Exploiting saliency for object segmentation from image level labels

Abstract

There have been remarkable improvements in the semantic labelling task in the recent years. However, the state of the art methods rely on large-scale pixel-level annotations. This paper studies the problem of training a pixel-wise semantic labeller network from image-level annotations of the present object classes. Recently, it has been shown that high quality seeds indicating discriminative object regions can be obtained from image-level labels. Without additional information, obtaining the full extent of the object is an inherently ill-posed problem due to co-occurrences. We propose using a saliency model as additional information and hereby exploit prior knowledge on the object extent and image statistics. We show how to combine both information sources in order to recover 80% of the fully supervised performance - which is the new state of the art in weakly supervised training for pixel-wise semantic labelling. The code is available at https://goo.gl/KygSeb.

arXiv commentCVPR 2017

References in corpus (19)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
• Striving for Simplicity: The All Convolutional Net
• Multi-Scale Context Aggregation by Dilated Convolutions
• Fully Convolutional Networks for Semantic Segmentation
• DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
• STC: A Simple to Complex Framework for Weakly-supervised Semantic Segmentation
• Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation
• Learning Deconvolution Network for Semantic Segmentation
• DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detection
• Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation
• Fully Convolutional Multi-Class Multiple Instance Learning
• BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation
• Deep Contrast Learning for Salient Object Detection
• PixelNet: Towards a General Pixel-level Architecture
• What's the Point: Semantic Segmentation with Point Supervision
• ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised Localization
• Simple Does It: Weakly Supervised Instance and Semantic Segmentation
• Built-in Foreground/Background Prior for Weakly-Supervised Semantic Segmentation

Cited by in corpus (13)

• Review: Deep Learning in Electron Microscopy
• CEREALS - Cost-Effective REgion-based Active Learning for Semantic Segmentation
• Effective Use of Synthetic Data for Urban Scene Semantic Segmentation
• Self-Erasing Network for Integral Object Attention
• Weakly Supervised Semantic Segmentation Based on Web Image Co-segmentation
• Self-explanatory Deep Salient Object Detection
• WebSeg: Learning Semantic Segmentation from Web Searches
• Adaptive Binarization for Weakly Supervised Affordance Segmentation
• Multi-Miner: Object-Adaptive Region Mining for Weakly-Supervised Semantic Segmentation
• Weakly- and Semi-Supervised Panoptic Segmentation
• Weakly Supervised Domain-Specific Color Naming Based on Attention
• Saliency guided deep network for weakly-supervised image segmentation
• Global and Local Sensitivity Guided Key Salient Object Re-augmentation for Video Saliency Detection