Can I read Deep Common Feature Mining for Efficient Video Semantic Segmentation on EtoBox?

Deep Common Feature Mining for Efficient Video Semantic Segmentation by Zheng, Yaoyan; Yang, Hongyu; Huang, Di is a scholarly article available to read on EtoBox.

What is Deep Common Feature Mining for Efficient Video Semantic Segmentation about?

Recent advancements in video semantic segmentation have made substantial progress by exploiting temporal correlations. Nevertheless, persistent challenges, including redundant computation and the reliability of the feature propagation process, underscore the need for further innovation. In response, we present Deep Common Feature Mining (DCFM), a novel approach strategically designed to address these challenges by leveraging the concept of feature sharing. DCFM explicitly decomposes features into two complementary components. The common representation extracted from a key-frame furnishes essential high-level information to neighboring non-key frames, allowing for direct re-utilization without feature propagation. Simultaneously, the independent feature, derived from each video frame, captures rapidly changing information, providing frame-specific clues crucial for segmentation. To achieve such decomposition, we employ a symmetric training strategy tailored for sparsely annotated data, empowering the backbone to learn a robust high-level representation enriched with common information. Additionally, we incorporate a self-supervised loss function to reinforce intra-class feature simi

Author

Zheng, Yaoyan; Yang, Hongyu; Huang, Di

Published

2024

Language

EN