Fully Convolutional Multi-Class Multiple Instance Learning

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.

in ICLR 2015

References in corpus (1)

• Very Deep Convolutional Networks for Large-Scale Image Recognition

Cited by in corpus (11)

• FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
• U-Net: Convolutional Networks for Biomedical Image Segmentation
• Semi and Weakly Supervised Semantic Segmentation Using Generative Adversarial Network
• Incorporating Network Built-in Priors in Weakly-supervised Semantic Segmentation
• Built-in Foreground/Background Prior for Weakly-Supervised Semantic Segmentation
• Applying Topological Persistence in Convolutional Neural Network for Music Audio Signals
• Recent Advances in the Applications of Convolutional Neural Networks to Medical Image Contour Detection
• Large-Scale 3D Scene Classification With Multi-View Volumetric CNN
• Diverse Sampling for Self-Supervised Learning of Semantic Segmentation
• Weakly Supervised Image Annotation and Segmentation with Objects and Attributes
• Hierarchical Scene Parsing by Weakly Supervised Learning with Image Descriptions