Mega: Moving Average Equipped Gated Attention

facebookresearch/mega 21 Sep 2022

The design choices in the Transformer attention mechanism, including weak inductive bias and quadratic computational complexity, have limited its application for modeling long sequences.

Image Classification +3

102
0.35 stars / hour

MobileViTv3: Mobile-Friendly Vision Transformer with Simple and Effective Fusion of Local, Global and Input Features

microndla/mobilevitv3 30 Sep 2022

We propose changes to the fusion block that are simple and effective to create MobileViTv3-block, which addresses the scaling and simplifies the learning task.

20
0.32 stars / hour

Elucidating the Design Space of Diffusion-Based Generative Models

crowsonkb/k-diffusion 1 Jun 2022

We argue that the theory and practice of diffusion-based generative models are currently unnecessarily convoluted and seek to remedy the situation by presenting a design space that clearly separates the concrete design choices.

Image Generation

573
0.28 stars / hour

A Lightweight Instrument-Agnostic Model for Polyphonic Note Transcription and Multipitch Estimation

spotify/basic-pitch 18 Mar 2022

Despite its simplicity, benchmark results show our system's note estimation to be substantially better than a comparable baseline, and its frame-level accuracy to be only marginally below those of specialized state-of-the-art AMT systems.

Music Transcription

1,147
0.27 stars / hour

Uncertainty-Driven Active Vision for Implicit Scene Reconstruction

facebookresearch/uncertainty-driven-active-vision 3 Oct 2022

We evaluate our proposed approach on the ABC dataset and the in the wild CO3D dataset, and show that: (1) we are able to obtain high quality state-of-the-art occupancy reconstructions; (2) our perspective conditioned uncertainty definition is effective to drive improvements in next best view selection and outperforms strong baseline approaches; and (3) we can further improve shape understanding by performing a gradient-based search on the view selection candidates.

Scene Understanding

9
0.24 stars / hour

Diffusion Posterior Sampling for General Noisy Inverse Problems

dps2022/diffusion-posterior-sampling 29 Sep 2022

Diffusion models have been recently studied as powerful generative inverse problem solvers, owing to their high quality reconstructions and the ease of combining existing iterative solvers.

Deblurring

31
0.26 stars / hour

EditEval: An Instruction-Based Benchmark for Text Improvements

facebookresearch/editeval 27 Sep 2022

Evaluation of text generation to date has primarily focused on content created sequentially, rather than improvements on a piece of text.

Text Generation

99
0.21 stars / hour

Text-Guided Neural Image Inpainting

idealwhite/tdanet 7 Apr 2020

To fulfill such a task, we propose a novel inpainting model named Text-Guided Dual Attention Inpainting Network (TDANet).

Image Inpainting Semantic Similarity +2

74
0.21 stars / hour

River: machine learning for streaming data in Python

online-ml/river 8 Dec 2020

It is the result from the merger of the two most popular packages for stream learning in Python: Creme and scikit-multiflow.

BIG-bench Machine Learning Continual Learning

3,712
0.20 stars / hour

TSInterpret: A unified framework for time series interpretability

fzi-forschungszentrum-informatik/TSInterpret 10 Aug 2022

With the increasing application of deep learning algorithms to time series classification, especially in high-stake scenarios, the relevance of interpreting those algorithms becomes key.

Interpretable Machine Learning Time Series Classification

30
0.20 stars / hour