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

ONNX-PackNet-SfM: Python scripts for performing monocular depth estimation using the PackNet-SfM model in ONNX

CMUA-Watermark: A Cross-Model Universal Adversarial Watermark for Combating Deepfakes (AAAI2022)

GNN-based Recommendation Benchmark

Tutorial on active learning with the Nvidia Transfer Learning Toolkit (TLT).

ColBERT: Contextualized Late Interaction over BERT (SIGIR'20)

Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes

A small library for doing fluid simulation with neural networks.

Neural Factorization of Shape and Reflectance Under An Unknown Illumination

Fedlearn支持前沿算法研发的Python工具库 | Fedlearn algorithm toolkit for researchers

Self-Supervised depth kalilia

The official code for paper "R2D2: Recursive Transformer based on Differentiable Tree for Interpretable Hierarchical Language Modeling".

The implementation for the SportsCap (IJCV 2021)

FCN (Fully Convolutional Network) is deep fully convolutional neural network architecture for semantic pixel-wise segmentation

Dual Attention Network for Scene Segmentation (CVPR2019)

Self-supervised learning on Graph Representation Learning (node-level task)

Info and sample codes for "NTU RGB+D Action Recognition Dataset"

Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bank

pcnaDeep integrates cutting-edge detection techniques with tracking and cell cycle resolving models.

(JMLR'19) A Python Toolbox for Scalable Outlier Detection (Anomaly Detection)

SoGCN: Second-Order Graph Convolutional Networks