Constrained Convolutional Neural Networks for Weakly Supervised Segmentation

TitleConstrained Convolutional Neural Networks for Weakly Supervised Segmentation
Publication TypeConference Paper
Year of Publication2015
AuthorsPathak, D., Krahenbuhl P., & Darrell T.
Published inThe IEEE International Conference on Computer Vision (ICCV)
Page(s)1796-1804
Date Published12/2015
Abstract

We present an approach to learn a dense pixel-wise labeling from image-level tags. Each image-level tag imposes constraints on the output labeling of a Convolutional Neural Network (CNN) classifier. We propose Constrained CNN (CCNN), a method which uses a novel loss function to optimize for any set of linear constraints on the output space (i.e. predicted label distribution) of a CNN. Our loss formulation is easy to optimize and can be incorporated directly into standard stochastic gradient descent optimization. The key idea is to phrase the training objective as a biconvex optimization for linear models, which we then relax to nonlinear deep networks. Extensive experiments demonstrate the generality of our new learning framework. The constrained loss yields state-of-the-art results on weakly supervised semantic image segmentation. We further demonstrate that adding slightly more supervision can greatly improve the performance of the learning algorithm.

URLhttp://www.icsi.berkeley.edu/pubs/vision/constrainedconvolutional15.pdf
ICSI Research Group

Vision