Fully Convolutional Multi-Class Multiple Instance Learning

2014/12/22 by Pathak, Deepak, Shelhamer, Evan, Long, Jonathan +1 · 2 citations
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE)

paper · doi:10.48550/arxiv.1412.7144

Abstract

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

• Emerging Semantic Segmentation from Positive and Negative Coarse Label Learning
• Weakly-Supervised Image Forgery Localization via Vision-Language Collaborative Reasoning Framework

Related

• From Image-level to Pixel-level Labeling with Convolutional Networks
• Instance-aware Semantic Segmentation via Multi-task Network Cascades
• Active Learning for Semantic Segmentation with Multi-class Label Query
• Diverse Sampling for Self-Supervised Learning of Semantic Segmentation
• Multi-Evidence Filtering and Fusion for Multi-Label Classification, Object Detection and Semantic Segmentation Based on Weakly Supervised Learning