number9473 / nn-algorithm Goto Github PK
View Code? Open in Web Editor NEWalgorithm for neural network
algorithm for neural network
center loss
We propose a method to push the frontiers of unconstrained face recognition in the wild, focusing on the problem of extreme pose variations.
We leverage deep Convolutional Neural Networks (CNNs) to learn discrimi-native representations we call Pose-Aware Models (PAMs)using 500K images from the CASIA WebFace dataset.
Experiments show that DSD training can improve the performance of a wide range of CNN, RNN and LSTMs on the tasks of image classification, caption generation and speech recognition.
we propose a novel network compression method called dynamic network surgery, which can remarkably reduce the network complexity by making on-the-fly connection pruning.
teacher network, student network
soft targets
Temperature
We demonstrate that IC-STNs can achieve better performance than conventional STNs with less model capacity
We present an image-conditional image generation model. The model transfers an input domain to a target domain in semantic level, and generates the target image in pixel level.
we propose a novel funnel-structured cascade (FuSt) detection framework. In a coarse-to-fine flavor, our FuSt consists of, from top to bottom, 1) multiple view-specific fast LAB cascade for extremely quick face proposal, 2) multiple coarse MLP cascade for further candidate window verification, and 3) a unified fine MLP cascade with shape-indexed features for accurate face detection.
TABLE I: Benchmarks for age and gender estimation from photos. With the exception of the FG-NET Aging and UIUCIFP-Y benchmarks, the table includes only benchmarks which are presently available online to the research community.
We show that activation-based attention transfer gives better improvements than full activation transfer, and can be combined with knowledge distillation
we propose an End-to-End learning approach to address ordinal regression problems using deep Convolutional Neural Network, which could simultaneously conduct feature learning and regression modeling
we publish an Asian Face Age Dataset (AFAD) containing more than 160K facial images with precise age ground-truths, which is the largest public age dataset to date.
this is the first work to address ordinal regression problems by using CNN, and achieves the state-of-the-art performance on both the MORPH and AFAD datasets
Following the experimental setting in [6][7][31], for both MORPH II and AFAD datasets, we randomly divide the whole dataset into two parts: one part (i.e., 80% of the whole data) is used for training, and the other one (i.e., 20% of the whole data) is used for testing.
The performance is measured by the Mean Absolute Error (MAE) metric and the Cumulative Score (CS).
we distill the knowledge learned the small clean dataset to facilitate learning a better model from the entire noisy dataset.
we propose a simple convolutional net architecture that can be used even when the amount of learning data is limited.
We evaluate our method on the recent Adience benchmark for age and gender estimation and show it to dramatically outperform current state-of-the-art methods.
The public available MSU MFSD Database for face spoof attack consists of 280 video clips of photo and video attack attempts to 35 clients.
We apply our method to visual domains including digits and face images and demon-strate its ability to generate convincing novel images of previously unseen entities, while preserving their identity.
The Replay-Attack Database for face spoofing consists of 1300 video clips of photo and video attack attempts to 50 clients, under different lighting conditions. This Database was produced at the Idiap Research Institute, in Switzerland.
we explore how these properties translate into exceptionally simple neural networks approximat-
ing both natural phenomena such as images and abstract representations thereof such as drawings.We further argue that when the statistical process generating the data is of a certain hierarchical form prevalent in physics and machine-learning, a deep neural network can be more efficient than a shallow one.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.