Fast Image Processing with Fully-Convolutional Networks
We present an approach to accelerating a wide variety of image processing operators. Our approach uses a fully-convolutional network that is trained on input-output pairs that demonstrate the operator's action. After training, the original operator need not be run at all. The trained network operates at full resolution and runs in constant time. We investigate the effect of network architecture on
Densely Connected Convolutional Networks - Meta Research | Meta Research
Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output. In this paper, we embrace this observation and introduce the Dense Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward fashion. Whereas
CNN Features off-the-shelf: an Astounding Baseline for Recognition
Recent results indicate that the generic descriptors extracted from the convolutional neural networks are very powerful. This paper adds to the mounting evidence that this is indeed the case. We report on a series of experiments conducted for different recognition tasks using the publicly available code and model of the \overfeat network which was trained to perform object classification on ILSVRC
Mask R-CNN
We present a conceptually simple, flexible, and general framework for object instance segmentation. Our approach efficiently detects objects in an image while simultaneously generating a high-quality segmentation mask for each instance. The method, called Mask R-CNN, extends Faster R-CNN by adding a branch for predicting an object mask in parallel with the existing branch for bounding box recognit
Object Contour Detection with a Fully Convolutional Encoder-Decoder Network
We develop a deep learning algorithm for contour detection with a fully convolutional encoder-decoder network. Different from previous low-level edge detection, our algorithm focuses on detecting higher-level object contours. Our network is trained end-to-end on PASCAL VOC with refined ground truth from inaccurate polygon annotations, yielding much higher precision in object contour detection than
DeepLab
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs We address the task of semantic image segmentation with Deep Learning and make three main contributions that are experimentally shown to have substantial practical merit. First, we highlight convolution with upsampled filters, or ‘atrous convolution’, as a powerful tool in dense predicti
Understanding deep learning requires rethinking generalization
Despite their massive size, successful deep artificial neural networks can exhibit a remarkably small difference between training and test performance. Conventional wisdom attributes small generalization error either to properties of the model family, or to the regularization techniques used during training. Through extensive systematic experiments, we show how these traditional approaches fail to
CNN による画像分類で使われる前処理・テスト時処理まとめ - iwiwi 備忘録
とりあえず ImageNet 系の論文で、目に入ったものから順々にまとめていきます。情報・ツッコミ歓迎。 前処理・Data Augmentation Mean Subtraction 入力画像から平均を引く。[103.939, 116.779, 123.68] を各ピクセルから引く。VGG はこれ。 Per-pixel Mean Subtraction 入力画像から平均を引く。ピクセル・チャンネルごとに計算された平均を引く。即ち、224x224x3 個の値について個別に平均を計算し用いる。AlexNet 論文から使われており、ResNet もこれ。 Random Crop 256x256 ピクセルに画像をリサイズし、そこから 224x224 のパッチをランダムに取り出す。AlexNet 論文で使われていた。ちなみに Chainer の ImageNet サンプルはこれと Horizonta
Deep Visual-Semantic Alignments for Generating Image Descriptions
Deep Visual-Semantic Alignments for Generating Image Descriptions We present a model that generates natural language descriptions of images and their regions. Our approach leverages datasets of images and their sentence descriptions to learn about the inter-modal correspondences between language and visual data. Our alignment model is based on a novel combination of Convolutional Neural Networks o
Conditional Random Fields as Recurrent Neural Networks
Pixel-level labelling tasks, such as semantic segmentation, play a central role in image understanding. Recent approaches have attempted to harness the capabilities of deep learning techniques for image recognition to tackle pixel-level labelling tasks. One central issue in this methodology is the limited capacity of deep learning techniques to delineate visual objects. To solve this problem, we i
Deep Learning のトレンドについて喋ってきた
Convolutional Neural NetworksのトレンドについてCasualじゃない話をしてきました． 全脳アーキテクチャ若手の会カジュアルトーク 全脳アーキテクチャ若手の会カジュアルトーク というところでお話をしてきました． ちょっと層がわからなかったのですが，IT系のエンジニアの方が多かったみたいです． （学生は4人くらい…？しかもほぼ身内） 僕のスライドはSlide Shareの方にアップロードされています． しかも，映像もアップロードされていた… 発表後記 実際はConvolutional Neural Networks(CNN)系論文128本ノックにするつもりだったとはいえない空気でしたね… 個人的には画像生成やキャプション生成系の研究速度はとても速く進んでいると感じています． Visual Turing Test の話はもう少し掘り下げたかったですね． Deep M
リリース、障害情報などのサービスのお知らせ
最新の人気エントリーの配信
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く
https://cs231n.stanford.edu/reports/2016/pdfs/286_Report.pdf
Product Insights | Surya Suravarapu | Substack
How does Pinterest decipher what's on unmarked pictures and categorize them?
Looking at Outfit to Parse Clothing
Learning Deconvolution Network for Semantic Segmentation
Fuller Understanding of Fully Convolutional Networks - Google スライド
https://www.robots.ox.ac.uk/~vgg/publications/2015/Simonyan15/simonyan15.pdf
GitHub - floodsung/Deep-Learning-Papers-Reading-Roadmap: Deep Learning papers reading roadmap for anyone who are eager to learn this amazing tech!
GitHub - torrvision/crfasrnn: This repository contains the source code for the semantic image segmentation method described in the ICCV 2015 paper: Conditional Random Fields as Recurrent Neural Networks. http://crfasrnn.torr.vision/
