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

Last update: Oct 23, 2021

Related tags

Deep Learning SCOT

Overview

DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision

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

@article{lan2021discobox,
  title={DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision},
  author={Lan, Shiyi and Yu, Zhiding and Choy, Christopher and Radhakrishnan, Subhashree and Liu, Guilin and Zhu, Yuke and Davis, Larry S and Anandkumar, Anima},
  journal={arXiv preprint arXiv:2105.06464},
  year={2021}
}

[ Paper ]

Introduction

This repository is the implementation of evaluating DiscoBox on PF-Pascal dataset.

This implementation is based on SCOT

Installation

Conda environment settings

conda create -n scot python=3.6
conda activate scot

cat /usr/local/cuda/version.txt
conda install pytorch=1.4.0 torchvision cudatoolkit=10.0 -c pytorch (if CUDA 10) 
conda install pytorch=1.4.0 torchvision cudatoolkit=9.0 -c pytorch (if CUDA 9) 

conda install -c anaconda scikit-image
conda install -c anaconda pandas
conda install -c anaconda requests
pip install gluoncv-torch

Pretrained Weights

Download the pretrained weights from this link.

Evaluation

Results on PF-PASCAL with res101:

    python evaluate_map_CAM.py --dataset pfpascal --thres img --backbone resnet101 --hyperpixel '(2,22,24,25,27,28,29)' --sim OTGeo --exp1 1.0 --exp2 0.5 --eps 0.05 --gpu 0 --classmap 1 --split test --alpha 0.05
    python evaluate_map_CAM.py --dataset pfpascal --thres img --backbone resnet101 --hyperpixel '(2,22,24,25,27,28,29)' --sim OTGeo --exp1 1.0 --exp2 0.5 --eps 0.05 --gpu 0 --classmap 1 --split test --alpha 0.10
    python evaluate_map_CAM.py --dataset pfpascal --thres img --backbone resnet101 --hyperpixel '(2,22,24,25,27,28,29)' --sim OTGeo --exp1 1.0 --exp2 0.5 --eps 0.05 --gpu 0 --classmap 1 --split test --alpha 0.15

All results

Method	Backbone	[email protected]	[email protected]	[email protected]
SCOT	ResNet-101	63.2	85.4	92.8
DiscoBox	ResNet-101	62.7	85.6	93.5

Training

Please look at this link for more details

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

Related tags

Overview

DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision

Introduction

Installation

Conda environment settings

Pretrained Weights

Evaluation

All results

Training

Owner

Shiyi Lan

This is the second place solution for : UmojaHack Africa 2022: African Snake Antivenom Binding Challenge

CLIPort: What and Where Pathways for Robotic Manipulation

Implementation of ReSeg using PyTorch

Using CNN to mimic the driver based on training data from Torcs

Implementation of the GBST block from the Charformer paper, in Pytorch

A learning-based data collection tool for human segmentation

Implementation of UNET architecture for Image Segmentation.

EMNLP 2021: Single-dataset Experts for Multi-dataset Question-Answering

Codes for ACL-IJCNLP 2021 Paper "Zero-shot Fact Verification by Claim Generation"

Generalized Data Weighting via Class-level Gradient Manipulation

A High-Performance Distributed Library for Large-Scale Bundle Adjustment

A Light in the Dark: Deep Learning Practices for Industrial Computer Vision

Leaderboard, taxonomy, and curated list of few-shot object detection papers.

This is my codes that can visualize the psnr image in testing videos.

TyXe: Pyro-based BNNs for Pytorch users

AdaFocus V2: End-to-End Training of Spatial Dynamic Networks for Video Recognition

Analysing poker data from home games with friends

PAMI stands for PAttern MIning. It constitutes several pattern mining algorithms to discover interesting patterns in transactional/temporal/spatiotemporal databases

Here is the implementation of our paper S2VC: A Framework for Any-to-Any Voice Conversion with Self-Supervised Pretrained Representations.

UCSD Oasis platform