On Regularized Losses for Weakly-supervised CNN Segmentation

Abstract

Minimization of regularized losses is a principled approach to weak supervision well-established in deep learning, in general. However, it is largely overlooked in semantic segmentation currently dominated by methods mimicking full supervision via "fake" fully-labeled training masks (proposals) generated from available partial input. To obtain such full masks the typical methods explicitly use standard regularization techniques for "shallow" segmentation, e.g. graph cuts or dense CRFs. In contrast, we integrate such standard regularizers directly into the loss functions over partial input. This approach simplifies weakly-supervised training by avoiding extra MRF/CRF inference steps or layers explicitly generating full masks, while improving both the quality and efficiency of training. This paper proposes and experimentally compares different losses integrating MRF/CRF regularization terms. We juxtapose our regularized losses with earlier proposal-generation methods using explicit regularization steps or layers. Our approach achieves state-of-the-art accuracy in semantic segmentation with near full-supervision quality.

References in corpus (5)

• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
• DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
• Adversarial Learning for Semi-Supervised Semantic Segmentation
• BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation
• Normalized Cut Loss for Weakly-supervised CNN Segmentation

Cited by in corpus (4)

• Gated CRF Loss for Weakly Supervised Semantic Image Segmentation
• Normalized Cut Loss for Weakly-supervised CNN Segmentation
• Scribble Hides Class: Promoting Scribble-Based Weakly-Supervised Semantic Segmentation with Its Class Label
• Regularization of Building Boundaries in Satellite Images using Adversarial and Regularized Losses