In pixels we trust: From Pixel Labeling to Object Localization and Scene Categorization
This work addresses scene understanding for computer vision applications, but it is incremental as it builds on existing methods like DeepLab and ResNet.
The paper tackles scene understanding by using semantic segmentation as input for object localization and scene categorization, achieving new state-of-the-art results on the NYU Depth V2 dataset across all three tasks.
While there has been significant progress in solving the problems of image pixel labeling, object detection and scene classification, existing approaches normally address them separately. In this paper, we propose to tackle these problems from a bottom-up perspective, where we simply need a semantic segmentation of the scene as input. We employ the DeepLab architecture, based on the ResNet deep network, which leverages multi-scale inputs to later fuse their responses to perform a precise pixel labeling of the scene. This semantic segmentation mask is used to localize the objects and to recognize the scene, following two simple yet effective strategies. We evaluate the benefits of our solutions, performing a thorough experimental evaluation on the NYU Depth V2 dataset. Our approach achieves a performance that beats the leading results by a significant margin, defining the new state of the art in this benchmark for the three tasks comprising the scene understanding: semantic segmentation, object detection and scene categorization.