5 papers
Occlusion-Aware Panoptic Segmentation with Joint Position Embedding and Occlusion-Level Attention
Wenbo Wei, Jun Wang, Shan Raza +1
Panoptic segmentation in complex scenes remains challenging because of occlusions, yet modern approaches often neglect occlusion modelling. In this paper, we propose Position Embed…
Multiple Descents in Deep Learning as a Sequence of Order-Chaos Transitions in LSTM Networks
Wenbo Wei, Fan Xu, Nicholas Chong Jia Le +2
We observe a novel `multiple-descent' phenomenon during the learning process of a recurrent neural network called long-short-term memory (LSTM) networks during its training on real…
SSVP: Synergistic Semantic-Visual Prompting for Industrial Zero-Shot Anomaly Detection
Chenhao Fu, Han Fang, Xiuzheng Zheng +4
Zero-Shot Anomaly Detection (ZSAD) leverages Vision-Language Models (VLMs) to enable supervision-free industrial inspection. However, existing ZSAD paradigms are constrained by sin…
Boosting Overlapping Organoid Instance Segmentation Using Pseudo-Label Unmixing and Synthesis-Assisted Learning
Gui Huang, Kangyuan Zheng, Xuan Cai +7
Organoids, sophisticated in vitro models of human tissues, are crucial for medical research due to their ability to simulate organ functions and assess drug responses accurately. A…
COCO-OLAC: A Benchmark for Occluded Panoptic Segmentation and Image Understanding
Wenbo Wei, Jun Wang, Abhir Bhalerao
To help address the occlusion problem in panoptic segmentation and image understanding, this paper proposes a new large-scale dataset named COCO-OLAC (COCO Occlusion Labels for All…