In pixels we trust: From Pixel Labeling to Object Localization and Scene Categorization

TL;DR

This paper introduces a bottom-up approach using semantic segmentation to unify pixel labeling, object detection, and scene classification, achieving state-of-the-art results on the NYU Depth V2 dataset.

Contribution

The paper presents a novel method that leverages semantic segmentation as a foundation to improve object localization and scene categorization, outperforming existing approaches.

Findings

Achieves new state-of-the-art performance on NYU Depth V2 for all three tasks.

Demonstrates the effectiveness of using semantic segmentation as a unified basis.

Significantly outperforms previous methods in scene understanding benchmarks.

Abstract

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.