Text-Guided Synthesis of Artistic Images with Retrieval-Augmented Diffusion Models

compvis/latent-diffusion 26 Jul 2022

In RDMs, a set of nearest neighbors is retrieved from an external database during training for each training instance, and the diffusion model is conditioned on these informative samples.

Image Generation Prompt Engineering

2,633
0.45 stars / hour

Elucidating the Design Space of Diffusion-Based Generative Models

lucidrains/imagen-pytorch 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

4,672
0.42 stars / hour

Deepchecks: A Library for Testing and Validating Machine Learning Models and Data

deepchecks/deepchecks 16 Mar 2022

This paper presents Deepchecks, a Python library for comprehensively validating machine learning models and data.

BIG-bench Machine Learning

1,892
0.40 stars / hour

Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation

cardwing/codes-for-pvkd CVPR 2022

This article addresses the problem of distilling knowledge from a large teacher model to a slim student network for LiDAR semantic segmentation.

3D Semantic Segmentation Knowledge Distillation +1

281
0.38 stars / hour

FRA-RIR: Fast Random Approximation of the Image-source Method

yluo42/fra-rir 8 Aug 2022

The training of modern speech processing systems often requires a large amount of simulated room impulse response (RIR) data in order to allow the systems to generalize well in real-world, reverberant environments.

Denoising Speech Denoising

62
0.38 stars / hour

GPT-NeoX-20B: An Open-Source Autoregressive Language Model

labmlai/annotated_deep_learning_paper_implementations BigScience (ACL) 2022

We introduce GPT-NeoX-20B, a 20 billion parameter autoregressive language model trained on the Pile, whose weights will be made freely and openly available to the public through a permissive license.

Language Modelling

11,436
0.36 stars / hour

Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN

Westlake-AI/openmixup 27 May 2022

We observe that MIM essentially teaches the model to learn better middle-level interactions among patches and extract more generalized features.

Image Classification Self-Supervised Learning

116
0.36 stars / hour

ferret: a Framework for Benchmarking Explainers on Transformers

g8a9/ferret 2 Aug 2022

Many interpretability tools allow practitioners and researchers to explain Natural Language Processing systems.

Natural Language Processing

83
0.34 stars / hour

Patching open-vocabulary models by interpolating weights

mlfoundations/patching 10 Aug 2022

We study model patching, where the goal is to improve accuracy on specific tasks without degrading accuracy on tasks where performance is already adequate.

Image Classification

13
0.33 stars / hour

towhee

towhee-io/towhee ICCV 2019

Towhee is a framework that is dedicated to making neural data processing pipelines simple and fast.

Action Classification Action Recognition +4

921
0.33 stars / hour