Code repo for "FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance Segmentation" (ICCV 2021)

Last update: Dec 17, 2022

Related tags

Overview

FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance Segmentation (ICCV 2021)

This repository contains the implementation of the following paper:

FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance Segmentation
Yuhang Zang,Chen Huang, Chen Change Loy
International Conference on Computer Vision (ICCV), 2021

[arXiv] [Project Page]

Running Environment

This code is based on mmdetection==2.14.0 and mmcv==1.3.9

Installation

Install mmdetection following the official instruction.
Install COCOAPI.

pip install -U 'git+https://github.com/cocodataset/cocoapi.git#subdirectory=PythonAPI'

Init data directory:

mkdir data

Download LVIS data:

|-- data
`-- |-- lvis_v1
    `-- |-- annotations
        |   |-- lvis_v1_train.json
        |   `-- lvis_v1_val.json
        `-- images
            |-- train2017
            |   |-- 000000000009.jpg
            |   |-- 000000000025.jpg
            |   |-- ... 
            `-- val2017
                |-- 000000000139.jpg
                |-- 000000000285.jpg
                |-- ...

Train

./slurm_train.sh <config_file> <work_dir>

Evaluation

./slurm_test.sh <config_file> <checkpoint_path>

Results and models of LVIS v1

Backbone	Lr schd	Sampler	FASA	mask AP	mask APr	mask APc	mask APf	Config	Download
R-50-FPN	24e	Random	×	18.8	1.2	16.3	29.2	config	Google Drive
R-50-FPN	24e	Random	✓	22.2	10.5	20.4	29.4	config	Google Drive

Citation

If you find our work useful for your research, please consider citing the paper

@inproceedings{zang2021fasa,
  title={FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance Segmentation},
  author={Zang, Yuhang and Huang, Chen and Loy, Chen Change},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  year={2021}
}

Contact

If you have any questions, please feel free to contact zang0012 AT ntu.edu.sg

License

This project is open sourced under MIT license.

You might also like...

Code release for ICCV 2021 paper "Anticipative Video Transformer"

Anticipative Video Transformer Ranked first in the Action Anticipation task of the CVPR 2021 EPIC-Kitchens Challenge! (entry: AVT-FB-UT) [project page

123 Dec 13, 2022

(ICCV 2021) Official code of "Dressing in Order: Recurrent Person Image Generation for Pose Transfer, Virtual Try-on and Outfit Editing."

Dressing in Order (DiOr) 👚 [Paper] 👖 [Webpage] 👗 [Running this code] The official implementation of "Dressing in Order: Recurrent Person Image Gene

277 Dec 28, 2022

Official code release for ICCV 2021 paper SNARF: Differentiable Forward Skinning for Animating Non-rigid Neural Implicit Shapes.

235 Dec 26, 2022

Demo code for ICCV 2021 paper "Sensor-Guided Optical Flow"

Sensor-Guided Optical Flow Demo code for "Sensor-Guided Optical Flow", ICCV 2021 This code is provided to replicate results with flow hints obtained f

10 Mar 16, 2022

Code for 'Single Image 3D Shape Retrieval via Cross-Modal Instance and Category Contrastive Learning', ICCV 2021

CMIC-Retrieval Code for Single Image 3D Shape Retrieval via Cross-Modal Instance and Category Contrastive Learning. ICCV 2021. Introduction In this wo

42 Nov 17, 2022

Code for ICCV 2021 paper "HuMoR: 3D Human Motion Model for Robust Pose Estimation"

367 Dec 24, 2022

Code for the ICCV 2021 Workshop paper: A Unified Efficient Pyramid Transformer for Semantic Segmentation.

Unified-EPT Code for the ICCV 2021 Workshop paper: A Unified Efficient Pyramid Transformer for Semantic Segmentation. Installation Linux, CUDA=10.0,

29 Aug 23, 2022

This repo includes our code for evaluating and improving transferability in domain generalization (NeurIPS 2021)

Transferability for domain generalization This repo is for evaluating and improving transferability in domain generalization (NeurIPS 2021), based on

9 Nov 29, 2022

Official code release for "Learned Spatial Representations for Few-shot Talking-Head Synthesis" ICCV 2021

16 Oct 5, 2022

Comments

AP Fixed, AP pooled

Dear Author,

Thank you for the great paper and nice repository! I wanted to ask about AP pooled and AP fixed, that you mentioned in the supplementary material, how did you implement this? I think mmdet does not officially support this and I was wondering if you could share the code in this repo.

opened by kostas1515 0
About the Adaptive Feature Sampling

Dear author, thanks for your excellent work. I have some questions about the Adaptive Feature Sampling strategy in your paper. When train the LVIS dataset, you mentioned that the per-class sampling probability pc is adjusted by the classification loss on the val set. And you report your experimental results on val set too. I wonder if I understand this idea wrong or we must obtain the LVIS val set during the training stage ? (not split a validation set from the train set but directly use the val set) Looking forward to your reply, thanks!

opened by waveboo 0

Code repo for "FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance Segmentation" (ICCV 2021)

Related tags

Overview

FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance Segmentation (ICCV 2021)

Running Environment

Installation

Train

Evaluation

Results and models of LVIS v1

Citation

Contact

License

You might also like...

Code release for ICCV 2021 paper "Anticipative Video Transformer"

(ICCV 2021) Official code of "Dressing in Order: Recurrent Person Image Generation for Pose Transfer, Virtual Try-on and Outfit Editing."

Official code release for ICCV 2021 paper SNARF: Differentiable Forward Skinning for Animating Non-rigid Neural Implicit Shapes.

Demo code for ICCV 2021 paper "Sensor-Guided Optical Flow"

Code for 'Single Image 3D Shape Retrieval via Cross-Modal Instance and Category Contrastive Learning', ICCV 2021

Code for ICCV 2021 paper "HuMoR: 3D Human Motion Model for Robust Pose Estimation"

Code for the ICCV 2021 Workshop paper: A Unified Efficient Pyramid Transformer for Semantic Segmentation.

This repo includes our code for evaluating and improving transferability in domain generalization (NeurIPS 2021)

Official code release for "Learned Spatial Representations for Few-shot Talking-Head Synthesis" ICCV 2021

Comments

AP Fixed, AP pooled

About the Adaptive Feature Sampling

Owner

Yuhang Zang

Code for "Human Pose Regression with Residual Log-likelihood Estimation", ICCV 2021 Oral

Code for ICCV 2021 paper "Distilling Holistic Knowledge with Graph Neural Networks"

code for ICCV 2021 paper 'Generalized Source-free Domain Adaptation'

Code for ICCV 2021 paper: ARAPReg: An As-Rigid-As Possible Regularization Loss for Learning Deformable Shape Generators..

Code for the ICCV 2021 paper "Pixel Difference Networks for Efficient Edge Detection" (Oral).

Sync2Gen Code for ICCV 2021 paper: Scene Synthesis via Uncertainty-Driven Attribute Synchronization

[ICCV 2021] Released code for Causal Attention for Unbiased Visual Recognition

Code Release for ICCV 2021 (oral), "AdaFit: Rethinking Learning-based Normal Estimation on Point Clouds"

Code for the paper "Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds" (ICCV 2021)

Official PyTorch code of DeepPanoContext: Panoramic 3D Scene Understanding with Holistic Scene Context Graph and Relation-based Optimization (ICCV 2021 Oral).