From data to functa: Your data point is a function and you can treat it like one

deepmind/functa 28 Jan 2022

A powerful continuous alternative is then to represent these measurements using an implicit neural representation, a neural function trained to output the appropriate measurement value for any input spatial location.

Imputation Novel View Synthesis

35
0.33 stars / hour

Neural Architectures for Named Entity Recognition

PKU-TANGENT/nlp-tutorial NAACL 2016

State-of-the-art named entity recognition systems rely heavily on hand-crafted features and domain-specific knowledge in order to learn effectively from the small, supervised training corpora that are available.

named-entity-recognition NER

196
0.32 stars / hour

Text2Light: Zero-Shot Text-Driven HDR Panorama Generation

frozenburning/text2light 20 Sep 2022

To achieve super-resolution inverse tone mapping, we derive a continuous representation of 360-degree imaging from the LDR panorama as a set of structured latent codes anchored to the sphere.

inverse tone mapping Inverse-Tone-Mapping +2

207
0.30 stars / hour

An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion

rinongal/textual_inversion 2 Aug 2022

Yet, it is unclear how such freedom can be exercised to generate images of specific unique concepts, modify their appearance, or compose them in new roles and novel scenes.

Text to image generation Text-to-Image Generation

1,318
0.29 stars / hour

Acme: A Research Framework for Distributed Reinforcement Learning

deepmind/acme 1 Jun 2020

These implementations serve both as a validation of our design decisions as well as an important contribution to reproducibility in RL research.

DQN Replay Dataset reinforcement-learning

2,844
0.29 stars / hour

Quality-Aware Memory Network for Interactive Volumetric Image Segmentation

0liliulei/Mem3D 20 Jun 2021

The proposed network has two appealing characteristics: 1) The memory-augmented network offers the ability to quickly encode past segmentation information, which will be retrieved for the segmentation of other slices; 2) The quality assessment module enables the model to directly estimate the qualities of segmentation predictions, which allows an active learning paradigm where users preferentially label the lowest-quality slice for multi-round refinement.

Active Learning Image Segmentation +3

56
0.29 stars / hour

HiFuse: Hierarchical Multi-Scale Feature Fusion Network for Medical Image Classification

huoxiangzuo/HiFuse 21 Sep 2022

A parallel hierarchy of local and global feature blocks is designed to efficiently extract local features and global representations at various semantic scales, with the flexibility to model at different scales and linear computational complexity relevant to image size.

Image Classification Inductive Bias +1

47
0.28 stars / hour

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

4,044
0.27 stars / hour

Omni-Dimensional Dynamic Convolution

osvai/odconv ICLR 2022

Learning a single static convolutional kernel in each convolutional layer is the common training paradigm of modern Convolutional Neural Networks (CNNs).

89
0.25 stars / hour
2,845
0.25 stars / hour