MIT-Adobe FiveK dataset
MIT-Adobe FiveK Dataset Summary We collected 5,000 photographs taken with SLR cameras by a set of different photographers. They are all in RAW format; that is, all the information recorded by the camera sensor is preserved. We made sure that these photographs cover a broad range of scenes, subjects, and lighting conditions. We then hired five photography students in an art school to adjust the ton
Food-101 -- Mining Discriminative Components with Random Forests
Food-101 – Mining Discriminative Components with Random Forests Lukas Bossard, Matthieu Guillaumin, Luc Van Gool In this paper we address the problem of automatically recognizing pictured dishes. To this end, we introduce a novel method to mine discriminative parts using Random Forests (RF), which allows us to mine for parts simultaneously for all classes and to share knowledge among them. To impr
WaveNet: A Generative Model for Raw Audio | DeepMind
Research WaveNet: A generative model for raw audio Published 8 September 2016 Authors Aäron van den Oord, Sander Dieleman This post presents WaveNet, a deep generative model of raw audio waveforms. We show that WaveNets are able to generate speech which mimics any human voice and which sounds more natural than the best existing Text-to-Speech systems, reducing the gap with human performance by ove
Sketch Simplification・ラフスケッãƒã®è‡ªå‹•ç·šç”»åŒ–
Neural Network-based Sketch Simplification全層畳込ã¿ãƒ‹ãƒ¥ãƒ¼ãƒ©ãƒ«ãƒãƒƒãƒˆãƒ¯ãƒ¼ã‚¯ã«ã‚ˆã‚‹ãƒ©ãƒ•ã‚¹ã‚±ãƒƒãƒã®è‡ªå‹•ç·šç”»åŒ– Edgar Simo-Serraシモセラ エドガー*, Satoshi Iizuka飯塚里志*, Kazuma Sasakiä½ã€…木一真, Hiroshi Ishikawa石å·åš (*equal contributionç†é 著者ã«ç›¸å½“) Project Siteプãƒã‚¸ã‚§ã‚¯ãƒˆã‚µã‚¤ãƒˆ Regarding this service本サービスã«ã¤ã„㦠We provide a service to use AI to clean rough sketches based on "Learning to Simplify: Fully Convolutional Networks for Rough Sketch Cleanup" [Simo-Serra
Synthesizing the preferred inputs for neurons in neural networks via deep generator networks
Deep neural networks (DNNs) have demonstrated state-of-the-art results on many pattern recognition tasks, especially vision classification problems. Understanding the inner workings of such computational brains is both fascinating basic science that is interesting in its own right - similar to why we study the human brain - and will enable researchers to further improve DNNs. One path to understan
Google supercharges machine learning tasks with TPU custom chip | Google Cloud Blog
Google supercharges machine learning tasks with TPU custom chip Editor's Update June 27, 2017: We recently announced Cloud TPUs. Machine learning provides the underlying oomph to many of Google’s most-loved applications. In fact, more than 100 teams are currently using machine learning at Google today, from Street View, to Inbox Smart Reply, to voice search. But one thing we know to be true at Goo
シモセラ エドガー　ラフスケッãƒã®è‡ªå‹•ç·šç”»åŒ–
æœ¬ç ”ç©¶ã§ã¯ã€ç•³è¾¼ã¿ãƒ‹ãƒ¥ãƒ¼ãƒ©ãƒ«ãƒãƒƒãƒˆãƒ¯ãƒ¼ã‚¯ã‚’用ã„ã¦ãƒ©ãƒ•ã‚¹ã‚±ãƒƒãƒã‚’ç·šç”»ã«è‡ªå‹•å¤‰æ›ã™ã‚‹æ‰‹æ³•ã‚’æ案ã™ã‚‹ã€‚æ—¢å˜ã®ã‚¹ã‚±ãƒƒãƒç°¡ç•¥åŒ–手法ã®å¤šãã¯å˜ç´”ãªãƒ©ãƒ•ã‚¹ã‚±ãƒƒãƒã®ãƒ™ã‚¯ã‚¿ãƒ¼ç”»åƒã®ã¿ã‚’対象ã¨ã—ã¦ãŠã‚Šã€ã‚¹ã‚ャンã—ãŸé‰›ç†ç”»ãªã©ã€ãƒ©ã‚¹ã‚¿ãƒ¼å½¢å¼ã®è¤‡é›‘ãªãƒ©ãƒ•ã‚¹ã‚±ãƒƒãƒã‚’線画化ã™ã‚‹ã®ã¯å›°é›£ã§ã‚ã£ãŸã€‚ã“ã‚Œã«å¯¾ã—æ案手法ã§ã¯ã€3種類ã®ç•³è¾¼ã¿å±¤ã‹ã‚‰æ§‹æˆã•ã‚Œã‚‹ãƒ‹ãƒ¥ãƒ¼ãƒ©ãƒ«ãƒãƒƒãƒˆãƒ¯ãƒ¼ã‚¯ãƒ¢ãƒ‡ãƒ«ã«ã‚ˆã£ã¦è¤‡é›‘ãªãƒ©ãƒ•ã¨ç·šç”»ã®å¯¾å¿œã‚’å¦ç¿’ã™ã‚‹ã“ã¨ã§ã€ãƒ©ã‚¹ã‚¿ãƒ¼å½¢å¼ã®æ§˜ã€…ãªãƒ©ãƒ•ã‚¹ã‚±ãƒƒãƒã‚’良好ã«ç·šç”»åŒ–ã™ã‚‹ã“ã¨ãŒã§ãる。æ案モデルã§ã¯ã€ä»»æ„ã®ã‚µã‚¤ã‚ºã‚„アスペクト比をもã¤ç”»åƒã‚’入力ã¨ã—ã¦æ‰±ã†ã“ã¨ãŒå¯èƒ½ã§ã‚ã‚Šã€å‡ºåŠ›ã•ã‚Œã‚‹ç·šç”»ã¯å…¥åŠ›ç”»åƒã¨åŒã˜ã‚µã‚¤ã‚ºã«ãªã‚‹ã€‚ã¾ãŸã€ã“ã®ã‚ˆã†ãªå¤šå±¤æ§‹é€ ã‚’ã‚‚ã¤ãƒ¢ãƒ‡ãƒ«ã‚’å¦ç¿’ã•ã›ã‚‹ãŸã‚ã€ãƒ©ãƒ•ã‚¹ã‚±ãƒƒãƒã¨ç·šç”»ãŒãƒšã‚¢ã«ãªã£ãŸæ–°ã—ã„データセットを構築ã—ã€ãƒ¢ãƒ‡ãƒ«ã‚’効果的ã«å¦ç¿’ã•ã›ã‚‹æ–¹æ³•ã‚’æ案ã—ãŸã€‚得られãŸçµæžœã«ã¤ã„ã¦ãƒ¦ãƒ¼ã‚¶ãƒ†ã‚¹ãƒˆã‚’è¡Œã„ã€æ案手法ã®æ€§
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
We consider image transformation problems, where an input image is transformed into an output image. Recent methods for such problems typically train feed-forward convolutional neural networks using a \emph{per-pixel} loss between the output and ground-truth images. Parallel work has shown that high-quality images can be generated by defining and optimizing \emph{perceptual} loss functions based o
Colorful Image Colorization
Example input grayscale photos and output colorizations from our algorithm. These examples are cases where our model works especially well. For randomly selected examples, see the Performance comparisons section below. Welcome! Computer vision algorithms often work well on some images, but fail on others. Ours is like this too. We believe our work is a significant step forward in solving the color
Multi-Scale Context Aggregation by Dilated Convolutions
State-of-the-art models for semantic segmentation are based on adaptations of convolutional networks that had originally been designed for image classification. However, dense prediction and image classification are structurally different. In this work, we develop a new convolutional network module that is specifically designed for dense prediction. The presented module uses dilated convolutions t
U-Net: Convolutional Networks for Biomedical Image Segmentation
U-Net: Convolutional Networks for Biomedical Image Segmentation The u-net is convolutional network architecture for fast and precise segmentation of images. Up to now it has outperformed the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks. It has won the Grand Challenge for Computer-Automated De
ImageWorsener
ImageWorsener is a cross-platform command-line utility and library for image scaling and other image processing. It has full support for PNG, JPEG, BMP formats, experimental support for WebP, read-only support for GIF, and limited support for some other image formats. It’s not as fast or memory-efficient as some utilities, but it’s very accurate. It is free software, licensed under an MIT-style li
COCO - Common Objects in Context
What is COCO? COCO is a new image recognition, segmentation, and captioning dataset. COCO has several features: Object segmentation Recognition in Context Multiple objects per image More than 300,000 images More than 2 Million instances 80 object categories 5 captions per image Keypoints on 100,000 people Tsung-Yi Lin Cornell Tech Genevieve Patterson MSR Matteo Ruggero Ronchi Caltech Yin Cui Corne
Net2Net: Accelerating Learning via Knowledge Transfer
We introduce techniques for rapidly transferring the information stored in one neural net into another neural net. The main purpose is to accelerate the training of a significantly larger neural net. During real-world workflows, one often trains very many different neural networks during the experimentation and design process. This is a wasteful process in which each new model is trained from scra
リリースã€éšœå®³æƒ…å ±ãªã©ã®ã‚µãƒ¼ãƒ“スã®ãŠçŸ¥ã‚‰ã›
最新ã®äººæ°—エントリーã®é…ä¿¡
j次ã®ãƒ–ックマーク
kå‰ã®ãƒ–ックマーク
lã‚ã¨ã§èªã‚€
eコメント一覧を開ã
oページを開ã
Google Play Books introduces Bubble Zoom
Deeply-Recursive Convolutional Network for Image Super-Resolution
Accurate Image Super-Resolution Using Very Deep Convolutional Networks
Princeton ModelNet
2015å¹´12月PRMUç ”ç©¶ä¼š 対応点探索ã®ãŸã‚ã®ç‰¹å¾´é‡è¡¨ç¾
Best practice for migrating an existing Git repo to support LFS? · Issue #326 · git-lfs/git-lfs
{{#tags}}- {{label}}
{{/tags}}