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

Machine Learning Toolkit for Kubernetes

Training Confidence-Calibrated Classifier for Detecting Out-of-Distribution Samples / ICLR 2018

Using this you can control your PC/Laptop volume by Hand Gestures (pinch-in, pinch-out) created with Python.

This folder contains the python code of UR5E's advanced forward kinematics model.

Real-time Neural Representation Fusion for Robust Volumetric Mapping

Bottom-up attention model for image captioning and VQA, based on Faster R-CNN and Visual Genome

text_recognition_toolbox: The reimplementation of a series of classical scene text recognition papers with Pytorch in a uniform way.

🔅 Shapash makes Machine Learning models transparent and understandable by everyone

Implementation of the Point Transformer layer, in Pytorch

Learning an Adaptive Meta Model-Generator for Incrementally Updating Recommender Systems

NeuroGen: activation optimized image synthesis for discovery neuroscience

buildseg is a building extraction plugin of QGIS based on PaddlePaddle.

This repository is for EMNLP 2021 paper: It is Not as Good as You Think! Evaluating Simultaneous Machine Translation on Interpretation Data

Pytorch implementation of the paper "Optimization as a Model for Few-Shot Learning"

Measures input lag without dedicated hardware, performing motion detection on recorded or live video

Light-weight network, depth estimation, knowledge distillation, real-time depth estimation, auxiliary data.

Relaxed-machines - explorations in neuro-symbolic differentiable interpreters

use machine learning to recognize gesture on raspberrypi

A tutorial showing how to train, convert, and run TensorFlow Lite object detection models on Android devices, the Raspberry Pi, and more!

Code repository for the paper "Doubly-Trained Adversarial Data Augmentation for Neural Machine Translation" with instructions to reproduce the results.