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

"Reinforcement Learning for Bandit Neural Machine Translation with Simulated Human Feedback"

Yolov5-lite - Minimal PyTorch implementation of YOLOv5

This repository contains the source code and data for reproducing results of Deep Continuous Clustering paper

Code for paper Adaptively Aligned Image Captioning via Adaptive Attention Time

Image process framework based on plugin like imagej, it is esay to glue with scipy.ndimage, scikit-image, opencv, simpleitk, mayavi...and any libraries based on numpy

Lightweight Python library for adding real-time object tracking to any detector.

HandTailor: Towards High-Precision Monocular 3D Hand Recovery

DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models

DeepStochlog Package For Python

RuDOLPH: One Hyper-Modal Transformer can be creative as DALL-E and smart as CLIP

Code for ACL'2021 paper WARP 🌀 Word-level Adversarial ReProgramming

Interpretable and Generalizable Person Re-Identification with Query-Adaptive Convolution and Temporal Lifting

Context-Sensitive Misspelling Correction of Clinical Text via Conditional Independence, CHIL 2022

Distilling Motion Planner Augmented Policies into Visual Control Policies for Robot Manipulation (CoRL 2021)

Space Invaders For Python

docTR by Mindee (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning.

IJON is an annotation mechanism that analysts can use to guide fuzzers such as AFL.

Python library for loading and using triangular meshes.

Repository for GNSS-based position estimation using a Deep Neural Network

This repository contains code and data for "On the Multimodal Person Verification Using Audio-Visual-Thermal Data"