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

This repository contains the source codes for the paper AtlasNet V2 - Learning Elementary Structures.

CondNet: Conditional Classifier for Scene Segmentation

Pytorch implementation of the paper: "SAPNet: Segmentation-Aware Progressive Network for Perceptual Contrastive Image Deraining"

LaneAF: Robust Multi-Lane Detection with Affinity Fields

Self-Supervised Generative Style Transfer for One-Shot Medical Image Segmentation

Migration of Edge-based Distributed Federated Learning

Scribble-Supervised LiDAR Semantic Segmentation, CVPR 2022 (ORAL)

TipToiDog - Tip Toi Dog With Python

A CROSS-MODAL FUSION NETWORK BASED ON SELF-ATTENTION AND RESIDUAL STRUCTURE FOR MULTIMODAL EMOTION RECOGNITION

Few-shot Neural Architecture Search

Multi-agent reinforcement learning algorithm and environment

On the model-based stochastic value gradient for continuous reinforcement learning

Visual Memorability for Robotic Interestingness via Unsupervised Online Learning (ECCV 2020 Oral and TRO)

Rethinking Portrait Matting with Privacy Preserving

A library for differentiable nonlinear optimization.

BLEND: A Fast, Memory-Efficient, and Accurate Mechanism to Find Fuzzy Seed Matches

Azua - build AI algorithms to aid efficient decision-making with minimum data requirements.

Code for "ATISS: Autoregressive Transformers for Indoor Scene Synthesis", NeurIPS 2021

The code repository for "PyCIL: A Python Toolbox for Class-Incremental Learning" in PyTorch.

A big endian Gentoo port developed on a Pine64.org RockPro64