Object-aware Contrastive Learning for Debiased Scene Representation

Last update: Dec 14, 2022

Overview

Object-aware Contrastive Learning

Official PyTorch implementation of "Object-aware Contrastive Learning for Debiased Scene Representation" by Sangwoo Mo*, Hyunwoo Kang*, Kihyuk Sohn, Chun-Liang Li, and Jinwoo Shin.

Installation

Install required libraries.

pip install -r requirements.txt

Download datasets in /data (e.g., /data/COCO).

Train models

Logs will be saved in logs/{dataset}_{model}_{arch}_b{global_batch_size} directory, where global_batch_size = num_nodes * gpus * batch_size (default batch size = 64 * 4 = 256).

Step 1. Train vanilla models

Train vanilla models (change dataset and ft_datasets as cub or in9).

python pretrain.py --dataset coco --model moco --arch resnet18\
    --ft_datasets coco --batch_size 64 --max_epochs 800

Step 2. Pre-compute CAM masks

Pre-compute bounding boxes for object-aware random crop.

python inference.py --mode save_box --model moco --arch resnet18\
    --ckpt_name coco_moco_r18_b256 --dataset coco\
    --expand_res 2 --cam_iters 10 --apply_crf\
    --save_path data/boxes/coco_cam-r18.txt

Pre-compute masks for background mixup.

python inference.py --mode save_mask --model moco --arch resnet18\
    --ckpt_name in9_moco_r18_256 --dataset in9\
    --expand_res 1 --cam_iters 1\
    --save_path data/masks/in9_cam-r18

Step 3. Re-train debiased models

Train contextual debiased model with object-aware random crop.

python pretrain.py --dataset coco-box-cam-r18 --model moco --arch resnet18\
     --ft_datasets coco --batch_size 64 --max_epochs 800

Train background debiased model with background mixup.

python pretrain.py --dataset in9-mask-cam-r18 --model moco_bgmix --arch resnet18\
    --ft_datasets in9 --batch_size 64 --max_epochs 800

Evaluate models

Linear evaluation

python inference.py --mode lineval --model moco --arch resnet18\
    --ckpt_name coco_moco_r18_b256 --dataset coco

Object localization

python inference.py --mode seg --model moco --arch resnet18\
    --ckpt_name cub200_moco_r18_b256 --dataset cub200\
    --expand_res 2 --cam_iters 10 --apply_crf

Detection & Segmentation (fine-tuning)

mv detection
python convert-pretrain-to-detectron2.py coco_moco_r50.pth coco_moco_r50.pkl
python train_net.py --config-file configs/coco_R_50_C4_2x_moco.yaml --num-gpus 8\
    MODEL.WEIGHTS weights/coco_moco_r18.pkl

Object-aware Contrastive Learning for Debiased Scene Representation

Related tags

Overview

Object-aware Contrastive Learning

Installation

Train models

Step 1. Train vanilla models

Step 2. Pre-compute CAM masks

Step 3. Re-train debiased models

Evaluate models

Linear evaluation

Object localization

Detection & Segmentation (fine-tuning)

Owner

CS_Final_Metal_surface_detection - This is a final project for CoderSchool Machine Learning bootcamp on 29/12/2021.

The source code of CVPR17 'Generative Face Completion'.

Real-time VIBE: Frame by Frame Inference of VIBE (Video Inference for Human Body Pose and Shape Estimation)

FCOSR: A Simple Anchor-free Rotated Detector for Aerial Object Detection

A C implementation for creating 2D voronoi diagrams

PyTorch implementation of Wide Residual Networks with 1-bit weights by McDonnell (ICLR 2018)

A Data Annotation Tool for Semantic Segmentation, Object Detection and Lane Line Detection.(In Development Stage)

CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation

Research code of ICCV 2021 paper "Mesh Graphormer"

Basics of 2D and 3D Human Pose Estimation.

Deep learning image registration library for PyTorch

Motion planning algorithms commonly used on autonomous vehicles. (path planning + path tracking)

Streamlit app demonstrating an image browser for the Udacity self-driving-car dataset with realtime object detection using YOLO.

1st Solution For NeurIPS 2021 Competition on ML4CO Dual Task

TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks

Official implementation of the paper ``Unifying Nonlocal Blocks for Neural Networks'' (ICCV'21)

Python Jupyter kernel using Poetry for reproducible notebooks

An auto discord account and token generator. Automatically verifies the phone number. Works without proxy. Bypasses captcha.

Official code of Team Yao at Multi-Modal-Fact-Verification-2022

The first public PyTorch implementation of Attentive Recurrent Comparators