Implementation for the paper (CVPR Oral): High Frequency Component Helps Explain the Generalization of Convolutional Neural Networks

Implementation for the paper (CVPR Oral): High Frequency Component Helps Explain the Generalization of Convolutional Neural Networks

Related Repos



uoguelph-mlrg Cutout This repository contains the code for the paper Improved Regularization of Convolutional Neural Networks with Cutout. Introduction Cutout is a simple regularization method for convolutional neural networks whic
 

dongjun-Lee Text Classification Models with Tensorflow Tensorflow implementation of Text Classification Models. Implemented Models: Word-level CNN [paper] Character-level CNN [paper] Very Deep CNN [paper] Word-level Bidirectional
 

alokwhitewolf Contains implementation of Guided Attention Inference Network (GAIN) presented in Tell Me Where to Look(CVPR 2018). This repository aims to apply GAIN on fcn8 architecture used for segmentation.
 

AdeelMufti World Models Implementation In Chainer This is a fairly complete implementation, in Chainer, of the World Models framework described by David Ha and Jürgen Schmidhuber: https://arxiv.org/abs/1803.10122 This project was created a
 

rafaelpadilla Citation This work was accepted to be presented at IWSSIP 2020. If you use this code for your research, please consider citing: @article{padillaCITE2020, title = {Survey on Performance Metrics for Object-Detection Algorithms
 

lancifollia TinyGBT TinyGBT(Tiny Gradient Boosted Trees) is a 200 line gradient boosted trees implementation written in pure python. Since this code is not for production, it is not optimized for speed and memory usage. Experimen
 

kororo ExcelCy ExcelCy is a toolkit to integrate Excel to spaCy NLP training experiences. Training NER using XLSX from PDF, DOCX, PPT, PNG or JPG. ExcelCy has pipeline to match Entity with PhraseMatcher or Matcher in regular
 

pandeykartikey Hierarchical Attention Networks for Document Classification We know that documents have a hierarchical structure, words combine to form sentences and sentences combine to form documents. We can try to learn that structure or we c