Shifan Zhang — accepted AI-conference papers

2025

Unleashing the Power of Task-Specific Directions in Parameter Efficient Fine-tuning

Chongjie Si, Zhiyi Shi, Shifan Zhang, Xiaokang Yang, Hanspeter Pfister, Wei Shen

ICLR 2025poster

Large language models demonstrate impressive performance on downstream tasks, yet requiring extensive resource consumption when fully fine-tuning all parameters. To mitigate this, Parameter Efficient Fine-Tuning (PEFT) strategies, such as LoRA, have been developed. In this paper, we delve into the…

Cited by 6 Source ↗PDF ↗Scholar ↗

2025

WISNet: Pseudo Label Generation on Unbalanced and Patch Annotated Waste Images

Shifan Zhang, Hongzi Zhu, Yinan He, Minyi Guo, Ziyang Lou, Shan Chang

CVPR 2025poster

Computer-vision-based assessment on waste sorting is desired to replace manpower supervision in Shanghai city. Due to the hardness of labeling a multitude of waste images, it is infeasible to train a semantic segmentation model for this purpose directly. In this work, we construct a new dataset cons…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗