4 papers
Collaborative Learning with Multiple Foundation Models for Source-Free Domain Adaptation
Huisoo Lee, Jisu Han, Hyunsouk Cho +1
Source-Free Domain Adaptation (SFDA) aims to adapt a pre-trained source model to an unlabeled target domain without access to source data. Recent advances in Foundation Models (FMs…
D-TPT: Dimensional Entropy Maximization for Calibrating Test-Time Prompt Tuning in Vision-Language Models
Jisu Han, Wonjun Hwang
Test-time adaptation paradigm provides flexibility towards domain shifts by performing immediate adaptation on unlabeled target data from the source model. Vision-Language Models (…
When Test-Time Adaptation Meets Self-Supervised Models
Jisu Han, Jihee Park, Dongyoon Han +1
Training on test-time data enables deep learning models to adapt to dynamic environmental changes, enhancing their practical applicability. Online adaptation from source to target…
SCHNet: SAM Marries CLIP for Human Parsing
Kunliang Liu, Jianming Wang, Rize Jin +2
Vision Foundation Model (VFM) such as the Segment Anything Model (SAM) and Contrastive Language-Image Pre-training Model (CLIP) has shown promising performance for segmentation and…