collaborators

5 papers

cs.CV2026

MixerCSeg: An Efficient Mixer Architecture for Crack Segmentation via Decoupled Mamba Attention

Zilong Zhao, Zhengming Ding, Pei Niu +2

Feature encoders play a key role in pixel-level crack segmentation by shaping the representation of fine textures and thin structures. Existing CNN-, Transformer-, and Mamba-based…

cs.CV2026

Seeing Clearly, Reasoning Confidently: Plug-and-Play Remedies for Vision Language Model Blindness

Xin Hu, Haomiao Ni, Yunbei Zhang +3

Vision language models (VLMs) have achieved remarkable success in broad visual understanding, yet they remain challenged by object-centric reasoning on rare objects due to the scar…

cs.CV2025

Doctor Approved: Generating Medically Accurate Skin Disease Images through AI-Expert Feedback

Janet Wang, Yunbei Zhang, Zhengming Ding +1

Paucity of medical data severely limits the generalizability of diagnostic ML models, as the full spectrum of disease variability can not be represented by a small clinical dataset…

cs.AI2025

eSkinHealth: A Multimodal Dataset for Neglected Tropical Skin Diseases

Janet Wang, Xin Hu, Yunbei Zhang +7

Skin Neglected Tropical Diseases (NTDs) impose severe health and socioeconomic burdens in impoverished tropical communities. Yet, advancements in AI-driven diagnostic support are h…

cs.CV2025

Enhancing Skin Disease Diagnosis: Interpretable Visual Concept Discovery with SAM

Xin Hu, Janet Wang, Jihun Hamm +2

Current AI-assisted skin image diagnosis has achieved dermatologist-level performance in classifying skin cancer, driven by rapid advancements in deep learning architectures. Howev…