From the 1 of 6 linked papers with an AI index.
6 papers
Training-Free Decoding of SAM3 Semantic Responses for Cross-Domain Infrastructure Crack Segmentation
Shipeng Liu, Zhanping Song, Liang Zhao +1
The paper introduces Semantic-Edge Response Decoding (SERD), a method that extracts internal semantic responses from the SAM3 vision model and refines them with an edge prior to ac…
Rethinking Efficient Crack Segmentation with Task-Aligned Structural-Directional Modeling
Shipeng Liu, Liang Zhao, Dengfeng Chen +1
Recent crack segmentation methods often follow generic semantic segmentation designs, using stronger backbones, hybrid CNN-Transformer-Mamba encoders, and auxiliary enhancement bra…
Training-Free Tunnel Defect Inspection and Engineering Interpretation via Visual Recalibration and Entity Reconstruction
Shipeng Liu, Liang Zhao, Dengfeng Chen +1
Tunnel inspection requires outputs that can support defect localization, measurement, severity grading, and engineering documentation. Existing training-free foundation-model pipel…
Describe-to-Score: A text-guided framework for image complexity assessment
Shipeng Liu, Zhonglin Zhang, Dengfeng Chen +1
Accurately assessing image complexity (IC) is essential for many vision tasks, yet existing approaches rely almost exclusively on visual features and therefore fail to capture the…
CLIC: Contrastive Learning Framework for Unsupervised Image Complexity Representation
Shipeng Liu, Liang Zhao, Dengfeng Chen
As a fundamental visual attribute, image complexity significantly influences both human perception and the performance of computer vision models. However, accurately assessing and…
CLICv2: Image Complexity Representation via Content Invariance Contrastive Learning
Shipeng Liu, Liang Zhao, Dengfeng Chen
Unsupervised image complexity representation often suffers from bias in positive sample selection and sensitivity to image content. We propose CLICv2, a contrastive learning framew…