Code for paper [ACE: Ally Complementary Experts for Solving Long-Tailed Recognition in One-Shot] (ICCV 2021, oral))

Last update: May 09, 2022

Related tags

Overview

ACE: Ally Complementary Experts for Solving Long-Tailed Recognition in One-Shot

This repository is the official PyTorch implementation of ICCV-21 paper ACE: Ally Complementary Experts for Solving Long-Tailed Recognition in One-Shot.

Prerequirements

To install the environment.

conda env create -f environment.yml
conda activate ACE
git clone https://github.com/NVIDIA/apex
cd apex
pip install -v --disable-pip-version-check --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" ./

Data format

The annotation of a dataset is a dict consisting of two field: annotations and num_classes. The field annotations is a list of dict with image_id, fpath, im_height, im_width and category_id.

Here is an example.

{
    'annotations': [
                    {
                        'image_id': 1,
                        'fpath': '/data/iNat18/images/train_val2018/Plantae/7477/3b60c9486db1d2ee875f11a669fbde4a.jpg',
                        'im_height': 600,
                        'im_width': 800,
                        'category_id': 7477
                    },
                    ...
                   ]
    'num_classes': 8142
}

Usage

Training

#bash data_parallel_train.sh configuration_file_path GPU_indexes
bash data_parallel_train.sh configs/cifar100_im100.yaml 0,1

Testing

#python valid.py configuration_file_path
python valid.py configs/cifar100_im100.yaml

Trained models

Acknowledgement

This project is developed based on Bag of tricks @AAAI-21, thanks for their works!

Citation

@inproceedings{cai2021ace,
  title={ACE: Ally Complementary Experts for Solving Long-Tailed Recognition in One-Shot},
  author={Cai, Jiarui and Wang, Yizhou and Hwang, Jenq-Neng},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={112--121},
  year={2021}
}

Code for paper [ACE: Ally Complementary Experts for Solving Long-Tailed Recognition in One-Shot] (ICCV 2021, oral))

Related tags

Overview

ACE: Ally Complementary Experts for Solving Long-Tailed Recognition in One-Shot

Prerequirements

Data format

Usage

Training

Testing

Acknowledgement

Citation

Owner

Jiarui

Implementation of Change-Based Exploration Transfer (C-BET)

Supervised Sliding Window Smoothing Loss Function Based on MS-TCN for Video Segmentation

Official pytorch implement for “Transformer-Based Source-Free Domain Adaptation”

A toolkit for controlling Euro Truck Simulator 2 with python to develop self-driving algorithms.

data/code repository of "C2F-FWN: Coarse-to-Fine Flow Warping Network for Spatial-Temporal Consistent Motion Transfer"

Lacmus is a cross-platform application that helps to find people who are lost in the forest using computer vision and neural networks.

MediaPipe Kullanarak İleri Seviye Bilgisayarla Görü

Hyperbolic Procrustes Analysis Using Riemannian Geometry

Reinforcement learning algorithms in RLlib

EqGAN - Improving GAN Equilibrium by Raising Spatial Awareness

Recreate CenternetV2 based on MMDET.

Enabling Lightweight Fine-tuning for Pre-trained Language Model Compression based on Matrix Product Operators

Semantic segmentation models, datasets and losses implemented in PyTorch.

Autonomous Movement from Simultaneous Localization and Mapping

A lightweight library designed to accelerate the process of training PyTorch models by providing a minimal

Paper Code：A Self-adaptive Weighted Differential Evolution Approach for Large-scale Feature Selection

Official repository for "Intriguing Properties of Vision Transformers" (2021)

Papers about explainability of GNNs

Datasets, Transforms and Models specific to Computer Vision

Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.