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

DrWhy is the collection of tools for eXplainable AI (XAI). It's based on shared principles and simple grammar for exploration, explanation and visualisation of predictive models.

Prototypical python implementation of the trust-region algorithm presented in Sequential Linearization Method for Bound-Constrained Mathematical Programs with Complementarity Constraints by Larson, Leyffer, Kirches, and Manns.

Open source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI & Research

An end-to-end machine learning library to directly optimize AUC loss

💊 A 3D Generative Model for Structure-Based Drug Design (NeurIPS 2021)

Extreme Lightwegith Portrait Segmentation

Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!

TensorRT examples (Jetson, Python/C++)(object detection)

Code release for Local Light Field Fusion at SIGGRAPH 2019

Bald-to-Hairy Translation Using CycleGAN

基于Flask开发后端、VUE开发前端框架，在WEB端部署YOLOv5目标检测模型

Deep Semisupervised Multiview Learning With Increasing Views (IEEE TCYB 2021, PyTorch Code)

Generate pixel-style avatars with python.

Official codes: Self-Supervised Learning by Estimating Twin Class Distribution

Exploration-Exploitation Dilemma Solving Methods

NFT-Price-Prediction-CNN - Using visual feature extraction, prices of NFTs are predicted via CNN (Alexnet and Resnet) architectures.

CAST: Character labeling in Animation using Self-supervision by Tracking

The Surprising Effectiveness of Visual Odometry Techniques for Embodied PointGoal Navigation

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with ONNX, TensorRT, ncnn, and OpenVINO supported.

This is the codebase for Diffusion Models Beat GANS on Image Synthesis.