5 papers
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…
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…
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…
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…
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…