4 papers
Memory-Efficient Transfer Learning with Fading Side Networks via Masked Dual Path Distillation
Yutong Zhang, Jiaxin Chen, Honglin Chen +5
Memory-efficient transfer learning (METL) approaches have recently achieved promising performance in adapting pre-trained models to downstream tasks. They avoid applying gradient b…
Transforming Vision Transformer: Towards Efficient Multi-Task Asynchronous Learning
Hanwen Zhong, Jiaxin Chen, Yutong Zhang +2
Multi-Task Learning (MTL) for Vision Transformer aims at enhancing the model capability by tackling multiple tasks simultaneously. Most recent works have predominantly focused on d…
EVLM: An Efficient Vision-Language Model for Visual Understanding
Kaibing Chen, Dong Shen, Hanwen Zhong +14
In the field of multi-modal language models, the majority of methods are built on an architecture similar to LLaVA. These models use a single-layer ViT feature as a visual prompt,…
AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm Quantizer
Zhuguanyu Wu, Jiaxin Chen, Hanwen Zhong +2
Vision Transformer (ViT) has become one of the most prevailing fundamental backbone networks in the computer vision community. Despite the high accuracy, deploying it in real appli…