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

Recurrent Scale Approximation (RSA) for Object Detection

Catalyst.Detection

ICML 21 - Voice2Series: Reprogramming Acoustic Models for Time Series Classification

Lbl2Vec learns jointly embedded label, document and word vectors to retrieve documents with predefined topics from an unlabeled document corpus.

Pre-Training 3D Point Cloud Transformers with Masked Point Modeling

GMFlow: Learning Optical Flow via Global Matching

Deep Learning Head Pose Estimation using PyTorch.

📚 A collection of all the Deep Learning Metrics that I came across which are not accuracy/loss.

Benchmarks for semi-supervised domain generalization.

Codes for realizing theories learned from Data Mining, Machine Learning, Deep Learning without using the present Python packages.

Labels4Free: Unsupervised Segmentation using StyleGAN

This repository includes code of my study about Asynchronous in Frequency domain of GAN images.

Improving Query Representations for DenseRetrieval with Pseudo Relevance Feedback:A Reproducibility Study.

LeViT a Vision Transformer in ConvNet's Clothing for Faster Inference

Self-Supervised Document-to-Document Similarity Ranking via Contextualized Language Models and Hierarchical Inference

Animatable Neural Radiance Fields for Modeling Dynamic Human Bodies

The final project of "Applying AI to 3D Medical Imaging Data" from "AI for Healthcare" nanodegree - Udacity.

Reproducing-BowNet: Learning Representations by Predicting Bags of Visual Words

KDD CUP 2020 Automatic Graph Representation Learning: 1st Place Solution

This program will stylize your photos with fast neural style transfer.