ASSET: Autoregressive Semantic Scene Editing with Transformers at High Resolutions

difanliu/asset 24 May 2022

We present ASSET, a neural architecture for automatically modifying an input high-resolution image according to a user's edits on its semantic segmentation map.

Semantic Segmentation

49
0.50 stars / hour

Hierarchical Text-Conditional Image Generation with CLIP Latents

lucidrains/DALLE2-pytorch 13 Apr 2022

Contrastive models like CLIP have been shown to learn robust representations of images that capture both semantics and style.

Ranked #5 on Text-to-Image Generation on COCO (using extra training data)

Conditional Image Generation Zero-Shot Text-to-Image Generation

5,139
0.46 stars / hour

AvatarCLIP: Zero-Shot Text-Driven Generation and Animation of 3D Avatars

hongfz16/avatarclip 17 May 2022

Our key insight is to take advantage of the powerful vision-language model CLIP for supervising neural human generation, in terms of 3D geometry, texture and animation.

Language Modelling motion synthesis +1

338
0.43 stars / hour

Extracting Triangular 3D Models, Materials, and Lighting From Images

NVlabs/nvdiffrec 24 Nov 2021

We present an efficient method for joint optimization of topology, materials and lighting from multi-view image observations.

720
0.42 stars / hour

Compressing Deep Graph Neural Networks via Adversarial Knowledge Distillation

MIRALab-USTC/GraphAKD 24 May 2022

To tackle these problems, we propose a novel Adversarial Knowledge Distillation framework for graph models named GraphAKD, which adversarially trains a discriminator and a generator to adaptively detect and decrease the discrepancy.

Graph Classification Knowledge Distillation +1

11
0.42 stars / hour

Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localization

lukemelas/deep-spectral-segmentation 16 May 2022

We find that these eigenvectors already decompose an image into meaningful segments, and can be readily used to localize objects in a scene.

graph partitioning Unsupervised Semantic Segmentation

69
0.38 stars / hour

PaddleNLP

PaddlePaddle/PaddleNLP NeurIPS 2020

Easy-to-use and powerful NLP library with Awesome model zoo, supporting wide-range of NLP tasks from research to industrial applications, including Neural Search, Question Answering, Information Extraction and Sentiment Analysis end-to-end system.

Natural Language Understanding

4,215
0.38 stars / hour

Colossal-AI: A Unified Deep Learning System For Large-Scale Parallel Training

hpcaitech/colossalai 28 Oct 2021

The Transformer architecture has improved the performance of deep learning models in domains such as Computer Vision and Natural Language Processing.

3,568
0.38 stars / hour

Zero-Shot Text-to-Image Generation

borisdayma/dalle-mini 24 Feb 2021

Text-to-image generation has traditionally focused on finding better modeling assumptions for training on a fixed dataset.

Ranked #11 on Text-to-Image Generation on COCO (using extra training data)

Text to image generation Zero-Shot Text-to-Image Generation

1,587
0.36 stars / hour

GraphMAE: Self-Supervised Masked Graph Autoencoders

thudm/graphmae 22 May 2022

Despite this, contrastive learning--which heavily relies on structural data augmentation and complicated training strategies--has been the dominant approach in graph SSL, while the progress of generative SSL on graphs, especially graph autoencoders (GAEs), has thus far not reached the potential as promised in other fields.

Contrastive Learning Data Augmentation +2

21
0.36 stars / hour