Fully Convolutional Multi-Class Multiple Instance Learning

2014-12-22 · Deepak Pathak, Evan Shelhamer, Jonathan Long, Trevor Darrell

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.

📄 PDF Abstract BibTeX arXiv:1412.7144

Code (1)

ahounkanrin/FCN-MIL tf

Tasks

Multiple Instance Learning Segmentation Semantic Segmentation Weakly-Supervised Semantic Segmentation

BiSeg: Simultaneous Instance Segmentation and Semantic Segmentation with Fully Convolutional Networks

2017-06-07 · Viet-Quoc Pham, Satoshi Ito, Tatsuo Kozakaya

We present a simple and effective framework for simultaneous semantic segmentation and instance segmentation with Fully Convolutional Networks (FCNs). The method, called BiSeg, predicts instance segmentation as a posteri…

Bayesian Inference Instance Segmentation Position Segmentation+1

Weakly Supervised Convolutional Dictionary Learning for Multi-Label Classification

2025-03-11 · Hao Chen, Dayuan Tan

Convolutional Dictionary Learning (CDL) has emerged as a powerful approach for signal representation by learning translation-invariant features through convolution operations. While existing CDL methods are predominantly…

Classification Dictionary Learning Environmental Sound Classification Multi-Label Classification+2

Brain Tumor Segmentation Based on Refined Fully Convolutional Neural Networks with A Hierarchical Dice Loss

2017-12-25 · Jiachi Zhang, Xiaolei Shen, Tianqi Zhuo, Hong Zhou

As a basic task in computer vision, semantic segmentation can provide fundamental information for object detection and instance segmentation to help the artificial intelligence better understand real world. Since the pro…

Binary Classification Brain Tumor Segmentation General Classification Instance Segmentation+5

A Multi-scale Multiple Instance Video Description Network

2015-05-21 · Huijuan Xu, Subhashini Venugopalan, Vasili Ramanishka, Marcus Rohrbach 외

Generating natural language descriptions for in-the-wild videos is a challenging task. Most state-of-the-art methods for solving this problem borrow existing deep convolutional neural network (CNN) architectures (AlexNet…

Image Segmentation Multiple Instance Learning Semantic Segmentation Sentence+1

Fully Convolutional Instance-aware Semantic Segmentation

2016-11-23 · CVPR 2017 7 · Yi Li, Haozhi Qi, Jifeng Dai, Xiangyang Ji 외

We present the first fully convolutional end-to-end solution for instance-aware semantic segmentation task. It inherits all the merits of FCNs for semantic segmentation and instance mask proposal. It performs instance ma…

General Classification Instance Segmentation Segmentation Semantic Segmentation