2020/08/23 by Rohit Mohan, Abhinav Valada, Mohan, Rohit +1
Computer Science · #Advanced Image and Video Retrieval Techniques #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Robotics (cs.RO) #Video Surveillance and Tracking Methods
paper · pdf · doi:10.48550/arxiv.2008.10112
openalex publication_date 2020/08/23 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
In this technical report, we present key details of our winning panoptic segmentation architecture EffPSb1bs4RVC. Our network is a lightweight version of our state-of-the-art EfficientPS architecture that consists of our proposed shared backbone with a modified EfficientNet-B5 model as the encoder, followed by the 2-way FPN to learn semantically rich multi-scale features. It consists of two task-specific heads, a modified Mask R-CNN instance head and our novel semantic segmentation head that processes features of different scales with specialized modules for coherent feature refinement. Finally, our proposed panoptic fusion module adaptively fuses logits from each of the heads to yield the panoptic segmentation output. The Robust Vision Challenge 2020 benchmarking results show that our model is ranked #1 on Microsoft COCO, VIPER and WildDash, and is ranked #2 on Cityscapes and Mapillary Vistas, thereby achieving the overall rank #1 for the panoptic segmentation task.