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

Discerning Decision-Making Process of Deep Neural Networks with Hierarchical Voting Transformation

Multiple-criteria decision-making (MCDM) with Electre, Promethee, Weighted Sum and Pareto

Implementation of the Triangle Multiplicative module, used in Alphafold2 as an efficient way to mix rows or columns of a 2d feature map, as a standalone package for Pytorch

The first public PyTorch implementation of Attentive Recurrent Comparators

OntoProtein: Protein Pretraining With Ontology Embedding

[NeurIPS 2021] Well-tuned Simple Nets Excel on Tabular Datasets

LexGLUE: A Benchmark Dataset for Legal Language Understanding in English

Keras-retinanet - Keras implementation of RetinaNet object detection.

Decorator for PyMC3

A lightweight library to compare different PyTorch implementations of the same network architecture.

This is the code for Compressing BERT: Studying the Effects of Weight Pruning on Transfer Learning

we propose a novel deep network, named feature aggregation and refinement network (FARNet), for the automatic detection of anatomical landmarks.

Package for working with hypernetworks in PyTorch.

NVIDIA container runtime

Little Ball of Fur - A graph sampling extension library for NetworKit and NetworkX (CIKM 2020)

This is project is the implementation of the DeepShift: Towards Multiplication-Less Neural Networks paper

code for our BMVC 2021 paper "HCV: Hierarchy-Consistency Verification for Incremental Implicitly-Refined Classification"

Posterior predictive distributions quantify uncertainties ignored by point estimates.

Hardware-accelerated DNN model inference ROS2 packages using NVIDIA Triton/TensorRT for both Jetson and x86_64 with CUDA-capable GPU

Jittor implementation of PCT:Point Cloud Transformer