Trending Research
Demucs: Deep Extractor for Music Sources with extra unlabeled data remixed
We study the problem of source separation for music using deep learning with four known sources: drums, bass, vocals and other accompaniments.
#2 best model for
Music Source Separation
on MUSDB18
Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation
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.
Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs
We present a new approach for the approximate K-nearest neighbor search based on navigable small world graphs with controllable hierarchy (Hierarchical NSW, HNSW).
AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
We propose AugMix, a data processing technique that is simple to implement, adds limited computational overhead, and helps models withstand unforeseen corruptions.
Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection
• sfzhang15/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.
TinyBERT: Distilling BERT for Natural Language Understanding
• huawei-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.
#9 best model for
Question Answering
on SQuAD1.1 dev
LANGUAGE MODELLING LINGUISTIC ACCEPTABILITY NATURAL LANGUAGE INFERENCE QUESTION ANSWERING SEMANTIC TEXTUAL SIMILARITY
Plug and Play Language Models: a Simple Approach to Controlled Text Generation
Large transformer-based language models (LMs) trained on huge text corpora have shown unparalleled generation capabilities.
EmbedMask: Embedding Coupling for One-stage Instance Segmentation
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.
StarGAN v2: Diverse Image Synthesis for Multiple Domains
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.
TensorNetwork on TensorFlow: A Spin Chain Application Using Tree Tensor Networks
TensorNetwork is an open source library for implementing tensor network algorithms in TensorFlow.