No boundary left behind in semantic segmentation

• Published in: 2022 35th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) Vol. 1; pp. 115 - 120
• Main Authors: Da Silva, Jefferson Fontinele, Silva, Bernardo, Oliveira, Luciano
• Format: Conference Proceeding
• Language: English
• Published: IEEE 24-10-2022
• Subjects: Convolutional neural networks; Graphics; Logic gates; Network architecture; Semantic segmentation; Semantics; Training
• ISSN: 2377-5416
• DOI: 10.1109/SIBGRAPI55357.2022.9991760

This paper proposes a novel network architecture for image semantic segmentation based on attention mechanisms placed on specific points inside a convolutional neural network. Attention is explored across our network to integrate information from object boundary and a baseline semantic segmenter (inner segmentation). We call our novel network Attention-fitted Fusion of boundary and Inner Segmentation (AFIS), which combines the two streams through a set of attention gates, forming an end-to-end network. We performed an extensive evaluation of our method over four public challenging data sets (Cityscapes, CamVid, Pascal Context, and Mapillary Vistas), finding superior results when compared with other twelve state-of-the-art segmenters, considering the same training conditions.