Trending Research

Self-supervised Pretraining of Visual Features in the Wild

2 Mar 2021facebookresearch/vissl

Recently, self-supervised learning methods like MoCo, SimCLR, BYOL and SwAV have reduced the gap with supervised methods.

 Ranked #1 on Self-Supervised Image Classification on ImageNet (finetuned) (using extra training data)

SELF-SUPERVISED IMAGE CLASSIFICATION SELF-SUPERVISED LEARNING SEMI-SUPERVISED IMAGE CLASSIFICATION

692
3.53 stars / hour

ContraGAN: Contrastive Learning for Conditional Image Generation

NeurIPS 2020 POSTECH-CVLab/PyTorch-StudioGAN

The discriminator of ContraGAN discriminates the authenticity of given samples and minimizes a contrastive objective to learn the relations between training images.

CONDITIONAL IMAGE GENERATION DATA AUGMENTATION

1,435
3.37 stars / hour

Generative Adversarial Transformers

1 Mar 2021dorarad/gansformer

We introduce the GANsformer, a novel and efficient type of transformer, and explore it for the task of visual generative modeling.

 Ranked #1 on Image Generation on LSUN Bedroom 256 x 256 (FID-10k-training-steps metric)

IMAGE GENERATION SCENE GENERATION

279
2.12 stars / hour

WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning

2 Mar 2021google-research-datasets/wit

First, WIT is the largest multimodal dataset by the number of image-text examples by 3x (at the time of writing).

REPRESENTATION LEARNING TEXT-IMAGE RETRIEVAL

207
2.03 stars / hour

Towards Open World Object Detection

3 Mar 2021JosephKJ/OWOD

Humans have a natural instinct to identify unknown object instances in their environments.

OPEN WORLD OBJECT DETECTION

113
1.79 stars / hour

Recipes for building an open-domain chatbot

28 Apr 2020hyunwoongko/chattypy

Building open-domain chatbots is a challenging area for machine learning research.

CHATBOT

209
1.74 stars / hour

Monster Mash: A Single-View Approach to Casual 3D Modeling and Animation

1 Dec 2020google/monster-mash

Monster Mash is a new sketch-based modeling and animation tool that allows you to quickly sketch a character, inflate it into 3D, and promptly animate it.

IMAGE GENERATION

421
1.13 stars / hour

Transformer in Transformer

27 Feb 2021lucidrains/transformer-in-transformer

By stacking the TNT blocks, we build the TNT model for image recognition.

FINE-GRAINED IMAGE CLASSIFICATION

101
1.06 stars / hour

Image-to-image Translation via Hierarchical Style Disentanglement

2 Mar 2021imlixinyang/HiSD

Recently, image-to-image translation has made significant progress in achieving both multi-label (\ie, translation conditioned on different labels) and multi-style (\ie, generation with diverse styles) tasks.

MULTIMODAL UNSUPERVISED IMAGE-TO-IMAGE TRANSLATION

77
1.04 stars / hour

Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions

24 Feb 2021whai362/PVT

Unlike the recently-proposed Transformer model (e. g., ViT) that is specially designed for image classification, we propose Pyramid Vision Transformer~(PVT), which overcomes the difficulties of porting Transformer to various dense prediction tasks.

IMAGE CLASSIFICATION INSTANCE SEGMENTATION OBJECT DETECTION SEMANTIC SEGMENTATION

308
0.81 stars / hour