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

Homepage of paper: Paint Transformer: Feed Forward Neural Painting with Stroke Prediction, ICCV 2021.

[KDD 2021, Research Track] DiffMG: Differentiable Meta Graph Search for Heterogeneous Graph Neural Networks

Learning recognition/segmentation models without end-to-end training. 40%-60% less GPU memory footprint. Same training time. Better performance.

Scripts used to make and evaluate OpenAlex's concept tagging model

PyTorch inference for "Progressive Growing of GANs" with CelebA snapshot

Deconfounding Temporal Autoencoder: Estimating Treatment Effects over Time Using Noisy Proxies

[BMVC2021] "TransFusion: Cross-view Fusion with Transformer for 3D Human Pose Estimation"

Lua-parser-lark - An out-of-box Lua parser written in Lark

Physics-Aware Training (PAT) is a method to train real physical systems with backpropagation.

Face recognize and crop them

This repository contains the code, data, and models of the paper titled "XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages" published in Findings of the Association for Computational Linguistics: ACL 2021.

Beancount-mercury - Beancount importer for Mercury Startup Checking

A library for differentiable nonlinear optimization.

A Python library for common tasks on 3D point clouds

Six - a Python 2 and 3 compatibility library

Official implementation for "Symbolic Learning to Optimize: Towards Interpretability and Scalability"

[CVPR'21] DeepSurfels: Learning Online Appearance Fusion

Tensorflow 2.x implementation of Vision-Transformer model

Deep GPs built on top of TensorFlow/Keras and GPflow

Exploring Machine Learning Models for detecting anomalous behavior in credit-card transactions. It's crucial that credit-card companies are able to recognize fraudulent activity so that customers are not charged for items they didn't purchase.