Browse > Computer Vision > Semantic Segmentation > Weakly-Supervised Semantic Segmentation

Weakly-Supervised Semantic Segmentation

21 papers with code ยท Computer Vision

The semantic segmentation task is to assign a label from a label set to each pixel in an image. In the case of fully supervised setting, the dataset consists of images and their corresponding pixel-level class-specific annotations (expensive pixel-level annotations). However, in the weakly-supervised setting, the dataset consists of images and corresponding annotations that are relatively easy to obtain, such as tags/labels of objects present in the image.

( Image credit: Weakly-Supervised Semantic Segmentation Network with Deep Seeded Region Growing )

Leaderboards

No evaluation results yet. Help compare methods by submit evaluation metrics.

Latest papers without code

Weakly Supervised Semantic Segmentation in 3D Graph-Structured Point Clouds of Wild Scenes

26 Apr 2020

The deficiency of 3D segmentation labels is one of the main obstacles to effective point cloud segmentation, especially for scenes in the wild with varieties of different objects.

3D SEMANTIC SEGMENTATION SCENE SEGMENTATION WEAKLY-SUPERVISED SEMANTIC SEGMENTATION

Realizing Pixel-Level Semantic Learning in Complex Driving Scenes based on Only One Annotated Pixel per Class

10 Mar 2020

Semantic segmentation tasks based on weakly supervised condition have been put forward to achieve a lightweight labeling process.

WEAKLY-SUPERVISED SEMANTIC SEGMENTATION

Weakly Supervised Semantic Segmentation of Satellite Images for Land Cover Mapping -- Challenges and Opportunities

19 Feb 2020

Therefore, this paper seeks to make a case for the application of weakly supervised learning strategies to get the most out of available data sources and achieve progress in high-resolution large-scale land cover mapping.

WEAKLY-SUPERVISED SEMANTIC SEGMENTATION

Weakly-Supervised Semantic Segmentation by Iterative Affinity Learning

19 Feb 2020

In this paper, we propose an iterative algorithm to learn such pairwise relations, which consists of two branches, a unary segmentation network which learns the label probabilities for each pixel, and a pairwise affinity network which learns affinity matrix and refines the probability map generated from the unary network.

WEAKLY-SUPERVISED SEMANTIC SEGMENTATION

Neural Diffusion Distance for Image Segmentation

NeurIPS 2019

To compute high-resolution diffusion distance or segmentation mask, we design an up-sampling strategy by feature-attentional interpolation which can be learned when training spec-diff-net.

WEAKLY-SUPERVISED SEMANTIC SEGMENTATION

Information Entropy Based Feature Pooling for Convolutional Neural Networks

ICCV 2019

In convolutional neural networks (CNNs), we propose to estimate the importance of a feature vector at a spatial location in the feature maps by the network's uncertainty on its class prediction, which can be quantified using the information entropy.

WEAKLY-SUPERVISED OBJECT LOCALIZATION WEAKLY-SUPERVISED SEMANTIC SEGMENTATION

Attention Bridging Network for Knowledge Transfer

ICCV 2019

With weights sharing and domain adversary training, this knowledge can be successfully transferred by regularizing the network's response to the same category in the target domain.

DOMAIN GENERALIZATION TRANSFER LEARNING WEAKLY-SUPERVISED SEMANTIC SEGMENTATION

Self-Supervised Difference Detection for Weakly-Supervised Semantic Segmentation

ICCV 2019

In this paper, to make the most of such mapping functions, we assume that the results of the mapping function include noise, and we improve the accuracy by removing noise.

WEAKLY-SUPERVISED SEMANTIC SEGMENTATION

Frame-to-Frame Aggregation of Active Regions in Web Videos for Weakly Supervised Semantic Segmentation

ICCV 2019

We propose a method of using videos automatically harvested from the web to identify a larger region of the target object by using temporal information, which is not present in the static image.

OPTICAL FLOW ESTIMATION WEAKLY-SUPERVISED SEMANTIC SEGMENTATION