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

Weakly-Supervised Semantic Segmentation

13 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

Leaderboards

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

Latest papers without code

Masked Based Unsupervised Content Transfer

ICLR 2020

We consider the problem of translating, in an unsupervised manner, between two domains where one contains some additional information compared to the other.

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

Saliency Guided Self-attention Network for Weakly-supervised Semantic Segmentation

12 Oct 2019

Weakly supervised semantic segmentation (WSSS) using only image-level labels can greatly reduce the annotation cost and therefore has attracted considerable research interest.

WEAKLY-SUPERVISED SEMANTIC SEGMENTATION

Integral Object Mining via Online Attention Accumulation

ICCV 2019

In order to accumulate the discovered different object parts, we propose an online attention accumulation (OAA) strategy which maintains a cumulative attention map for each target category in each training image so that the integral object regions can be gradually promoted as the training goes.

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

HistoSegNet: Semantic Segmentation of Histological Tissue Type in Whole Slide Images

ICCV 2019

In digital pathology, tissue slides are scanned into Whole Slide Images (WSI) and pathologists first screen for diagnostically-relevant Regions of Interest (ROIs) before reviewing them.

WEAKLY-SUPERVISED SEMANTIC SEGMENTATION