Trending Research

Ordered by accumulated GitHub stars in last 3 days
506-390-6537 2039125668 Greatest
1
Card image cap
A Hierarchical Multi-task Approach for Learning Embeddings from Semantic Tasks
Much efforts has been devoted to evaluate whether multi-task learning can be leveraged to learn rich representations that can be used in various Natural Language Processing (NLP) down-stream applications. The model is trained in a hierarchical fashion to introduce an inductive bias by supervising a set of low level tasks at the bottom layers of the model and more complex tasks at the top layers of the model.

143
2.59 stars / hour
 Paper  Code
2
Addressing the Fundamental Tension of PCGML with Discriminative Learning
This approach presents a fundamental tension: the more design effort expended to produce detailed training examples for shaping a generator, the lower the return on investment from applying PCGML in the first place. In response, we propose the use of discriminative models (which capture the validity of a design rather the distribution of the content) trained on positive and negative examples.

10,505
1.29 stars / hour
(844) 557-8729  Code
3
Card image cap
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers. Unlike recent language representation models, BERT is designed to pre-train deep bidirectional representations by jointly conditioning on both left and right context in all layers.
7,514
0.55 stars / hour
 Paper  Code
4
AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles
Developing and testing algorithms for autonomous vehicles in real world is an expensive and time consuming process. Also, in order to utilize recent advances in machine intelligence and deep learning we need to collect a large amount of annotated training data in a variety of conditions and environments.

6,206
0.49 stars / hour
 Paper  Code
5
Card image cap
Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks
In this work, we propose a simple, lightweight approach for better context exploitation in CNNs. We also propose a parametric gather-excite operator pair which yields further performance gains, relate it to the recently-introduced Squeeze-and-Excitation Networks, and analyse the effects of these changes to the CNN feature activation statistics.
85
0.38 stars / hour
8175996395  Code
6
Card image cap
Aequitas: A Bias and Fairness Audit Toolkit
Recent work has raised concerns on the risk of unintended bias in algorithmic decision making systems being used nowadays that can affect individuals unfairly based on race, gender or religion, among other possible characteristics. While a lot of bias metrics and fairness definitions have been proposed in recent years, there is no consensus on which metric/definition should be used and there are very few available resources to operationalize them.

79
0.35 stars / hour
nothing  Code
7
Speech Intention Understanding in a Head-final Language: A Disambiguation Utilizing Intonation-dependency
This paper suggests a system which identifies the intention of an utterance, given its acoustic feature and text. Based on an intuitive understanding of Korean language which is engaged in data annotation, we construct a network identifying the intention of a speech and validate its utility with sample sentences.

21
0.33 stars / hour
 Paper  Code
8
Card image cap
Fully Supervised Speaker Diarization
In this paper, we propose a fully supervised speaker diarization approach, named unbounded interleaved-state recurrent neural networks (UIS-RNN). Given extracted speaker-discriminative embeddings (a.k.a.

497
0.33 stars / hour
(845) 619-2327  Code
9
Card image cap
Deep Residual Learning for Image Recognition
We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.
9,697
0.30 stars / hour
 Paper  Code
10
TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
TensorFlow is an interface for expressing machine learning algorithms, and an implementation for executing such algorithms. A computation expressed using TensorFlow can be executed with little or no change on a wide variety of heterogeneous systems, ranging from mobile devices such as phones and tablets up to large-scale distributed systems of hundreds of machines and thousands of computational devices such as GPU cards.
114,655
0.29 stars / hour
 Paper  Code
11
Card image cap
Self-Attention Generative Adversarial Networks
In this paper, we propose the Self-Attention Generative Adversarial Network (SAGAN) which allows attention-driven, long-range dependency modeling for image generation tasks. Traditional convolutional GANs generate high-resolution details as a function of only spatially local points in lower-resolution feature maps.
3,803
0.27 stars / hour
 Paper  Code
12
Card image cap
Progressive Growing of GANs for Improved Quality, Stability, and Variation
We describe a new training methodology for generative adversarial networks. The key idea is to grow both the generator and discriminator progressively: starting from a low resolution, we add new layers that model increasingly fine details as training progresses.
3,803
0.27 stars / hour
 Paper  Code
13
Card image cap
GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
Generative Adversarial Networks (GANs) excel at creating realistic images with complex models for which maximum likelihood is infeasible. However, the convergence of GAN training has still not been proved.
3,803
0.27 stars / hour
 Paper  Code
14
Card image cap
Learning Named Entity Tagger using Domain-Specific Dictionary
Recent advances in deep neural models allow us to build reliable named entity recognition (NER) systems without handcrafting features. However, such methods require large amounts of manually-labeled training data.

95
0.25 stars / hour
soul-diseased  Code
15
Card image cap
Automated Phrase Mining from Massive Text Corpora
As one of the fundamental tasks in text analysis, phrase mining aims at extracting quality phrases from a text corpus. Since one can easily obtain many quality phrases from public knowledge bases to a scale that is much larger than that produced by human experts, in this paper, we propose a novel framework for automated phrase mining, AutoPhrase, which leverages this large amount of high-quality phrases in an effective way and achieves better performance compared to limited human labeled phrases.

95
0.25 stars / hour
8323669917  Code
16
Card image cap
models
Models and examples built with TensorFlow
44,565
0.22 stars / hour
 Paper  Code
17
Card image cap
Scene Text Detection and Recognition: The Deep Learning Era
As an important research area in computer vision, scene text detection and recognition has been inescapably influenced by this wave of revolution, consequentially entering the era of deep learning. In recent years, the community has witnessed substantial advancements in mindset, approach and performance.

58
0.22 stars / hour
 Paper  Code
18
Card image cap
Consistent Individualized Feature Attribution for Tree Ensembles
Interpreting predictions from tree ensemble methods such as gradient boosting machines and random forests is important, yet feature attribution for trees is often heuristic and not individualized for each prediction. Here we show that popular feature attribution methods are inconsistent, meaning they can lower a feature's assigned importance when the true impact of that feature actually increases.

2,665
0.18 stars / hour
 Paper  Code
19
Card image cap
SEGAN: Speech Enhancement Generative Adversarial Network
The majority of them tackle a limited number of noise conditions and rely on first-order statistics. In contrast to current techniques, we operate at the waveform level, training the model end-to-end, and incorporate 28 speakers and 40 different noise conditions into the same model, such that model parameters are shared across them.

18
0.16 stars / hour
self-treated  Code
20
Card image cap
Language and Noise Transfer in Speech Enhancement Generative Adversarial Network
This makes the adaptability of those systems into new, low resource environments an important topic. In this work, we present the results of adapting a speech enhancement generative adversarial network by finetuning the generator with small amounts of data.

18
0.16 stars / hour
 Paper  Code
21
Card image cap
Whispered-to-voiced Alaryngeal Speech Conversion with Generative Adversarial Networks
Most methods of voice restoration for patients suffering from aphonia either produce whispered or monotone speech. Apart from intelligibility, this type of speech lacks expressiveness and naturalness due to the absence of pitch (whispered speech) or artificial generation of it (monotone speech).

18
0.16 stars / hour
 Paper  Code
22
Card image cap
Transfer learning for time series classification
Transfer learning for deep neural networks is the process of first training a base network on a source dataset, and then transferring the learned features (the network's weights) to a second network to be trained on a target dataset. Therefore, in an effort to predict the best source dataset for a given target dataset, we propose a new method relying on Dynamic Time Warping to measure inter-datasets similarities.

41
0.16 stars / hour
 Paper  Code
23
Card image cap
Analogical Reasoning on Chinese Morphological and Semantic Relations
Analogical reasoning is effective in capturing linguistic regularities. This paper proposes an analogical reasoning task on Chinese.
3,197
0.15 stars / hour
917-293-0539  Code
24
Card image cap
Relational inductive biases, deep learning, and graph networks
This has been due, in part, to cheap data and cheap compute resources, which have fit the natural strengths of deep learning. As a companion to this paper, we have released an open-source software library for building graph networks, with demonstrations of how to use them in practice.

2,136
0.15 stars / hour
sina  Code
25
Card image cap
Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
Image-to-image translation is a class of vision and graphics problems where the goal is to learn the mapping between an input image and an output image using a training set of aligned image pairs. Our goal is to learn a mapping $G: X \rightarrow Y$ such that the distribution of images from $G(X)$ is indistinguishable from the distribution $Y$ using an adversarial loss.
5,895
0.15 stars / hour
727-306-6272  Code
26
Card image cap
Image-to-Image Translation with Conditional Adversarial Networks
We investigate conditional adversarial networks as a general-purpose solution to image-to-image translation problems. These networks not only learn the mapping from input image to output image, but also learn a loss function to train this mapping.
5,895
0.15 stars / hour
 Paper  Code
27
Card image cap
Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
We present an approach to efficiently detect the 2D pose of multiple people in an image. The approach uses a nonparametric representation, which we refer to as Part Affinity Fields (PAFs), to learn to associate body parts with individuals in the image.
9,840
0.15 stars / hour
 Paper  Code
28
Card image cap
Hand Keypoint Detection in Single Images using Multiview Bootstrapping
We call this procedure multiview bootstrapping: first, an initial keypoint detector is used to produce noisy labels in multiple views of the hand. The method is used to train a hand keypoint detector for single images.
9,840
0.15 stars / hour
419-386-5158  Code
29
Card image cap
Convolutional Pose Machines
Pose Machines provide a sequential prediction framework for learning rich implicit spatial models. In this work we show a systematic design for how convolutional networks can be incorporated into the pose machine framework for learning image features and image-dependent spatial models for the task of pose estimation.
9,840
0.15 stars / hour
 Paper  Code
30
Large-Scale Study of Curiosity-Driven Learning
However, annotating each environment with hand-designed, dense rewards is not scalable, motivating the need for developing reward functions that are intrinsic to the agent. In this paper: (a) We perform the first large-scale study of purely curiosity-driven learning, i.e. without any extrinsic rewards, across 54 standard benchmark environments, including the Atari game suite.
337
0.14 stars / hour
straddle mill  Code
31
Card image cap
AllenNLP: A Deep Semantic Natural Language Processing Platform
This paper describes AllenNLP, a platform for research on deep learning methods in natural language understanding. AllenNLP is designed to support researchers who want to build novel language understanding models quickly and easily.

4,203
0.14 stars / hour
(646) 640-7532  Code
32
Mask R-CNN
Our approach efficiently detects objects in an image while simultaneously generating a high-quality segmentation mask for each instance. We show top results in all three tracks of the COCO suite of challenges, including instance segmentation, bounding-box object detection, and person keypoint detection.
8,718
0.13 stars / hour
 Paper  Code
33
Card image cap
tensor2tensor
Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.

5,729
0.13 stars / hour
8022335778  Code
34
Card image cap
Generalizing to Unseen Domains via Adversarial Data Augmentation
We are concerned with learning models that generalize well to different \emph{unseen} domains. Only using training data from a single source distribution, we propose an iterative procedure that augments the dataset with examples from a fictitious target domain that is "hard" under the current model.
19
0.13 stars / hour
 Paper  Code
35
Card image cap
Deep Speech: Scaling up end-to-end speech recognition
We present a state-of-the-art speech recognition system developed using end-to-end deep learning. Our architecture is significantly simpler than traditional speech systems, which rely on laboriously engineered processing pipelines; these traditional systems also tend to perform poorly when used in noisy environments.
8,426
0.13 stars / hour
(347) 919-9756  Code
36
Card image cap
Attention Is All You Need
The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism.
1,418
0.11 stars / hour
 Paper  Code
37
Card image cap
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers. Unlike recent language representation models, BERT is designed to pre-train deep bidirectional representations by jointly conditioning on both left and right context in all layers.
1,645
0.11 stars / hour
 Paper  Code
38
Card image cap
Evaluating the Utility of Hand-crafted Features in Sequence Labelling
Conventional wisdom is that hand-crafted features are redundant for deep learning models, as they already learn adequate representations of text automatically from corpora. In this work, we test this claim by proposing a new method for exploiting handcrafted features as part of a novel hybrid learning approach, incorporating a feature auto-encoder loss component.

10
0.11 stars / hour
 Paper  Code
39
Card image cap
Enriching Word Vectors with Subword Information
Continuous word representations, trained on large unlabeled corpora are useful for many natural language processing tasks. A vector representation is associated to each character $n$-gram; words being represented as the sum of these representations.

16,365
0.11 stars / hour
 Paper  Code
40
Card image cap
FastText.zip: Compressing text classification models
We consider the problem of producing compact architectures for text classification, such that the full model fits in a limited amount of memory. After considering different solutions inspired by the hashing literature, we propose a method built upon product quantization to store word embeddings.

16,365
0.11 stars / hour
270-797-2446  Code
41
Card image cap
Bag of Tricks for Efficient Text Classification
This paper explores a simple and efficient baseline for text classification. Our experiments show that our fast text classifier fastText is often on par with deep learning classifiers in terms of accuracy, and many orders of magnitude faster for training and evaluation.

16,365
0.11 stars / hour
4196674373  Code
42
Card image cap
fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
2,472
0.10 stars / hour
 Paper  Code
43
Card image cap
Auto-Keras: Efficient Neural Architecture Search with Network Morphism
Neural architecture search (NAS) has been proposed to automatically tune deep neural networks, but existing search algorithms usually suffer from expensive computational cost. Network morphism, which keeps the functionality of a neural network while changing its neural architecture, could be helpful for NAS by enabling a more efficient training during the search.
3,676
0.10 stars / hour
 Paper  Code
44
Card image cap
DensePose: Dense Human Pose Estimation In The Wild
In this work, we establish dense correspondences between RGB image and a surface-based representation of the human body, a task we refer to as dense human pose estimation. We first gather dense correspondences for 50K persons appearing in the COCO dataset by introducing an efficient annotation pipeline.

3,767
0.10 stars / hour
 Paper  Code
45
Card image cap
Detectron
FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.
17,555
0.10 stars / hour
5053515461  Code
46
Card image cap
SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels
We present Spline-based Convolutional Neural Networks (SplineCNNs), a variant of deep neural networks for irregular structured and geometric input, e.g., graphs or meshes. Our main contribution is a novel convolution operator based on B-splines, that makes the computation time independent from the kernel size due to the local support property of the B-spline basis functions.
769
0.10 stars / hour
 Paper  Code
47
Card image cap
A guide to convolution arithmetic for deep learning
We introduce a guide to help deep learning practitioners understand and manipulate convolutional neural network architectures. The guide clarifies the relationship between various properties (input shape, kernel shape, zero padding, strides and output shape) of convolutional, pooling and transposed convolutional layers, as well as the relationship between convolutional and transposed convolutional layers.

5,062
0.10 stars / hour
939-419-0310  Code
48
Card image cap
Horizon
A platform for Applied Reinforcement Learning (Applied RL)

1,249
0.09 stars / hour
case  Code
49
Card image cap
modAL: A modular active learning framework for Python
modAL is a modular active learning framework for Python, aimed to make active learning research and practice simpler. Its distinguishing features are (i) clear and modular object oriented design (ii) full compatibility with scikit-learn models and workflows.

295
0.09 stars / hour
 Paper  Code
50
Card image cap
Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates
Subword units are an effective way to alleviate the open vocabulary problems in neural machine translation (NMT). While sentences are usually converted into unique subword sequences, subword segmentation is potentially ambiguous and multiple segmentations are possible even with the same vocabulary.

1,654
0.09 stars / hour
 Paper  Code
51
Card image cap
Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
Also, most NMT systems have difficulty with rare words. These issues have hindered NMT's use in practical deployments and services, where both accuracy and speed are essential.

1,654
0.09 stars / hour
(914) 254-4614  Code
52
Card image cap
Efficient Contextualized Representation: Language Model Pruning for Sequence Labeling
Many efforts have been made to facilitate natural language processing tasks with pre-trained language models (LMs), and brought significant improvements to various applications. To fully leverage the nearly unlimited corpora and capture linguistic information of multifarious levels, large-size LMs are required; but for a specific task, only parts of these information are useful.

80
0.09 stars / hour
 Paper  Code