2021/12/08 by Qi Song, Jie Li, Song, Qi +7 · 2 citations
Computer Science · #Advanced Neural Network Applications #Artificial intelligence #Attention network #Channel (broadcasting) #Computer science #Domain Adaptation and Few-Shot Learning #Feature (linguistics) #Image (mathematics) #Multimodal Machine Learning Applications #Pascal (unit) #Pattern recognition (psychology) #Segmentation #Set (abstract data type) #Similarity (geometry) #cs.CV
paper · pdf · doi:10.48550/arxiv.2112.04108
published in arXiv (Cornell University) (Cornell University) · Accepted by AAAI 2022
openalex publication_date 2021/12/08 · arxiv created 2022/07/11 · arxiv updated 2022/07/12 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Recent non-local self-attention methods have proven to be effective in capturing long-range dependencies for semantic segmentation. These methods usually form a similarity map of RC*C (by compressing spatial dimensions) or RHW*HW (by compressing channels) to describe the feature relations along either channel or spatial dimensions, where C is the number of channels, H and W are the spatial dimensions of the input feature map. However, such practices tend to condense feature dependencies along the other dimensions,hence causing attention missing, which might lead to inferior results for small/thin categories or inconsistent segmentation inside large objects. To address this problem, we propose anew approach, namely Fully Attentional Network (FLANet),to encode both spatial and channel attentions in a single similarity map while maintaining high computational efficiency. Specifically, for each channel map, our FLANet can harvest feature responses from all other channel maps, and the associated spatial positions as well, through a novel fully attentional module. Our new method has achieved state-of-the-art performance on three challenging semantic segmentation datasets,i.e., 83.6%, 46.99%, and 88.5% on the Cityscapes test set,the ADE20K validation set, and the PASCAL VOC test set,respectively.