Detect, Replace, Refine: Deep Structured Prediction For Pixel Wise Labeling

12/14/2016
by   Spyros Gidaris, et al.
0

Pixel wise image labeling is an interesting and challenging problem with great significance in the computer vision community. In order for a dense labeling algorithm to be able to achieve accurate and precise results, it has to consider the dependencies that exist in the joint space of both the input and the output variables. An implicit approach for modeling those dependencies is by training a deep neural network that, given as input an initial estimate of the output labels and the input image, it will be able to predict a new refined estimate for the labels. In this context, our work is concerned with what is the optimal architecture for performing the label improvement task. We argue that the prior approaches of either directly predicting new label estimates or predicting residual corrections w.r.t. the initial labels with feed-forward deep network architectures are sub-optimal. Instead, we propose a generic architecture that decomposes the label improvement task to three steps: 1) detecting the initial label estimates that are incorrect, 2) replacing the incorrect labels with new ones, and finally 3) refining the renewed labels by predicting residual corrections w.r.t. them. Furthermore, we explore and compare various other alternative architectures that consist of the aforementioned Detection, Replace, and Refine components. We extensively evaluate the examined architectures in the challenging task of dense disparity estimation (stereo matching) and we report both quantitative and qualitative results on three different datasets. Finally, our dense disparity estimation network that implements the proposed generic architecture, achieves state-of-the-art results in the KITTI 2015 test surpassing prior approaches by a significant margin.

READ FULL TEXT

page 6

page 12

page 14

page 15

page 16

page 17

page 18

page 19

research
12/11/2017

Error Correction for Dense Semantic Image Labeling

Pixelwise semantic image labeling is an important, yet challenging, task...
research
12/04/2017

Learning Deep Correspondence through Prior and Posterior Feature Constancy

Stereo matching algorithms usually consist of four steps, including matc...
research
10/11/2019

Shooting Labels: 3D Semantic Labeling by Virtual Reality

Availability of a few, large-size, annotated datasets, like ImageNet, Pa...
research
03/01/2020

ZoomNet: Part-Aware Adaptive Zooming Neural Network for 3D Object Detection

3D object detection is an essential task in autonomous driving and robot...
research
02/10/2020

Uncertainty Estimation for End-To-End Learned Dense Stereo Matching via Probabilistic Deep Learning

Motivated by the need to identify erroneous disparity assignments, vario...
research
05/03/2018

Pixel-wise Attentional Gating for Parsimonious Pixel Labeling

To achieve parsimonious inference in per-pixel labeling tasks with a lim...
research
12/20/2014

Training Deep Neural Networks on Noisy Labels with Bootstrapping

Current state-of-the-art deep learning systems for visual object recogni...

Please sign up or login with your details

Forgot password? Click here to reset