Weakly-Supervised Semantic Segmentation

79 papers with code • 3 benchmarks • 4 datasets

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 )


Use these libraries to find Weakly-Supervised Semantic Segmentation models and implementations

Most implemented papers

Constrained-CNN losses for weakly supervised segmentation

LIVIAETS/SizeLoss_WSS 12 May 2018

To the best of our knowledge, the method of [Pathak et al., 2015] is the only prior work that addresses deep CNNs with linear constraints in weakly supervised segmentation.

Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations

jiwoon-ahn/irn CVPR 2019

For generating the pseudo labels, we first identify confident seed areas of object classes from attention maps of an image classification model, and propagate them to discover the entire instance areas with accurate boundaries.

Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation

deeplab/deeplab-public 9 Feb 2015

Deep convolutional neural networks (DCNNs) trained on a large number of images with strong pixel-level annotations have recently significantly pushed the state-of-art in semantic image segmentation.

Puzzle-CAM: Improved localization via matching partial and full features

OFRIN/PuzzleCAM 27 Jan 2021

Weakly-supervised semantic segmentation (WSSS) is introduced to narrow the gap for semantic segmentation performance from pixel-level supervision to image-level supervision.

Fully Convolutional Multi-Class Multiple Instance Learning

ahounkanrin/FCN-MIL 22 Dec 2014

We propose a novel MIL formulation of multi-class semantic segmentation learning by a fully convolutional network.

Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation

jiwoon-ahn/psa CVPR 2018

To alleviate this issue, we present a novel framework that generates segmentation labels of images given their image-level class labels.

Integral Object Mining via Online Attention Accumulation

PengtaoJiang/OAA-PyTorch 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.

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

lyndonchan/hsn_v1 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.

Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentation

YudeWang/SEAM CVPR 2020

Our method is based on the observation that equivariance is an implicit constraint in fully supervised semantic segmentation, whose pixel-level labels take the same spatial transformation as the input images during data augmentation.

Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation

GuoleiSun/MCIS_wsss ECCV 2020

Moreover, our approach ranked 1st place in the Weakly-Supervised Semantic Segmentation Track of CVPR2020 Learning from Imperfect Data Challenge.