Trending Research

An Attention Free Transformer

labmlai/annotated_deep_learning_paper_implementations 28 May 2021

We introduce Attention Free Transformer (AFT), an efficient variant of Transformers that eliminates the need for dot product self attention.

0.12 stars / hour

FNet: Mixing Tokens with Fourier Transforms

labmlai/annotated_deep_learning_paper_implementations 9 May 2021

We show that Transformer encoder architectures can be massively sped up, with limited accuracy costs, by replacing the self-attention sublayers with simple linear transformations that "mix" input tokens.

Linguistic Acceptability Machine Translation +5

0.12 stars / hour

ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinement

yuval-alaluf/restyle-encoder 6 Apr 2021

Instead of directly predicting the latent code of a given real image using a single pass, the encoder is tasked with predicting a residual with respect to the current estimate of the inverted latent code in a self-correcting manner.

Image Generation

0.12 stars / hour
0.12 stars / hour

Itihasa: A large-scale corpus for Sanskrit to English translation

rahular/itihasa 6 Jun 2021

This work introduces Itihasa, a large-scale translation dataset containing 93, 000 pairs of Sanskrit shlokas and their English translations.

0.12 stars / hour

Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning

researchmm/soho 7 Apr 2021

As region-based visual features usually represent parts of an image, it is challenging for existing vision-language models to fully understand the semantics from paired natural languages.

Representation Learning

0.12 stars / hour

Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts

facebookresearch/ContrastiveSceneContexts 16 Dec 2020

The rapid progress in 3D scene understanding has come with growing demand for data; however, collecting and annotating 3D scenes (e. g. point clouds) are notoriously hard.

Instance Segmentation Scene Understanding +1

0.12 stars / hour

GAN Prior Embedded Network for Blind Face Restoration in the Wild

yangxy/GPEN 13 May 2021

The proposed GAN prior embedded network (GPEN) is easy-to-implement, and it can generate visually photo-realistic results.

Blind Face Restoration Image Generation

0.11 stars / hour

Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers

lkeab/BCNet 23 Mar 2021

Segmenting highly-overlapping objects is challenging, because typically no distinction is made between real object contours and occlusion boundaries.

Amodal Instance Segmentation Boundary Detection +4

0.11 stars / hour

Sensitive Data Detection with High-Throughput Neural Network Models for Financial Institutions

capitalone/DataProfiler 17 Dec 2020

However, the application of sensitive entity detection for production systems in financial institutions has not been well explored due to the lack of publicly available, labeled datasets.

Named Entity Recognition

0.11 stars / hour