Fully Convolutional Multi-Class Multiple Instance Learning
Deepak Pathak, Evan Shelhamer, Jonathan Long et al. · arXiv (Cornell University) · 2014
Multiple instance learning (MIL) can reduce the need for costly annotation in tasks such as semantic segmentation by weakening the required degree of supervision. We propose a novel MIL formulation of multi-class semantic segmentation learning by a fully convolutional network. In this setting, we seek to learn a semantic segmentation model from just weak image-level labels. The model is trained end-to-end to jointly optimize the representation while disambiguating the pixel-image label assignment. Fully convolutional training accepts inputs of any size, does not need object proposal pre-processing, and offers a pixelwise loss map for selecting latent instances. Our multi-class MIL loss exploits the further supervision given by images with multiple labels. We evaluate this approach through preliminary experiments on the PASCAL VOC segmentation challenge.
Cited by 236 works. doi:10.48550/arxiv.1412.7144 Open-access PDF
Authors
References
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
- Object Detection with Discriminatively Trained Part-Based Models
- Fully Convolutional Networks for Semantic Segmentation
- Semantic contours from inverse detectors
- SLIC Superpixels Compared to State-of-the-Art Superpixel Methods
- Support Vector Machines for Multiple-Instance Learning
- Multi-fold MIL Training for Weakly Supervised Object Localization
- Detector discovery in the wild: Joint multiple instance and representation learning
- A Tractable Inference Algorithm for Diagnosing Multiple Diseases