Wider or Deeper: Revisiting the ResNet Model for Visual Recognition

Overview

ademxapp

Visual applications by the University of Adelaide

In designing our Model A, we did not over-optimize its structure for efficiency unless it was neccessary, which led us to a high-performance model without non-trivial building blocks. Besides, by doing so, we anticipate this model and its trivial variants to perform well when they are finetuned for new tasks, considering their better spatial efficiency and larger model sizes compared to conventional ResNet models.

In this work, we try to find a proper depth for ResNets, without grid-searching the whole space, especially when it is too costly to do so, e.g., on the ILSVRC 2012 classification dataset. For more details, refer to our report: Wider or Deeper: Revisiting the ResNet Model for Visual Recognition.

This code is a refactored version of the one that we used in the competition, and has not yet been tested extensively, so feel free to open an issue if you find any problem.

To use, first install MXNet.

Updates

  • Recent updates
    • Model A1 trained on Cityscapes
    • Model A1 trained on VOC
    • Training code for semantic image segmentation
    • Training code for image classification on ILSVRC 2012 (Still needs to be evaluated.)
  • History
    • Results on VOC using COCO for pre-training
    • Fix the bug in testing resulted from changing the EPS in BatchNorm layers
    • Model A1 for ADE20K trained using the train set with testing code
    • Segmentation results with multi-scale testing on VOC and Cityscapes
    • Model A and Model A1 for ILSVRC with testing code
    • Segmentation results with single-scale testing on VOC and Cityscapes

Image classification

Pre-trained models

  1. Download the ILSVRC 2012 classification val set 6.3GB, and put the extracted images into the directory:

    data/ilsvrc12/ILSVRC2012_val/
    
  2. Download the models as below, and put them into the directory:

    models/
    
  3. Check the classification performance of pre-trained models on the ILSVRC 2012 val set:

    python iclass/ilsvrc.py --data-root data/ilsvrc12 --output output --batch-images 10 --phase val --weights models/ilsvrc-cls_rna-a_cls1000_ep-0001.params --split val --test-scales 320 --gpus 0 --no-choose-interp-method --pool-top-infer-style caffe
    
    python iclass/ilsvrc.py --data-root data/ilsvrc12 --output output --batch-images 10 --phase val --weights models/ilsvrc-cls_rna-a1_cls1000_ep-0001.params --split val --test-scales 320 --gpus 0 --no-choose-interp-method

Results on the ILSVRC 2012 val set tested with a single scale (320, without flipping):

model|top-1 error (%)|top-5 error (%)|download
:---:|:---:|:---:|:---:
[Model A](https://cdn.rawgit.com/itijyou/ademxapp/master/misc/ilsvrc_model_a.pdf)|19.20|4.73|[aar](https://cloudstor.aarnet.edu.au/plus/index.php/s/V7dncO4H0ijzeRj)
[Model A1](https://cdn.rawgit.com/itijyou/ademxapp/master/misc/ilsvrc_model_a1.pdf)|19.54|4.75|[aar](https://cloudstor.aarnet.edu.au/plus/index.php/s/NOPhJ247fhVDnZH)

Note: Due to a change of MXNet in padding at pooling layers, some of the computed feature maps in Model A will have different sizes from those stated in our report. However, this has no effect on Model A1, which always uses convolution layers (instead of pooling layers) for down-sampling. So, in most cases, just use Model A1, which was initialized from Model A, and tuned for 45k extra iterations.

New models

  1. Find a machine with 4 devices, each with at least 11G memories.

  2. Download the ILSVRC 2012 classification train set 138GB, and put the extracted images into the directory:

    data/ilsvrc12/ILSVRC2012_train/
    

    with the following structure:

    ILSVRC2012_train
    |-- n01440764
    |-- n01443537
    |-- ...
    `-- n15075141
    
  3. Train a new Model A from scratch, and check its performance:

    python iclass/ilsvrc.py --gpus 0,1,2,3 --data-root data/ilsvrc12 --output output --model ilsvrc-cls_rna-a_cls1000 --batch-images 256 --crop-size 224 --lr-type linear --base-lr 0.1 --to-epoch 90 --kvstore local --prefetch-threads 8 --prefetcher process --backward-do-mirror
    
    python iclass/ilsvrc.py --data-root data/ilsvrc12 --output output --batch-images 10 --phase val --weights output/ilsvrc-cls_rna-a_cls1000_ep-0090.params --split val --test-scales 320 --gpus 0
  4. Tune a Model A1 from our released Model A, and check its performance:

    python iclass/ilsvrc.py --gpus 0,1,2,3 --data-root data/ilsvrc12 --output output --model ilsvrc-cls_rna-a1_cls1000_from-a --batch-images 256 --crop-size 224 --weights models/ilsvrc-cls_rna-a_cls1000_ep-0001.params --lr-type linear --base-lr 0.01 --to-epoch 9 --kvstore local --prefetch-threads 8 --prefetcher process --backward-do-mirror
    
    python iclass/ilsvrc.py --data-root data/ilsvrc12 --output output --batch-images 10 --phase val --weights output/model ilsvrc-cls_rna-a1_cls1000_from-a_ep-0009.params --split val --test-scales 320 --gpus 0
  5. Or train a new Model A1 from scratch, and check its performance:

    python iclass/ilsvrc.py --gpus 0,1,2,3 --data-root data/ilsvrc12 --output output --model ilsvrc-cls_rna-a1_cls1000 --batch-images 256 --crop-size 224 --lr-type linear --base-lr 0.1 --to-epoch 90 --kvstore local --prefetch-threads 8 --prefetcher process --backward-do-mirror
    
    python iclass/ilsvrc.py --data-root data/ilsvrc12 --output output --batch-images 10 --phase val --weights output/ilsvrc-cls_rna-a1_cls1000_ep-0090.params --split val --test-scales 320 --gpus 0

It cost more than 40 days on our workstation with 4 Maxwell GTX Titan cards. So, be patient or try smaller models as described in our report.

Note: The best setting (prefetch-threads and prefetcher) for efficiency can vary depending on the circumstances (the provided CPUs, GPUs, and filesystem).

Note: This code may not accurately reproduce our reported results, since there are subtle differences in implementation, e.g., different cropping strategies, interpolation methods, and padding strategies.

Semantic image segmentation

We show the effectiveness of our models (as pre-trained features) by semantic image segmenatation using plain dilated FCNs initialized from our models. Several A1 models tuned on the train set of PASCAL VOC, Cityscapes and ADE20K are available.

  • To use, download and put them into the directory:

    models/
    

PASCAL VOC 2012:

  1. Download the PASCAL VOC 2012 dataset 2GB, and put the extracted images into the directory:

    data/VOCdevkit/VOC2012
    

    with the following structure:

    VOC2012
    |-- JPEGImages
    |-- SegmentationClass
    `-- ...
    
  2. Check the performance of the pre-trained models:

    python issegm/voc.py --data-root data/VOCdevkit --output output --phase val --weights models/voc_rna-a1_cls21_s8_ep-0001.params --split val --test-scales 500 --test-flipping --gpus 0
    
    python issegm/voc.py --data-root data/VOCdevkit --output output --phase val --weights models/voc_rna-a1_cls21_s8_coco_ep-0001.params --split val --test-scales 500 --test-flipping --gpus 0

Results on the val set:

model|training data|testing scale|mean IoU (%)|download
:---|:---:|:---:|:---:|:---:
Model A1, 2 conv.|VOC; SBD|500|80.84|[aar](https://cloudstor.aarnet.edu.au/plus/index.php/s/YqNptRcboMD44Kd)
Model A1, 2 conv.|VOC; SBD; COCO|500|82.86|[aar](https://cloudstor.aarnet.edu.au/plus/index.php/s/JKWePbLPlpfRDW4)

Results on the test set:

model|training data|testing scale|mean IoU (%)
:---|:---:|:---:|:---:
Model A1, 2 conv.|VOC; SBD|500|[82.5](http://host.robots.ox.ac.uk:8080/anonymous/H0KLZK.html)
Model A1, 2 conv.|VOC; SBD|multiple|[83.1](http://host.robots.ox.ac.uk:8080/anonymous/BEWE9S.html)
Model A1, 2 conv.|VOC; SBD; COCO|multiple|[84.9](http://host.robots.ox.ac.uk:8080/anonymous/JU1PXP.html)

Cityscapes:

  1. Download the Cityscapes dataset, and put the extracted images into the directory:

    data/cityscapes
    

    with the following structure:

    cityscapes
    |-- gtFine
    `-- leftImg8bit
    
  2. Clone the official Cityscapes toolkit:

    git clone https://github.com/mcordts/cityscapesScripts.git data/cityscapesScripts
  3. Check the performance of the pre-trained model:

    python issegm/voc.py --data-root data/cityscapes --output output --phase val --weights models/cityscapes_rna-a1_cls19_s8_ep-0001.params --split val --test-scales 2048 --test-flipping --gpus 0
  4. Tune a Model A1, and check its performance:

    python issegm/voc.py --gpus 0,1,2,3 --split train --data-root data/cityscapes --output output --model cityscapes_rna-a1_cls19_s8 --batch-images 16 --crop-size 500 --origin-size 2048 --scale-rate-range 0.7,1.3 --weights models/ilsvrc-cls_rna-a1_cls1000_ep-0001.params --lr-type fixed --base-lr 0.0016 --to-epoch 140 --kvstore local --prefetch-threads 8 --prefetcher process --cache-images 0 --backward-do-mirror
    
    python issegm/voc.py --gpus 0,1,2,3 --split train --data-root data/cityscapes --output output --model cityscapes_rna-a1_cls19_s8_x1-140 --batch-images 16 --crop-size 500 --origin-size 2048 --scale-rate-range 0.7,1.3 --weights output/cityscapes_rna-a1_cls19_s8_ep-0140.params --lr-type linear --base-lr 0.0008 --to-epoch 64 --kvstore local --prefetch-threads 8 --prefetcher process --cache-images 0 --backward-do-mirror
    
    python issegm/voc.py --data-root data/cityscapes --output output --phase val --weights output/cityscapes_rna-a1_cls19_s8_x1-140_ep-0064.params --split val --test-scales 2048 --test-flipping --gpus 0

Results on the val set:

model|training data|testing scale|mean IoU (%)|download
:---|:---:|:---:|:---:|:---:
Model A1, 2 conv.|fine|1024x2048|78.08|[aar](https://cloudstor.aarnet.edu.au/plus/index.php/s/2hbvpro6J4XKVIu)

Results on the test set:

model|training data|testing scale|class IoU (%)|class iIoU (%)| category IoU (%)| category iIoU(%)
:---|:---:|:---:|:---:|:---:|:---:|:---:
Model A2, 2 conv.|fine|1024x2048|78.4|59.1|90.9|81.1
Model A2, 2 conv.|fine|multiple|79.4|58.0|91.0|80.1
Model A2, 2 conv.|fine; coarse|1024x2048|79.9|59.7|91.2|80.8
Model A2, 2 conv.|fine; coarse|multiple|80.6|57.8|91.0|79.1

For more information, refer to the official leaderboard.

Note: Model A2 was initialized from Model A, and tuned for 45k extra iterations using the Places data in ILSVRC 2016.

MIT Scene Parsing Benchmark (ADE20K):

  1. Download the MIT Scene Parsing dataset, and put the extracted images into the directory:

    data/ade20k/
    

    with the following structure:

    ade20k
    |-- annotations
    |   |-- training
    |   `-- validation
    `-- images
        |-- testing
        |-- training
        `-- validation
    
  2. Check the performance of the pre-trained model:

    python issegm/voc.py --data-root data/ade20k --output output --phase val --weights models/ade20k_rna-a1_cls150_s8_ep-0001.params --split val --test-scales 500 --test-flipping --test-steps 2 --gpus 0

Results on the val set:

model|testing scale|pixel accuracy (%)|mean IoU (%)|download
:---|:---:|:---:|:---:|:---:
[Model A1, 2 conv.](https://cdn.rawgit.com/itijyou/ademxapp/master/misc/ade20k_model_a1.pdf)|500|80.55|43.34|[aar](https://cloudstor.aarnet.edu.au/plus/index.php/s/E4JeZpmssK50kpn)

Citation

If you use this code or these models in your research, please cite:

@Misc{word.zifeng.2016,
    author = {Zifeng Wu and Chunhua Shen and Anton van den Hengel},
    title = {Wider or Deeper: {R}evisiting the ResNet Model for Visual Recognition},
    year = {2016}
    howpublished = {arXiv:1611.10080}
}

License

This code is only for academic purpose. For commercial purpose, please contact us.

Acknowledgement

This work is supported with supercomputing resources provided by the PSG cluster at NVIDIA and the Phoenix HPC service at the University of Adelaide.

Owner
Zifeng Wu
Postdoctoral researcher at the University of Adelaide
Zifeng Wu
TensorFlow (Python API) implementation of Neural Style

neural-style-tf This is a TensorFlow implementation of several techniques described in the papers: Image Style Transfer Using Convolutional Neural Net

Cameron 3.1k Jan 02, 2023
[NeurIPS 2021]: Are Transformers More Robust Than CNNs? (Pytorch implementation & checkpoints)

Are Transformers More Robust Than CNNs? Pytorch implementation for NeurIPS 2021 Paper: Are Transformers More Robust Than CNNs? Our implementation is b

Yutong Bai 145 Dec 01, 2022
Official PyTorch implementation of "Improving Face Recognition with Large AgeGaps by Learning to Distinguish Children" (BMVC 2021)

Inter-Prototype (BMVC 2021): Official Project Webpage This repository provides the official PyTorch implementation of the following paper: Improving F

Jungsoo Lee 16 Jun 30, 2022
The openspoor package is intended to allow easy transformation between different geographical and topological systems commonly used in Dutch Railway

Openspoor The openspoor package is intended to allow easy transformation between different geographical and topological systems commonly used in Dutch

7 Aug 22, 2022
CaLiGraph Ontology as a Challenge for Semantic Reasoners ([email protected]'21)

CaLiGraph for Semantic Reasoning Evaluation Challenge This repository contains code and data to use CaLiGraph as a benchmark dataset in the Semantic R

Nico Heist 0 Jun 08, 2022
Advanced Signal Processing Notebooks and Tutorials

Advanced Digital Signal Processing Notebooks and Tutorials Prof. Dr. -Ing. Gerald Schuller Jupyter Notebooks and Videos: Renato Profeta Applied Media

Guitars.AI 115 Dec 13, 2022
Official implementation for paper: A Latent Transformer for Disentangled Face Editing in Images and Videos.

A Latent Transformer for Disentangled Face Editing in Images and Videos Official implementation for paper: A Latent Transformer for Disentangled Face

InterDigital 108 Dec 09, 2022
Sign Language Translation with Transformers (COLING'2020, ECCV'20 SLRTP Workshop)

transformer-slt This repository gathers data and code supporting the experiments in the paper Better Sign Language Translation with STMC-Transformer.

Kayo Yin 107 Dec 27, 2022
RL-GAN: Transfer Learning for Related Reinforcement Learning Tasks via Image-to-Image Translation

RL-GAN: Transfer Learning for Related Reinforcement Learning Tasks via Image-to-Image Translation RL-GAN is an official implementation of the paper: T

42 Nov 10, 2022
Faune proche - Retrieval of Faune-France data near a google maps location

faune_proche Récupération des données de Faune-France près d'un lieu google maps

4 Feb 15, 2022
Camera Distortion-aware 3D Human Pose Estimation in Video with Optimization-based Meta-Learning

Camera Distortion-aware 3D Human Pose Estimation in Video with Optimization-based Meta-Learning This is the official repository of "Camera Distortion-

Hanbyel Cho 12 Oct 06, 2022
Code and experiments for "Deep Neural Networks for Rank Consistent Ordinal Regression based on Conditional Probabilities"

corn-ordinal-neuralnet This repository contains the orginal model code and experiment logs for the paper "Deep Neural Networks for Rank Consistent Ord

Raschka Research Group 14 Dec 27, 2022
Source code related to the article submitted to the International Conference on Computational Science ICCS 2022 in London

POTHER: Patch-Voted Deep Learning-based Chest X-ray Bias Analysis for COVID-19 Detection Source code related to the article submitted to the Internati

Tomasz Szczepański 1 Apr 29, 2022
natural image generation using ConvNets

The Eyescream Project Generating Natural Images using Neural Networks. For our research summary on this work, please read the Arxiv paper: http://arxi

Meta Archive 601 Nov 23, 2022
PyTorch implementation of "PatchGame: Learning to Signal Mid-level Patches in Referential Games" to appear in NeurIPS 2021

PatchGame: Learning to Signal Mid-level Patches in Referential Games This repository is the official implementation of the paper - "PatchGame: Learnin

Kamal Gupta 22 Mar 16, 2022
Escaping the Gradient Vanishing: Periodic Alternatives of Softmax in Attention Mechanism

Period-alternatives-of-Softmax Experimental Demo for our paper 'Escaping the Gradient Vanishing: Periodic Alternatives of Softmax in Attention Mechani

slwang9353 0 Sep 06, 2021
Homepage of paper: Paint Transformer: Feed Forward Neural Painting with Stroke Prediction, ICCV 2021.

Paint Transformer: Feed Forward Neural Painting with Stroke Prediction [Paper] [Official Paddle Implementation] [Huggingface Gradio Demo] [Unofficial

442 Dec 16, 2022
Learning High-Speed Flight in the Wild

Learning High-Speed Flight in the Wild This repo contains the code associated to the paper Learning Agile Flight in the Wild. For more information, pl

Robotics and Perception Group 391 Dec 29, 2022
Expand human face editing via Global Direction of StyleCLIP, especially to maintain similarity during editing.

Oh-My-Face This project is based on StyleCLIP, RIFE, and encoder4editing, which aims to expand human face editing via Global Direction of StyleCLIP, e

AiLin Huang 51 Nov 17, 2022
Boosted CVaR Classification (NeurIPS 2021)

Boosted CVaR Classification Runtian Zhai, Chen Dan, Arun Sai Suggala, Zico Kolter, Pradeep Ravikumar NeurIPS 2021 Table of Contents Quick Start Train

Runtian Zhai 4 Feb 15, 2022