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

RRxIO - Robust Radar Visual/Thermal Inertial Odometry: Robust and accurate state estimation even in challenging visual conditions.

An end-to-end implementation of intent prediction with Metaflow and other cool tools

Distance-Ratio-Based Formulation for Metric Learning

Reinforcement learning algorithms in RLlib

PyTorch implementation of the TTC algorithm

Implementation of ICLR 2020 paper "Revisiting Self-Training for Neural Sequence Generation"

Artificial intelligence technology inferring issues and logically supporting facts from raw text

Hyperparameter Optimization for TensorFlow, Keras and PyTorch

Code for "PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation" CVPR 2019 oral

Codes and pretrained weights for winning submission of 2021 Brain Tumor Segmentation (BraTS) Challenge

Photographic Image Synthesis with Cascaded Refinement Networks - Pytorch Implementation

Paddle pit - Rethinking Spatial Dimensions of Vision Transformers

RMNA: A Neighbor Aggregation-Based Knowledge Graph Representation Learning Model Using Rule Mining

Test-Time Personalization with a Transformer for Human Pose Estimation, NeurIPS 2021

PlenOctrees: NeRF-SH Training & Conversion

Multi-query Video Retreival

HAT: Hierarchical Aggregation Transformers for Person Re-identification

MVSDF - Learning Signed Distance Field for Multi-view Surface Reconstruction

Shared Attention for Multi-label Zero-shot Learning

A pytorch-based deep learning framework for multi-modal 2D/3D medical image segmentation