bhheo / Bss_distillation
Licence: mit
Knowledge Distillation with Adversarial Samples Supporting Decision Boundary (AAAI 2019)
Stars: ✭ 51
Programming Languages
python
139335 projects - #7 most used programming language
Labels
Projects that are alternatives of or similar to Bss distillation
Isic2018 Part3
Source code for 'ISIC 2018: Skin Lesion Analysis Towards Melanoma Detection' - Task 3 (Classification)
Stars: ✭ 17 (-66.67%)
Mutual labels: image-classification
Pytorch Toolbelt
PyTorch extensions for fast R&D prototyping and Kaggle farming
Stars: ✭ 942 (+1747.06%)
Mutual labels: image-classification
Cv Pretrained Model
A collection of computer vision pre-trained models.
Stars: ✭ 995 (+1850.98%)
Mutual labels: image-classification
Image classification cifar 10
Image Classification on CIFAR-10 Dataset using Multi Layer Perceptrons in Python from Scratch.
Stars: ✭ 18 (-64.71%)
Mutual labels: image-classification
Orange3 Imageanalytics
🍊 🎑 Orange3 add-on for dealing with image related tasks
Stars: ✭ 24 (-52.94%)
Mutual labels: image-classification
Deepmodels
TensorFlow Implementation of state-of-the-art models since 2012
Stars: ✭ 33 (-35.29%)
Mutual labels: image-classification
Quickdraw
Implementation of Quickdraw - an online game developed by Google
Stars: ✭ 805 (+1478.43%)
Mutual labels: image-classification
Efficientnas
Towards Automated Deep Learning: Efficient Joint Neural Architecture and Hyperparameter Search https://arxiv.org/abs/1807.06906
Stars: ✭ 44 (-13.73%)
Mutual labels: image-classification
Retrained Inceptionv3
Retrained InceptionV3 image classification model
Stars: ✭ 15 (-70.59%)
Mutual labels: image-classification
Node Image Classification
A simple example on Image Classification in Node.js with TensorFlow.js
Stars: ✭ 23 (-54.9%)
Mutual labels: image-classification
Concise Ipython Notebooks For Deep Learning
Ipython Notebooks for solving problems like classification, segmentation, generation using latest Deep learning algorithms on different publicly available text and image data-sets.
Stars: ✭ 23 (-54.9%)
Mutual labels: image-classification
Albumentations
Fast image augmentation library and an easy-to-use wrapper around other libraries. Documentation: https://albumentations.ai/docs/ Paper about the library: https://www.mdpi.com/2078-2489/11/2/125
Stars: ✭ 9,353 (+18239.22%)
Mutual labels: image-classification
Dmsmsgrcg
A photo OCR project aims to output DMS messages contained in sign structure images.
Stars: ✭ 18 (-64.71%)
Mutual labels: image-classification
Hardhat Detector
A convolutional neural network implementation of a script that detects whether an individual is wearing a hardhat or not.
Stars: ✭ 41 (-19.61%)
Mutual labels: image-classification
Eccv2020 Code
ECCV 2020 论文开源项目合集，同时欢迎各位大佬提交issue，分享ECCV 2020开源项目
Stars: ✭ 827 (+1521.57%)
Mutual labels: image-classification
Multidigitmnist
Combine multiple MNIST digits to create datasets with 100/1000 classes for few-shot learning/meta-learning
Stars: ✭ 48 (-5.88%)
Mutual labels: image-classification
Computervision Recipes
Best Practices, code samples, and documentation for Computer Vision.
Stars: ✭ 8,214 (+16005.88%)
Mutual labels: image-classification
Channel Pruning
Channel Pruning for Accelerating Very Deep Neural Networks (ICCV'17)
Stars: ✭ 979 (+1819.61%)
Mutual labels: image-classification
Knowledge Distillation with Adversarial Samples Supporting Decision Boundary
Official Pytorch implementation of paper:
Knowledge Distillation with Adversarial Samples Supporting Decision Boundary (AAAI 2019).
Sporlight and poster are available on homepage
Environment
Python 3.6, Pytorch 0.4.1, Torchvision
Knowledge distillation (CIFAR-10)
python train_BSS_distillation.py
Distillation from ResNet 26 (teacher) to ResNet 10 (student) on CIFAR-10 dataset.
Pre-trained teacher network (ResNet 26) is included.
Citation
@inproceedings{BSSdistill,
title = {Knowledge Distillation with Adversarial Samples Supporting Decision Boundary},
author = {Byeongho Heo, Minsik Lee, Sangdoo Yun, Jin Young Choi},
booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
year = {2019}
}
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].