Dual-Thresholded Heatmap-Guided Proposal Clustering and Negative Certainty Supervision with Enhanced Base Network for Weakly Supervised Object Detection

ArXi:2509.08289v2 Announce Type: replace Weakly supervised object detection (WSOD) has attracted significant attention in recent years, as it does not require box-level annotations. State-of-the-art methods generally adopt a multi-module network, which employs WSDDN as the multiple instance detection network module and uses multiple instance refinement modules to refine performance. However, these approaches suffer from three key limitations.