4 papers
Role-Decoupled Attention Residuals: Separating Matching and Content Retrieval Across Depth
Kehan Wang
Depth-routing residual architectures allow Transformer layers to retrieve earlier representations instead of inheriting only the immediately preceding state. Existing Block Attenti…
HAARES Half-Split Residual Basis Routing for Deep Transformers
Kehan Wang
Block-level residual routing makes learned residual aggregation practical by routing over block summaries, but each summary compresses an ordered sequence of attention and MLP upda…
Intelligent Image Search Algorithms Fusing Visual Large Models
Kehan Wang, Tingqiong Cui, Yang Zhang +3
Fine-grained image retrieval, which aims to find images containing specific object components and assess their detailed states, is critical in fields like security and industrial i…
Uncertainty Aware Human-machine Collaboration in Camouflaged Object Detection
Ziyue Yang, Kehan Wang, Yuhang Ming +4
Camouflaged Object Detection (COD), the task of identifying objects concealed within their environments, has seen rapid growth due to its wide range of practical applications. A ke…