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

Official Pytorch implementation of the paper: "Locally Shifted Attention With Early Global Integration"

Model Zoo for AI Model Efficiency Toolkit

Code for the paper titled "Generalized Depthwise-Separable Convolutions for Adversarially Robust and Efficient Neural Networks" (NeurIPS 2021 Spotlight).

(NeurIPS 2020) Wasserstein Distances for Stereo Disparity Estimation

Pytorch implementation of PTNet for high-resolution and longitudinal infant MRI synthesis

Car Price Predictor App used to predict the price of the car based on certain input parameters created using python's scikit-learn, fastapi, numpy and joblib packages.

3D Avatar Lip Syncronization from speech (JALI based face-rigging)

PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation

Modified prey-predator system - Modified prey–predator model describes the rate of change for each species by adding coupling terms.

A library for answering questions using data you cannot see

Predict multi paths to a moving person depending on his trajectory history.

A Dying Light 2 (DL2) PAKFile Utility for Modders and Mod Makers.

Implementation of Memory-Efficient Neural Networks with Multi-Level Generation, ICCV 2021

PyTorch implementation of "Representing Shape Collections with Alignment-Aware Linear Models" paper.

Label-Free Model Evaluation with Semi-Structured Dataset Representations

An Active Automata Learning Library Written in Python

Rendering color and depth images for ShapeNet models.

Source code to accompany Defunctland's video "FASTPASS: A Complicated Legacy"

Deep-Learning-Image-Captioning - Implementing convolutional and recurrent neural networks in Keras to generate sentence descriptions of images

A collection of resources and papers on Diffusion Models, a darkhorse in the field of Generative Models