Diverse Sampling for Self-Supervised Learning of Semantic Segmentation
arXiv:1612.01991
Abstract
We propose an approach for learning category-level semantic segmentation purely from image-level classification tags indicating presence of categories. It exploits localization cues that emerge from training classification-tasked convolutional networks, to drive a "self-supervision" process that automatically labels a sparse, diverse training set of points likely to belong to classes of interest. Our approach has almost no hyperparameters, is modular, and allows for very fast training of segmentation in less than 3 minutes. It obtains competitive results on the VOC 2012 segmentation benchmark. More, significantly the modularity and fast training of our framework allows new classes to efficiently added for inference.
References in corpus (17)
- Adam: A Method for Stochastic Optimization
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
- Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
- Conditional Random Fields as Recurrent Neural Networks
- Fully Convolutional Networks for Semantic Segmentation
- Object Detectors Emerge in Deep Scene CNNs
- STC: A Simple to Complex Framework for Weakly-supervised Semantic Segmentation
- Weakly Supervised Object Localization with Multi-fold Multiple Instance Learning
- Fully Convolutional Multi-Class Multiple Instance Learning
- BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation
- High-performance Semantic Segmentation Using Very Deep Fully Convolutional Networks
- Feedforward semantic segmentation with zoom-out features
- Simple Does It: Weakly Supervised Instance and Semantic Segmentation
- Self-taught Object Localization with Deep Networks
- Deconvolutional Feature Stacking for Weakly-Supervised Semantic Segmentation
- From Image-level to Pixel-level Labeling with Convolutional Networks