Jacobian-Free Backprop

Associated Publication

JFB: Jacobian-Free Backpropagation for Implicit Models (arXiv Link)

@article{WuFung2022JFB,
    title={JFB: Jacobian-Free Backpropagation for Implicit Models},
    author={Fung, Samy Wu and Heaton, Howard and Li, Qiuwei and McKenzie, Daniel and Osher, Stanley and Yin, Wotao},
    journal={Proceedings of the AAAI Conference on Artificial Intelligence},
    year={2022}
}

Set-up

Install all the requirements:

pip install -r requirements.txt

Training

For each dataset, there are three types of training drivers:

FPN with our proposed backprop:

	python train_CIFAR10.py
	python train_CIFAR10_Unaugmented.py
	python train_MNIST.py
	python train_SVHN.py

FPN with Jacobian-based backprop:

	python train_CIFAR10_Jacobian_Based.py
	python train_CIFAR10_Unaugmented_Jacobian_Based.py
	python train_MNIST_Jacobian_Based.py
	python train_SVHN_Jacobian_Based.py

Explicit models.

	python train_CIFAR10_Explicit.py
	python train_CIFAR10_Unaugmented_Explicit.py
	python train_MNIST_Explicit.py
	python train_SVHN_Explicit.py

JFB: Jacobian-Free Backpropagation for Implicit Models

Related tags

Overview

Jacobian-Free Backprop

Associated Publication

Set-up

Training

Owner

Typal Research

Implementation of Pooling by Sliced-Wasserstein Embedding (NeurIPS 2021)

IAST: Instance Adaptive Self-training for Unsupervised Domain Adaptation (ECCV 2020)

This repository contains the reference implementation for our proposed Convolutional CRFs.

TransPrompt - Towards an Automatic Transferable Prompting Framework for Few-shot Text Classification

Simple torch.nn.module implementation of Alias-Free-GAN style filter and resample

An Open-Source Tool for Automatic Disease Diagnosis..

AdaFocus (ICCV 2021) Adaptive Focus for Efficient Video Recognition

A selection of State Of The Art research papers (and code) on human locomotion (pose + trajectory) prediction (forecasting)

DeepOBS: A Deep Learning Optimizer Benchmark Suite

This is the unofficial code of Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes. which achieve state-of-the-art trade-off between accuracy and speed on cityscapes and camvid, without using inference acceleration and extra data

code for CVPR paper Zero-shot Instance Segmentation

Trains an agent with stochastic policy gradient ascent to solve the Lunar Lander challenge from OpenAI

A Learning-based Camera Calibration Toolbox

The PyTorch implementation of Directed Graph Contrastive Learning (DiGCL), NeurIPS-2021

[WWW 2021] Source code for "Graph Contrastive Learning with Adaptive Augmentation"

Sequence-to-Sequence learning using PyTorch

Cooperative multi-agent reinforcement learning for high-dimensional nonequilibrium control

TensorFlow Tutorials with YouTube Videos

Codes for our IJCAI21 paper: Dialogue Discourse-Aware Graph Model and Data Augmentation for Meeting Summarization

Improving Query Representations for DenseRetrieval with Pseudo Relevance Feedback:A Reproducibility Study.