learning
Jingren Liu, Zhong Ji, Yanwei Pang +1
The proliferation of Few-Shot Class Incremental Learning (FSCIL) methodologies has highlighted the critical challenge of maintaining robust anti-amnesia capabilities in FSCIL learn…