Trending Research

FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence

21 Jan 2020google-research/fixmatch

Semi-supervised learning (SSL) provides an effective means of leveraging unlabeled data to improve a model's performance.

SEMI-SUPERVISED IMAGE CLASSIFICATION

126
1.58 stars / hour
156
1.05 stars / hour

Reformer: The Efficient Transformer

13 Jan 2020google/trax

Large Transformer models routinely achieve state-of-the-art results on a number of tasks but training these models can be prohibitively costly, especially on long sequences.

LANGUAGE MODELLING

1,513
0.71 stars / hour

Soft Actor-Critic Algorithms and Applications

13 Dec 2018denisyarats/pytorch_sac

A fork of OpenAI Baselines, implementations of reinforcement learning algorithms

DECISION MAKING

43
0.70 stars / hour

adet

2 Jan 2020aim-uofa/adet

AdelaiDet is an open source toolbox for multiple instance-level detection applications.

INSTANCE SEGMENTATION SEMANTIC SEGMENTATION

28
0.70 stars / hour

Depth-Aware Video Frame Interpolation

CVPR 2019 baowenbo/DAIN

The proposed model then warps the input frames, depth maps, and contextual features based on the optical flow and local interpolation kernels for synthesizing the output frame.

OPTICAL FLOW ESTIMATION VIDEO FRAME INTERPOLATION

699
0.65 stars / hour

Augmenting Self-attention with Persistent Memory

2 Jul 2019lucidrains/reformer-pytorch

More precisely, we augment the self-attention layers with persistent memory vectors that play a similar role as the feed-forward layer.

LANGUAGE MODELLING

374
0.54 stars / hour

rasa

WS 2019 RasaHQ/rasa

💬 Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants

SPOKEN DIALOGUE SYSTEMS

7,615
0.40 stars / hour

Automatically Annotated Turkish Corpus for Named Entity Recognition and Text Categorization using Large-Scale Gazetteers

8 Feb 2017juand-r/entity-recognition-datasets

Turkish Wikipedia Named-Entity Recognition and Text Categorization (TWNERTC) dataset is a collection of automatically categorized and annotated sentences obtained from Wikipedia.

NAMED ENTITY RECOGNITION TEXT CATEGORIZATION

494
0.37 stars / hour

DDSP: Differentiable Digital Signal Processing

14 Jan 2020magenta/ddsp

In this paper, we introduce the Differentiable Digital Signal Processing (DDSP) library, which enables direct integration of classic signal processing elements with deep learning methods.

AUDIO GENERATION

971
0.37 stars / hour