We present a regularized self-labeling approach to improve the generalization and robustness properties of fine-tuning.

Overview

Overview

This repository provides the implementation for the paper "Improved Regularization and Robustness for Fine-tuning in Neural Networks", which will be presented as a poster paper in NeurIPS'21.

In this work, we propose a regularized self-labeling approach that combines regularization and self-training methods for improving the generalization and robustness properties of fine-tuning. Our approach includes two components:

  • First, we encode layer-wise regularization to penalize the model weights at different layers of the neural net.
  • Second, we add self-labeling that relabels data points based on current neural net's belief and reweights data points whose confidence is low.

An illustration of our approach

Requirements

  • Python >= 3.6
  • PyTorch >= 1.7
  • Optuna >= 2.5
  • Numpy

Usage

Our algorithm is based on layer-wise regularization and self label-correction and label-weighting.

As an example, here are the test accuracy results on the Indoor dataset with independent label noise:

Method Noise = 20% Noise = 40% Noise = 60% Noise = 80%
Ours 75.21 $\pm$ 0.46 68.13 $\pm$ 0.16 57.59 $\pm$ 0.55 34.08 $\pm$ 0.79
Fine-tuning 65.02 $\pm$ 0.39 57.49 $\pm$ 0.39 44.60 $\pm$ 0.95 27.09 $\pm$ 0.19

Run following code to replicate above results:

python train_label_noise.py --config configs/config_constraint_indoor.json --model ResNet18 \
    --reg_method constraint --reg_norm frob \
    --reg_extractor 7.80246991703043 --reg_predictor 14.077402847906 \
    --noise_rate 0.2 --train_correct_label --reweight_epoch 5 --reweight_temp 2.0 --correct_epoch 10 --correct_thres 0.9 

python train_label_noise.py --config configs/config_constraint_indoor.json --model ResNet18 \
    --reg_method constraint --reg_norm frob \
    --reg_extractor 8.47139398080791 --reg_predictor 19.0191127114923 \
    --noise_rate 0.4 --train_correct_label --reweight_epoch 5 --reweight_temp 2.0 --correct_epoch 10 --correct_thres 0.9 

python train_label_noise.py --config configs/config_constraint_indoor.json --model ResNet18 \
    --reg_method constraint --reg_norm frob \
    --reg_extractor 10.7576018531961 --reg_predictor 19.8157649727473 \
    --noise_rate 0.6 --train_correct_label --reweight_epoch 5 --reweight_temp 2.0 --correct_epoch 10 --correct_thres 0.9 
    
python train_label_noise.py --config configs/config_constraint_indoor.json --model ResNet18 \
    --reg_method constraint --reg_norm frob \
    --reg_extractor 9.2031662757248 --reg_predictor 6.41568500472423 \
    --noise_rate 0.8 --train_correct_label --reweight_epoch 5 --reweight_temp 1.5 --correct_epoch 10 --correct_thres 0.9 

Data Preparation

We use seven image datasets in our paper. We list the link for downloading these datasets and describe how to prepare data to run our code below.

  • Aircrafts: download and extract into ./data/aircrafts
    • remove the class 257.clutter out of the data directory
  • CUB-200-2011: download and extract into ./data/CUB_200_2011/
  • Caltech-256: download and extract into ./data/caltech256/
  • Stanford-Cars: download and extract into ./data/StanfordCars/
  • Stanford-Dogs: download and extract into ./data/StanfordDogs/
  • Flowers: download and extract into ./data/flowers/
  • MIT-Indoor: download and extract into ./data/Indoor/

Our code automatically handles the split of the datasets.

Citation

If you find this repository useful, consider citing our work titled above.

Acknowledgment

Thanks to the authors of mars-finetuning and WS-DAN.PyTorch for providing their implementation publicly available.

Owner
NEU-StatsML-Research
We are a group of faculty and students from the Computer Science College of Northeastern University
NEU-StatsML-Research
TumorInsight is a Brain Tumor Detection and Classification model built using RESNET50 architecture.

A Brain Tumor Detection and Classification Model built using RESNET50 architecture. The model is also deployed as a web application using Flask framework.

Pranav Khurana 0 Aug 17, 2021
PyTorch implementation of the supervised learning experiments from the paper Model-Agnostic Meta-Learning (MAML)

pytorch-maml This is a PyTorch implementation of the supervised learning experiments from the paper Model-Agnostic Meta-Learning (MAML): https://arxiv

Kate Rakelly 516 Jan 05, 2023
HGCN: Harmonic Gated Compensation Network For Speech Enhancement

HGCN The official repo of "HGCN: Harmonic Gated Compensation Network For Speech Enhancement", which was accepted at ICASSP2022. How to use step1: Calc

ScorpioMiku 33 Nov 14, 2022
TreeSubstitutionCipher - Encryption system based on trees and substitution

Tree Substitution Cipher Generation Algorithm: Generate random tree. Tree nodes

stepa 1 Jan 08, 2022
Pytorch implementation of Hinton's Dynamic Routing Between Capsules

pytorch-capsule A Pytorch implementation of Hinton's "Dynamic Routing Between Capsules". https://arxiv.org/pdf/1710.09829.pdf Thanks to @naturomics fo

Tim Omernick 625 Oct 27, 2022
Facebook Research 605 Jan 02, 2023
Code for Reciprocal Adversarial Learning for Brain Tumor Segmentation: A Solution to BraTS Challenge 2021 Segmentation Task

BRATS 2021 Solution For Segmentation Task This repo contains the supported pytorch code and configuration files to reproduce 3D medical image segmenta

Himashi Amanda Peiris 6 Sep 15, 2022
Python binding for Khiva library.

Khiva-Python Build Documentation Build Linux and Mac OS Build Windows Code Coverage README This is the Khiva Python binding, it allows the usage of Kh

Shapelets 46 Oct 16, 2022
First-Order Probabilistic Programming Language

FOPPL: A First-Order Probabilistic Programming Language This is an implementation of FOPPL, an S-expression based probabilistic programming language d

Renato Costa 23 Dec 20, 2022
A pytorch implementation of MBNET: MOS PREDICTION FOR SYNTHESIZED SPEECH WITH MEAN-BIAS NETWORK

Pytorch-MBNet A pytorch implementation of MBNET: MOS PREDICTION FOR SYNTHESIZED SPEECH WITH MEAN-BIAS NETWORK Training To train a new model, please ru

46 Dec 28, 2022
Breaking Shortcut: Exploring Fully Convolutional Cycle-Consistency for Video Correspondence Learning

Breaking Shortcut: Exploring Fully Convolutional Cycle-Consistency for Video Correspondence Learning Yansong Tang *, Zhenyu Jiang *, Zhenda Xie *, Yue

Zhenyu Jiang 12 Nov 16, 2022
Deeplab-resnet-101 in Pytorch with Jaccard loss

Deeplab-resnet-101 Pytorch with Lovász hinge loss Train deeplab-resnet-101 with binary Jaccard loss surrogate, the Lovász hinge, as described in http:

Maxim Berman 95 Apr 15, 2022
Lama-cleaner: Image inpainting tool powered by LaMa

Lama-cleaner: Image inpainting tool powered by LaMa

Qing 5.8k Jan 05, 2023
Rewrite ultralytics/yolov5 v6.0 opencv inference code based on numpy, no need to rely on pytorch

Rewrite ultralytics/yolov5 v6.0 opencv inference code based on numpy, no need to rely on pytorch; pre-processing and post-processing using numpy instead of pytroch.

炼丹去了 21 Dec 12, 2022
Object detection GUI based on PaddleDetection

PP-Tracking GUI界面测试版 本项目是基于飞桨开源的实时跟踪系统PP-Tracking开发的可视化界面 在PaddlePaddle中加入pyqt进行GUI页面研发,可使得整个训练过程可视化,并通过GUI界面进行调参,模型预测,视频输出等,通过多种类型的识别,简化整体预测流程。 GUI界面

杨毓栋 68 Jan 02, 2023
BaseCls BaseCls 是一个基于 MegEngine 的预训练模型库,帮助大家挑选或训练出更适合自己科研或者业务的模型结构

BaseCls BaseCls 是一个基于 MegEngine 的预训练模型库,帮助大家挑选或训练出更适合自己科研或者业务的模型结构。 文档地址:https://basecls.readthedocs.io 安装 安装环境 BaseCls 需要 Python = 3.6。 BaseCls 依赖 M

MEGVII Research 28 Dec 23, 2022
Lane assist for ETS2, built with the ultra-fast-lane-detection model.

Euro-Truck-Simulator-2-Lane-Assist Lane assist for ETS2, built with the ultra-fast-lane-detection model. This project was made possible by the amazing

36 Jan 05, 2023
Unofficial PyTorch code for BasicVSR

Dependencies and Installation The code is based on BasicSR, Please install the BasicSR framework first. Pytorch=1.51 Training cd ./code CUDA_VISIBLE_

Long 59 Dec 06, 2022
SuMa++: Efficient LiDAR-based Semantic SLAM (Chen et al IROS 2019)

SuMa++: Efficient LiDAR-based Semantic SLAM This repository contains the implementation of SuMa++, which generates semantic maps only using three-dime

Photogrammetry & Robotics Bonn 701 Dec 30, 2022
Benchmarking the robustness of Spatial-Temporal Models

Benchmarking the robustness of Spatial-Temporal Models This repositery contains the code for the paper Benchmarking the Robustness of Spatial-Temporal

Yi Chenyu Ian 15 Dec 16, 2022