Deep Learning for Semantic Part Segmentation with High-Level Guidance

05/10/2015
by   S. Tsogkas, et al.
0

In this work we address the task of segmenting an object into its parts, or semantic part segmentation. We start by adapting a state-of-the-art semantic segmentation system to this task, and show that a combination of a fully-convolutional Deep CNN system coupled with Dense CRF labelling provides excellent results for a broad range of object categories. Still, this approach remains agnostic to high-level constraints between object parts. We introduce such prior information by means of the Restricted Boltzmann Machine, adapted to our task and train our model in an discriminative fashion, as a hidden CRF, demonstrating that prior information can yield additional improvements. We also investigate the performance of our approach "in the wild", without information concerning the objects' bounding boxes, using an object detector to guide a multi-scale segmentation scheme. We evaluate the performance of our approach on the Penn-Fudan and LFW datasets for the tasks of pedestrian parsing and face labelling respectively. We show superior performance with respect to competitive methods that have been extensively engineered on these benchmarks, as well as realistic qualitative results on part segmentation, even for occluded or deformable objects. We also provide quantitative and extensive qualitative results on three classes from the PASCAL Parts dataset. Finally, we show that our multi-scale segmentation scheme can boost accuracy, recovering segmentations for finer parts.

READ FULL TEXT

page 6

page 7

page 9

research
05/24/2018

Complex Relations in a Deep Structured Prediction Model for Fine Image Segmentation

Many deep learning architectures for semantic segmentation involve a Ful...
research
01/17/2017

Convolutional Oriented Boundaries: From Image Segmentation to High-Level Tasks

We present Convolutional Oriented Boundaries (COB), which produces multi...
research
12/28/2018

Coarse-to-fine Semantic Segmentation from Image-level Labels

Deep neural network-based semantic segmentation generally requires large...
research
07/17/2020

GMNet: Graph Matching Network for Large Scale Part Semantic Segmentation in the Wild

The semantic segmentation of parts of objects in the wild is a challengi...
research
03/30/2022

FLOAT: Factorized Learning of Object Attributes for Improved Multi-object Multi-part Scene Parsing

Multi-object multi-part scene parsing is a challenging task which requir...
research
06/03/2016

Reinforcement Learning for Semantic Segmentation in Indoor Scenes

Future advancements in robot autonomy and sophistication of robotics tas...
research
07/13/2016

Do semantic parts emerge in Convolutional Neural Networks?

Semantic object parts can be useful for several visual recognition tasks...

Please sign up or login with your details

Forgot password? Click here to reset