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

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.

READ FULL TEXT

page 1

page 5

page 7

research
08/09/2017

BlitzNet: A Real-Time Deep Network for Scene Understanding

Real-time scene understanding has become crucial in many applications su...
research
11/17/2020

Multi Receptive Field Network for Semantic Segmentation

Semantic segmentation is one of the key tasks in computer vision, which ...
research
10/24/2011

Towards Holistic Scene Understanding: Feedback Enabled Cascaded Classification Models

Scene understanding includes many related sub-tasks, such as scene categ...
research
07/23/2021

Standardized Max Logits: A Simple yet Effective Approach for Identifying Unexpected Road Obstacles in Urban-Scene Segmentation

Identifying unexpected objects on roads in semantic segmentation (e.g., ...
research
06/03/2016

Reinforcement Learning for Semantic Segmentation in Indoor Scenes

Future advancements in robot autonomy and sophistication of robotics tas...
research
08/20/2011

Toward Parts-Based Scene Understanding with Pixel-Support Parts-Sparse Pictorial Structures

Scene understanding remains a significant challenge in the computer visi...
research
02/10/2012

Scene Parsing with Multiscale Feature Learning, Purity Trees, and Optimal Covers

Scene parsing, or semantic segmentation, consists in labeling each pixel...

Please sign up or login with your details

Forgot password? Click here to reset