A Holistically-Guided Decoder for Deep Representation Learning With Applications to Semantic Segmentation and Object Detection

Both high-level and high-resolution feature representations are of great importance in various visual understanding tasks. To acquire high-resolution feature maps with high-level semantic information, one common strategy is to adopt dilated convolutions in the backbone networks to extract high-resol...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 45(2023), 10 vom: 01. Okt., Seite 11390-11406
1. Verfasser: Liu, Jianbo (VerfasserIn)
Weitere Verfasser: He, Junjun, Zheng, Yuanjie, Yi, Shuai, Wang, Xiaogang, Li, Hongsheng
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2023
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article
Beschreibung
Zusammenfassung:Both high-level and high-resolution feature representations are of great importance in various visual understanding tasks. To acquire high-resolution feature maps with high-level semantic information, one common strategy is to adopt dilated convolutions in the backbone networks to extract high-resolution feature maps, such as the dilatedFCN-based methods for semantic segmentation. However, due to many convolution operations are conducted on the high-resolution feature maps, such methods have large computational complexity and memory consumption. To balance the performance and efficiency, there also exist encoder-decoder structures that gradually recover the spatial information by combining multi-level feature maps from a feature encoder, such as the FPN architecture for object detection and the U-Net for semantic segmentation. Although being more efficient, the performances of existing encoder-decoder methods for semantic segmentation are far from comparable with the dilatedFCN-based methods. In this paper, we propose one novel holistically-guided decoder which is introduced to obtain the high-resolution semantic-rich feature maps via the multi-scale features from the encoder. The decoding is achieved via novel holistic codeword generation and codeword assembly operations, which take advantages of both the high-level and low-level features from the encoder features. With the proposed holistically-guided decoder, we implement the EfficientFCN architecture for semantic segmentation and HGD-FPN for object detection and instance segmentation. The EfficientFCN achieves comparable or even better performance than state-of-the-art methods with only 1/3 of their computational costs for semantic segmentation on PASCAL Context, PASCAL VOC, ADE20K datasets. Meanwhile, the proposed HGD-FPN achieves higher mean Average Precision (mAP) when integrated into several object detection frameworks with ResNet-50 encoding backbones
Beschreibung:Date Revised 06.09.2023
published: Print-Electronic
Citation Status PubMed-not-MEDLINE
ISSN:1939-3539
DOI:10.1109/TPAMI.2021.3114342