Trending Research

Demucs: Deep Extractor for Music Sources with extra unlabeled data remixed

3 Sep 2019facebookresearch/demucs

We study the problem of source separation for music using deep learning with four known sources: drums, bass, vocals and other accompaniments.

MUSIC SOURCE SEPARATION

876
2.21 stars / hour

Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation

20 Sep 2018facebookresearch/demucs

The majority of the previous methods have formulated the separation problem through the time-frequency representation of the mixed signal, which has several drawbacks, including the decoupling of the phase and magnitude of the signal, the suboptimality of time-frequency representation for speech separation, and the long latency in calculating the spectrograms.

SPEAKER SEPARATION SPEECH SEPARATION

876
2.21 stars / hour

Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs

30 Mar 2016granne/granne

We present a new approach for the approximate K-nearest neighbor search based on navigable small world graphs with controllable hierarchy (Hierarchical NSW, HNSW).

118
1.52 stars / hour

AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty

5 Dec 2019google-research/augmix

We propose AugMix, a data processing technique that is simple to implement, adds limited computational overhead, and helps models withstand unforeseen corruptions.

IMAGE CLASSIFICATION

212
1.16 stars / hour

Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection

5 Dec 2019sfzhang15/ATSS

In this paper, we first point out that the essential difference between anchor-based and anchor-free detection is actually how to define positive and negative training samples, which leads to the performance gap between them.

OBJECT DETECTION

194
1.07 stars / hour

TinyBERT: Distilling BERT for Natural Language Understanding

23 Sep 2019huawei-noah/Pretrained-Language-Model

To accelerate inference and reduce model size while maintaining accuracy, we firstly propose a novel transformer distillation method that is a specially designed knowledge distillation (KD) method for transformer-based models.

LANGUAGE MODELLING LINGUISTIC ACCEPTABILITY NATURAL LANGUAGE INFERENCE QUESTION ANSWERING SEMANTIC TEXTUAL SIMILARITY

405
0.84 stars / hour

Plug and Play Language Models: a Simple Approach to Controlled Text Generation

4 Dec 2019uber-research/PPLM

Large transformer-based language models (LMs) trained on huge text corpora have shown unparalleled generation capabilities.

LANGUAGE MODELLING TEXT GENERATION

209
0.78 stars / hour

EmbedMask: Embedding Coupling for One-stage Instance Segmentation

4 Dec 2019yinghdb/EmbedMask

The pixel-level clustering enables EmbedMask to generate high-resolution masks without missing details from repooling, and the existence of proposal embedding simplifies and strengthens the clustering procedure to achieve high speed with higher performance than segmentation-based methods.

INSTANCE SEGMENTATION SEMANTIC SEGMENTATION

85
0.77 stars / hour

StarGAN v2: Diverse Image Synthesis for Multiple Domains

4 Dec 2019clovaai/stargan-v2

A good image-to-image translation model should learn a mapping between different visual domains while satisfying the following properties: 1) diversity of generated images and 2) scalability over multiple domains.

IMAGE-TO-IMAGE TRANSLATION

281
0.69 stars / hour

TensorNetwork on TensorFlow: A Spin Chain Application Using Tree Tensor Networks

3 May 2019google/TensorNetwork

TensorNetwork is an open source library for implementing tensor network algorithms in TensorFlow.

TENSOR NETWORKS

1,042
0.69 stars / hour