Implementation of "Distribution Alignment: A Unified Framework for Long-tail Visual Recognition"(CVPR 2021)

Related tags

Deep LearningDisAlign
Overview

Implementation of "Distribution Alignment: A Unified Framework for Long-tail Visual Recognition"(CVPR 2021)

[Paper][Code]

We implement the classification, object detection and instance segmentation tasks based on our cvpods. The users should install cvpods first and run the experiments in this repo.

Changelog

  • 4.23.2021 Update the DisAlign on LVIS v0.5(Mask R-CNN + Res50)
  • 4.12.2021 Update the README

0. How to Use

  • Step-1: Install the latest cvpods.
  • Step-2: cd cvpods
  • Step-3: Prepare dataset for different tasks.
  • Step-4: git clone https://github.com/Megvii-BaseDetection/DisAlign playground_disalign
  • Step-5: Enter one folder and run pods_train --num-gpus 8
  • Step-6: Use pods_test --num-gpus 8 to evaluate the last the checkpoint

1. Image Classification

We support the the following three datasets:

  • ImageNet-LT Dataset
  • iNaturalist-2018 Dataset
  • Place-LT Dataset

We refer the user to CLS_README for more details.

2. Object Detection/Instance Segmentation

We support the two versions of the LVIS dataset:

  • LVIS v0.5
  • LVIS v1.0

Highlight

  1. To speedup the evaluation on LVIS dataset, we provide the C++ optimized evaluation api by modifying the coco_eval(C++) in cvpods.
  • The C++ version lvis_eval API will save ~30% time when calculating the mAP.
  1. We provide support for the metric of AP_fixed and AP_pool proposed in large-vocab-devil
  2. We will support more recent works on long-tail detection in this project(e.g. EQLv2, CenterNet2, etc.) in the future.

We refer the user to DET_README for more details.

3. Semantic Segmentation

We adopt the mmsegmentation as the codebase for runing all experiments of DisAlign. Currently, the user should use DisAlign_Seg for the semantic segmentation experiments. We will add the support for these experiments in cvpods in the future.

Acknowledgement

Thanks for the following projects:

Citing DisAlign

If you are using the DisAlign in your research or with to refer to the baseline results publised in this repo, please use the following BibTex entry.

@inproceedings{zhang2021disalign,
  title={Distribution Alignment: A Unified Framework for Long-tail Visual Recognition.},
  author={Zhang, Songyang and Li, Zeming and Yan, Shipeng and He, Xuming and Sun, Jian},
  booktitle={CVPR},
  year={2021}
}

License

This repo is released under the Apache 2.0 license. Please see the LICENSE file for more information.

Comments
  • scale in cosine classifier

    scale in cosine classifier

    Hi, thanks for your great work! I notice you use the cosine classifier in many experiments and it can get a better baseline. The formula is as follows

    image

    I am wondering the value of s?

    opened by L1aoXingyu 5
  •  Is it correct to freeze the weight and bias of the DisAlign Linear Layer as well?

    Is it correct to freeze the weight and bias of the DisAlign Linear Layer as well?

    Hello. Thank you for your project! I'm testing your code on my custom dataset. My task is classification. I have a question about your code implementation.

    https://github.com/Megvii-BaseDetection/DisAlign/blob/a2fc3500a108cb83e3942293a5675c97ab3a2c6e/classification/imagenetlt/resnext50/resx50.scratch.imagenet_lt.224size.90e.disalign.10e/net.py#L56-L62

    From my understanding, in stage 2, remove the linear layer used in stage 1 and add DisAlign Linear Layer. And freeze all parts except for logit_scale, logit_bias, and confidence_layer. At this time, the weight and bias of DisAlignLinear are also frozen. (self.weight, self.bias) Is my understanding correct?

    If so, are the weight and bias of DisAlignLinearLayer fixed after the initialization? (The weight and bias of the linear layer in stage 1 are not copied either)

    If my understanding is correct, why is the weight of DisAlignLinear also frozen?

    I will wait for your reply. thanks!

    opened by jeongHwarr 4
  • Where is the DisAlignLinear module?

    Where is the DisAlignLinear module?

    Hello. Thank you for your impressive project!

    I want to apply DisAlign to classification. However, an error occurs in the import part. https://github.com/Megvii-BaseDetection/DisAlign/blob/a2fc3500a108cb83e3942293a5675c97ab3a2c6e/classification/imagenetlt/resnext50/resx50.scratch.imagenet_lt.224size.90e.disalign.10e/net.py#L7 I coudn't find the DisAlignLinear in cvpods.layers. and there also isn't exist at https://github.com/Megvii-BaseDetection/cvpods/tree/master/cvpods/layers How can I solve this problem?

    Thank you!

    opened by jeongHwarr 4
  • Can someone kindly share their codes of Classification task on ImageNet_LT?

    Can someone kindly share their codes of Classification task on ImageNet_LT?

    I tried to train the proposed method on ImageNet_LT, but I can only get an average testing rate about 49%, which is far from the rate described in the paper (52.9). Some of the details regarding my implementations are given as follows: (1) The feature extractor is ResNexT-50 and the head classifier is a linear classifier. The testing accuracy in Stage-One is 43.9%, which is OK.

    (2) The testing accuracy of adopting cRT method in Stage-Two is 49.6%, which is identical to one reported in other papers. (3) When fine-tuning the model in Stage-2, both the feature-extractor and head classifier are frozen, and a DisAliLinear model (which is implemented in CVPODs) is retrained. The testing accuracy can only reach 48.8%, which is far away from the one reported in your paper.

    opened by smallcube 4
  • The code for semantic segmentation is missing

    The code for semantic segmentation is missing

    Hi, thank you for the nice work, but the code for semantic segmentation is missing and the URL for it in the README could not be opened. Could you please fix this issue?

    opened by curiosity654 3
  • About the reference Distribution p_r in Eq. (10)

    About the reference Distribution p_r in Eq. (10)

    Hi, Thank you for providing your code. Here I was wondering the Equation (10) in your paper (The definition of p_r), which seems not to be a distribution. Since every x_i can only have one label, the reference distribution p_r(y| x_i) will be the distribution like (0, 0, 0,...,w_c, 0, 0,...,0). And the sum of this distribution is w_c, but not 1.

    Could you help me understand this equation? Thanks in advance.

    opened by Kevinz-code 3
  • import error

    import error

    Hi, thanks for the great work. Maybe I missed it, but it seems that the code for this project has been incorporated into cvpods. I couldn't launch any experiments due to ImportErrors like: from cvpods.layers import DisAlignLinear ImportError: cannot import name 'DisAlignLinear' from 'cvpods.layers' Also, I didn't find the corresponding functions in cvpods.

    Any help will be appreciated. Thanks.

    opened by YUE-FAN 2
  • about the confidence score σ(x)

    about the confidence score σ(x)

    In the paper, the σ(x) is implemented as a linear layer followed by a non-linear activation function (e.g., sigmoid function) for all input x. How to understand the input x?the matrix of raw iamge, or the extracted features, even or cls_score? Thank you!

    opened by lzed2399 2
  • exp_reweight = exp_reweight / np.sum(exp_reweight) * num_foreground

    exp_reweight = exp_reweight / np.sum(exp_reweight) * num_foreground

    Dear author, I have some questions about the code and paper:

    1. exp_reweight = exp_reweight / np.sum(exp_reweight) * num_foreground Why "exp_reweight" is multiplied by the coefficient "num_foreground"? It is not mentioned in the paper.
    2. Is "K" in the empirical class frequencies r = [r1, · · · , rK] on the training set in the paper the same as the class number C of the training set?
    opened by Liu-wanbing 2
  • The DisAlign_Seg page can't open

    The DisAlign_Seg page can't open

    opened by Kittywyk 1
  • Do you use validation dataset?

    Do you use validation dataset?

    https://github.com/Megvii-BaseDetection/DisAlign/blob/main/classification/imagenetlt/resnext50/resx50.scratch.imagenet_lt.224size.90e.disalign.10e/config.py#L31

    It seems that you only use test dataset? What is the reason for that?

    opened by qianlanwyd 1
  • How can I test and augtest the trained semseg DisAlign model?

    How can I test and augtest the trained semseg DisAlign model?

    opened by jh151170 0
  • the code question in semantic_seg

    the code question in semantic_seg

    Hi, I have a questation about the logit_scale and logit_bias in semantic_seg. The shape of the above parameter is (1, num_classes, 1, 1), why not is (1, num_classes, 512, 512) which is matched the input image size for semantic segmenation.

    opened by Ianresearch 8
  • Value of the learned scale and bias vector?

    Value of the learned scale and bias vector?

    Hi, did you check the value change of the learned scale and bias vector throughout the training process? I find the value of them change in the first few iterations and remain stable in the rest time on my own classification dataset. I wonder how the learned vectors look like in your paper? Thanks!

    opened by Jacobew 1
Owner
BaseDetection Team of Megvii
A fast Protein Chain / Ligand Extractor and organizer.

Are you tired of using visualization software, or full blown suites just to separate protein chains / ligands ? Are you tired of organizing the mess o

Amine Abdz 9 Nov 06, 2022
Unofficial PyTorch implementation of Google AI's VoiceFilter system

VoiceFilter Note from Seung-won (2020.10.25) Hi everyone! It's Seung-won from MINDs Lab, Inc. It's been a long time since I've released this open-sour

MINDs Lab 883 Jan 07, 2023
Node for thenewboston digital currency network.

Project setup For project setup see INSTALL.rst Community Join the community to stay updated on the most recent developments, project roadmaps, and ra

thenewboston 27 Jul 08, 2022
Paddle Graph Learning (PGL) is an efficient and flexible graph learning framework based on PaddlePaddle

DOC | Quick Start | 中文 Breaking News !! 🔥 🔥 🔥 OGB-LSC KDD CUP 2021 winners announced!! (2021.06.17) Super excited to announce our PGL team won TWO

1.5k Jan 06, 2023
Replication Code for "Self-Supervised Bug Detection and Repair" NeurIPS 2021

Self-Supervised Bug Detection and Repair This is the reference code to replicate the research in Self-Supervised Bug Detection and Repair in NeurIPS 2

Microsoft 85 Dec 24, 2022
Unicorn can be used for performance analyses of highly configurable systems with causal reasoning

Unicorn can be used for performance analyses of highly configurable systems with causal reasoning. Users or developers can query Unicorn for a performance task.

AISys Lab 27 Jan 05, 2023
[Preprint] ConvMLP: Hierarchical Convolutional MLPs for Vision, 2021

Convolutional MLP ConvMLP: Hierarchical Convolutional MLPs for Vision Preprint link: ConvMLP: Hierarchical Convolutional MLPs for Vision By Jiachen Li

SHI Lab 143 Jan 03, 2023
Implementing SYNTHESIZER: Rethinking Self-Attention in Transformer Models using Pytorch

Implementing SYNTHESIZER: Rethinking Self-Attention in Transformer Models using Pytorch Reference Paper URL Author: Yi Tay, Dara Bahri, Donald Metzler

Myeongjun Kim 66 Nov 30, 2022
Code and Data for the paper: Molecular Contrastive Learning with Chemical Element Knowledge Graph [AAAI 2022]

Knowledge-enhanced Contrastive Learning (KCL) Molecular Contrastive Learning with Chemical Element Knowledge Graph [ AAAI 2022 ]. We construct a Chemi

Fangyin 58 Dec 26, 2022
Where2Act: From Pixels to Actions for Articulated 3D Objects

Where2Act: From Pixels to Actions for Articulated 3D Objects The Proposed Where2Act Task. Given as input an articulated 3D object, we learn to propose

Kaichun Mo 69 Nov 28, 2022
A general-purpose programming language, focused on simplicity, safety and stability.

The Rivet programming language A general-purpose programming language, focused on simplicity, safety and stability. Rivet's goal is to be a very power

The Rivet programming language 17 Dec 29, 2022
Align before Fuse: Vision and Language Representation Learning with Momentum Distillation

This is the official PyTorch implementation of the ALBEF paper [Blog]. This repository supports pre-training on custom datasets, as well as finetuning on VQA, SNLI-VE, NLVR2, Image-Text Retrieval on

Salesforce 805 Jan 09, 2023
MCMC samplers for Bayesian estimation in Python, including Metropolis-Hastings, NUTS, and Slice

Sampyl May 29, 2018: version 0.3 Sampyl is a package for sampling from probability distributions using MCMC methods. Similar to PyMC3 using theano to

Mat Leonard 304 Dec 25, 2022
A geometric deep learning pipeline for predicting protein interface contacts.

A geometric deep learning pipeline for predicting protein interface contacts.

44 Dec 30, 2022
AOT (Associating Objects with Transformers) in PyTorch

An efficient modular implementation of Associating Objects with Transformers for Video Object Segmentation in PyTorch

162 Dec 14, 2022
AVD Quickstart Containerlab

AVD Quickstart Containerlab WARNING This repository is still under construction. It's fully functional, but has number of limitations. For example: RE

Carl Buchmann 3 Apr 10, 2022
ISNAS-DIP: Image Specific Neural Architecture Search for Deep Image Prior [CVPR 2022]

ISNAS-DIP: Image-Specific Neural Architecture Search for Deep Image Prior (CVPR 2022) Metin Ersin Arican*, Ozgur Kara*, Gustav Bredell, Ender Konukogl

Özgür Kara 24 Dec 18, 2022
Probabilistic Entity Representation Model for Reasoning over Knowledge Graphs

Implementation for the paper: Probabilistic Entity Representation Model for Reasoning over Knowledge Graphs, Nurendra Choudhary, Nikhil Rao, Sumeet Ka

Nurendra Choudhary 8 Nov 15, 2022
KIND: an Italian Multi-Domain Dataset for Named Entity Recognition

KIND (Kessler Italian Named-entities Dataset) KIND is an Italian dataset for Named-Entity Recognition. It contains more than one million tokens with t

Digital Humanities 5 Jun 21, 2022
An optimization and data collection toolbox for convenient and fast prototyping of computationally expensive models.

An optimization and data collection toolbox for convenient and fast prototyping of computationally expensive models. Hyperactive: is very easy to lear

Simon Blanke 422 Jan 04, 2023