Projects

latest | popular

Filter by
DETR: End-to-End Object Detection with Transformers
A new method that views object detection as a direct set prediction problem.
object-detection image-segmentation panoptic-segmentation transformers
VirTex: Learning Visual Representations from Textual Annotations
We train CNN+Transformer from scratch from COCO, transfer the CNN to 6 downstream vision tasks, and exceed ImageNet features despite using 10x fewer ...
convolutional-neural-networks transformers coco visual-representations
Self-Supervised Scene De-occlusion
We investigate the problem of scene de-occlusion, which aims to recover the underlying occlusion ordering and complete the invisible parts of occluded ...
self-supervised-learning computer-vision de-occlusion image-generation
The Lottery Ticket Hypothesis: A Survey
Dive deeper into the lottery ticket hypothesis and review the literature after the original ICLR best paper award by Frankle & Carbin (2019).
lottery-ticket-hypothesis survey deep-learning article
How to Steal Modern NLP Systems with Gibberish?
It’s possible to steal BERT-based models without any real training data, even using gibberish word sequences.
bert adversarial-attacks computer-security adversarial-learning
NeuralCook — Image2Ingredients and Cooking Recommendation
Deep learning application to identify ingredients from cooking dishes images and recommend dishes to cook, given a set of ingredients.
cooking text-generation recommendation-systems joint-embeddings
BERTology Meets Biology
Interpreting Attention in Protein Language Models.
bert healthcare biology health
Image GPT: Generative Pretraining from Pixels
Transformers trained on pixel sequences can generate coherent image completions and samples.
transformers openai computer-vision image-completion
STEFANN: Scene Text Editor using Font Adaptive Neural Network
A generalized method for realistic modification of textual content present in a scene image. ⭐️ Accepted in CVPR 2020.
scene-image scene-text-editor font-adaptive font-generation
BLiTZ — A Bayesian Neural Network library for PyTorch
Bayesian Layers in Torch Zoo is a simple and extensible library to create Bayesian Neural Network layers on the top of PyTorch.
bayesian-deep-learning pytorch blitz bayesian-neural-networks
projects 1 - 10 of 136
Topic experts
Share your project
Discover, build and share what you've made with ML.
Share someone else's project
Share something interesting you found that's made with ML.