DeepAI AI Chat
Log In Sign Up

STC: A Simple to Complex Framework for Weakly-supervised Semantic Segmentation

09/10/2015
by   Yunchao Wei, et al.
Nankai University
National University of Singapore
adobe
BEIJING JIAOTONG UNIVERSITY
0

Recently, significant improvement has been made on semantic object segmentation due to the development of deep convolutional neural networks (DCNNs). Training such a DCNN usually relies on a large number of images with pixel-level segmentation masks, and annotating these images is very costly in terms of both finance and human effort. In this paper, we propose a simple to complex (STC) framework in which only image-level annotations are utilized to learn DCNNs for semantic segmentation. Specifically, we first train an initial segmentation network called Initial-DCNN with the saliency maps of simple images (i.e., those with a single category of major object(s) and clean background). These saliency maps can be automatically obtained by existing bottom-up salient object detection techniques, where no supervision information is needed. Then, a better network called Enhanced-DCNN is learned with supervision from the predicted segmentation masks of simple images based on the Initial-DCNN as well as the image-level annotations. Finally, more pixel-level segmentation masks of complex images (two or more categories of objects with cluttered background), which are inferred by using Enhanced-DCNN and image-level annotations, are utilized as the supervision information to learn the Powerful-DCNN for semantic segmentation. Our method utilizes 40K simple images from Flickr.com and 10K complex images from PASCAL VOC for step-wisely boosting the segmentation network. Extensive experimental results on PASCAL VOC 2012 segmentation benchmark well demonstrate the superiority of the proposed STC framework compared with other state-of-the-arts.

READ FULL TEXT

page 3

page 5

page 8

11/19/2019

Reliability Does Matter: An End-to-End Weakly Supervised Semantic Segmentation Approach

Weakly supervised semantic segmentation is a challenging task as it only...
02/01/2018

Learning Semantic Segmentation with Diverse Supervision

Models based on deep convolutional neural networks (CNN) have significan...
12/28/2018

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

Deep neural network-based semantic segmentation generally requires large...
08/04/2021

Free Lunch for Co-Saliency Detection: Context Adjustment

We unveil a long-standing problem in the prevailing co-saliency detectio...
06/12/2018

Weakly-Supervised Semantic Segmentation by Iteratively Mining Common Object Features

Weakly-supervised semantic segmentation under image tags supervision is ...
12/03/2014

Convolutional Feature Masking for Joint Object and Stuff Segmentation

The topic of semantic segmentation has witnessed considerable progress d...
12/07/2016

Bottom-Up Top-Down Cues for Weakly-Supervised Semantic Segmentation

We consider the task of learning a classifier for semantic segmentation ...