Weakly-supervised semantic image segmentation with CNNs using point supervision

Last update: Sep 14, 2022

Related tags

Overview

Code for our ECCV paper What's the Point: Semantic Segmentation with Point Supervision.

Summary

This library is a custom build of Caffe for semantic image segmentation with point supervision. It is written for the "FCN-32S-PASCAL" model (fully-convolutional network, stride of 32 for PASCAL VOC 2012), based on this model. More details on the original model are available here.

Quick Start

See the code README page to get started.

Code Structure

All Caffe src files and models are in the caffe directory. All code and scripts to run and evaluate the various models are in the whats-the-point-2016 directory.

Modified Caffe src files:

softmax_loss_expectation_layer.cpp: CPU version of our custom loss layer
softmax_loss_expectation_layer.cu: GPU version of our custom loss layer
loss_layers.hpp: Registers our new loss layer
caffe.proto: Adds new loss parameters.

Code for the paper One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation, CVPR 2021.

One Thing One Click One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation (CVPR2021) Code for the paper One Thi

44 Dec 12, 2022

Reducing Information Bottleneck for Weakly Supervised Semantic Segmentation (NeurIPS 2021)

Reducing Information Bottleneck for Weakly Supervised Semantic Segmentation (NeurIPS 2021) The implementation of Reducing Infromation Bottleneck for W

81 Dec 16, 2022

Contrastive learning of Class-agnostic Activation Map for Weakly Supervised Object Localization and Semantic Segmentation (CVPR 2022)

CCAM (Unsupervised) Code repository for our paper "CCAM: Contrastive learning of Class-agnostic Activation Map for Weakly Supervised Object Localizati

113 Dec 27, 2022

[CVPR'22] Weakly Supervised Semantic Segmentation by Pixel-to-Prototype Contrast

wseg Overview The Pytorch implementation of Weakly Supervised Semantic Segmentation by Pixel-to-Prototype Contrast. [arXiv] Though image-level weakly

96 Dec 30, 2022

Learning trajectory representations using self-supervision and programmatic supervision.

Trajectory Embedding for Behavior Analysis (TREBA) Implementation from the paper: Jennifer J. Sun, Ann Kennedy, Eric Zhan, David J. Anderson, Yisong Y

58 Jan 6, 2023

Group R-CNN for Point-based Weakly Semi-supervised Object Detection (CVPR2022)

Group R-CNN for Point-based Weakly Semi-supervised Object Detection (CVPR2022) By Shilong Zhang*, Zhuoran Yu*, Liyang Liu*, Xinjiang Wang, Aojun Zhou,

129 Dec 24, 2022

Leveraging Instance-, Image- and Dataset-Level Information for Weakly Supervised Instance Segmentation

Leveraging Instance-, Image- and Dataset-Level Information for Weakly Supervised Instance Segmentation This paper has been accepted and early accessed

39 Sep 20, 2022

Cross-Image Region Mining with Region Prototypical Network for Weakly Supervised Segmentation

Cross-Image Region Mining with Region Prototypical Network for Weakly Supervised Segmentation The code of: Cross-Image Region Mining with Region Proto

16 Nov 26, 2022

Mixup for Supervision, Semi- and Self-Supervision Learning Toolbox and Benchmark

OpenSelfSup News Downstream tasks now support more methods(Mask RCNN-FPN, RetinaNet, Keypoints RCNN) and more datasets(Cityscapes). 'GaussianBlur' is

332 Jan 3, 2023

Comments

Labels for objectness priors

Hi, sorry for opening an issue after a long time.

I was trying to implement your code in PyTorch with a different architecture, but I am stuck by finding a way of implementing the objectness prior. In particular, I don't know how to get the predictions which are used as ground truth. Are these provided for PASCAL-VOC Images? How can I get them? I see that there is the Matlab code for them, but it's not clear to me on which data you had trained that model.

If you can provide the objectness prior labels as png/jpg images it would be amazing! Thank you!

opened by fcdl94 1
How to train with my own data with point supervision and my own model, not fcn32 model?

I mean I can only find three .prototxt files in the folder and I can not find the new soft_max_expectation layer in the the three. I do not quite understand where to see the difference between point supervision and pixel-level supervision from the files.

opened by brisker 1

Owner

GitHub

The PyTorch implementation of DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision.

DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision The PyTorch implementation of DiscoBox: Weakly Supe

1 Oct 23, 2021

Perturbed Self-Distillation: Weakly Supervised Large-Scale Point Cloud Semantic Segmentation (ICCV2021)

Perturbed Self-Distillation: Weakly Supervised Large-Scale Point Cloud Semantic Segmentation (ICCV2021) This is the implementation of PSD (ICCV 2021),

12 Dec 12, 2022

Weakly Supervised Dense Event Captioning in Videos, i.e. generating multiple sentence descriptions for a video in a weakly-supervised manner.

WSDEC This is the official repo for our NeurIPS paper Weakly Supervised Dense Event Captioning in Videos. Description Repo directories ./: global conf

96 Nov 1, 2022

A Comprehensive Analysis of Weakly-Supervised Semantic Segmentation in Different Image Domains (IJCV submission)

wsss-analysis The code of: A Comprehensive Analysis of Weakly-Supervised Semantic Segmentation in Different Image Domains, arXiv pre-print 2019 paper.

48 Dec 18, 2022

A weakly-supervised scene graph generation codebase. The implementation of our CVPR2021 paper ``Linguistic Structures as Weak Supervision for Visual Scene Graph Generation''

README.md shall be finished soon. WSSGG 0 Overview 1 Installation 1.1 Faster-RCNN 1.2 Language Parser 1.3 GloVe Embeddings 2 Settings 2.1 VG-GT-Graph

35 Nov 20, 2022