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

The authors' implementation of Unsupervised Adversarial Learning of 3D Human Pose from 2D Joint Locations

PyTorch code accompanying the paper "Landmark-Guided Subgoal Generation in Hierarchical Reinforcement Learning" (NeurIPS 2021).

Must-read Papers on Physics-Informed Neural Networks.

DiscoNet: Learning Distilled Collaboration Graph for Multi-Agent Perception [NeurIPS 2021]

MobileNetV1-V2，MobileNeXt，GhostNet，AdderNet，ShuffleNetV1-V2，Mobile+ViT etc.

Free Book about Deep-Learning approaches for Chess (like AlphaZero, Leela Chess Zero and Stockfish NNUE)

Dynamic hair modeling from monocular videos using deep neural networks

The Official PyTorch Implementation of DiscoBox.

Uni-Fold: Training your own deep protein-folding models

phylotorch-bito is a package providing an interface to BITO for phylotorch

Awesome Artificial Intelligence, Machine Learning and Deep Learning as we learn it

Code for paper 'Hand-Object Contact Consistency Reasoning for Human Grasps Generation' at ICCV 2021

FAVD: Featherweight Assisted Vulnerability Discovery

Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated Semantics

NLP From Scratch Without Large-Scale Pretraining: A Simple and Efficient Framework

Bunch of different tools which helps visualizing and annotating images for semantic/instance segmentation tasks

Ros2-voiceroid2 - ROS2 wrapper package of VOICEROID2

automated systems to assist guarding corona Virus precautions for Closed Rooms (e.g. Halls, offices, etc..)

Evolutionary Population Curriculum for Scaling Multi-Agent Reinforcement Learning

Simple Tensorflow implementation of Toward Spatially Unbiased Generative Models (ICCV 2021)