Generating Furry Cars: Disentangling Object Shape and Appearance across Multiple Domains

This is an interesting paper about learning and combining representations of object shape and appearance from the different domains (for example, dogs and cars). This allows to create a model, which borrows different properties from each domain and generates images, which don't exist in a single domain.
The main idea is the following:
- use FineGAN as a base model;
- represent object appearance with a differentiable histogram of visual features;
- optimize the generator so that images with different shapes but similar appearances produce similar histograms;

Paper: https://openreview.net/forum?id=M88oFvqp_9
Project link: https://utkarshojha.github.io/inter-domain-gan/
Code will be available here: https://github.com/utkarshojha/inter-domain-gan

A detailed unofficial overview of the paper: https://andlukyane.com/blog/paper-review-furrycars

#cv #gan #deeplearning #contrastivelearning

Starting -1 Data Science Breakfast as an audio chat

Today @ 🕙11:00 CET.
☕️ 🥐🇫🇷 Parisian Data Breakfast will be held online 🌐! See you soon at
https://spatial.chat/s/DataBreakfast

Self-supervision paper from arxiv for histopathology CV.

Authors draw inspiration from the process of how histopathologists tend to review the images, and how those images are stored. Histopathology images are multiscale slices of enormous size (tens of thousands pixels by one side), and area experts constantly move through different levels of magnification to keep in mind both fine and coarse structures of the tissue.

Therefore, in this paper the loss is proposed to capture relation between different magnification levels. Authors propose to train network to order concentric patches by their magnification level. They organise it as the classification task — network to predict id of the order permutation instead of predicting order itself.

Also, authors proposed specific architecture for this task and appended self-training procedure, as it was shown to boost results even after pre-training.

All this allows them to reach quality increase even in high-data regime.

My description of the architecture and loss expanded here.
Source of the work here.

Unsupervised 3D Neural Rendering of Minecraft Worlds

Work on unsupervised neural rendering framework for generating photorealistic images of Minecraft (or any large 3D block worlds).

Why this is cool: this is a step towards better graphics for games.

Project Page: https://nvlabs.github.io/GANcraft/
YouTube: https://www.youtube.com/watch?v=1Hky092CGFQ&t=2s

#GAN #Nvidia #Minecraft

Awesome graph repos

Collections of methods and papers for specific graph topics.

Graph-based Deep Learning Literature — Links to Conference Publications and the top 10 most-cited publications, Related workshops, Surveys / Literature Reviews / Books in graph-based deep learning.

awesome-graph-classification — A collection of graph classification methods, covering embedding, deep learning, graph kernel and factorization papers with reference implementations.

Awesome-Graph-Neural-Networks — A collection of resources related with graph neural networks..

awesome-graph — A curated list of resources for graph databases and graph computing tools

awesome-knowledge-graph — A curated list of Knowledge Graph related learning materials, databases, tools and other resources.

awesome-knowledge-graph — A curated list of awesome knowledge graph tutorials, projects and communities.

Awesome-GNN-Recommendation — graph mining for recommender systems.

awesome-graph-attack-papers — links to works about adversarial attacks and defenses on graph data or GNNs.

Graph-Adversarial-Learning — Attack-related papers, Defense-related papers, Robustness Certification papers, etc., ranging from 2017 to 2021.

awesome-self-supervised-gnn — Papers about self-supervised learning on GNNs.

awesome-self-supervised-learning-for-graphs — A curated list for awesome self-supervised graph representation learning resources.

Awesome-Graph-Contrastive-Learning — Collection of resources related with Graph Contrastive Learning.

Starting 0 Data Breakfast as an audio chat in this channel in 15 minutes.

This is an informal online event where you can discuss anything related to Data Science (even vaguely related).

Researchers from Berkeley rolled out VideoGPT - a transformer that generates videos.

The results are not super "WOW", but the architecture is quite simple and now it can be a starting point for all future work in this direction. As you know, GPT-3 for text generation was also not built right away. So let's will wait for method acceleration and quality improvement.

📝Paper
⚙️Code
🌐Project page
🃏Demo

For almost 5 years channel picture beared arbitrary picture found in google and now we updated it with a proper new channel logo generated by neural network. Do you like it?

The Annotated Transformer

3 years ago Alexander Rush created an incredible notebook supported the "Attention is All You Need" paper giving a possibility to dive in the implementation details and obtain your own transformer :)

We, SkoltechNLP group, within our Neual NLP 2021 course revisited this notebook for adapting it as a seminar. Of course, the original code was created 3 years ago and in some places is incompatible with new versions of required libraries. As a result, we created "runnable with 'Run all Cells' for April 2021" version of this notebook:
https://github.com/skoltech-nlp/annotated-transformer

So if you want to learn the Transformer and run an example in your computer or Colab, you can save your time and use current version of this great notebook. Also, we add some links to the amazing resources about Transformers that emerged during these years:
* Seq2Seq and Attention by Lena Voita;
* The Illustrated Transformer.

Enjoy your Transformer! And be free to ask any questions and leave comments.

​​MDETR: Modulated Detection for End-to-End Multi-Modal Understanding

Multi-modal reasoning systems rely on a pre-trained object detector to extract regions of interest from the image. However, this crucial module is typically used as a black box, trained independently of the downstream task and on a fixed vocabulary of objects and attributes.
The authors present an end-to-end approach to multi-modal reasoning systems, which works much better than using a separate pre-trained decoder.
They pre-train the network on 1.3M text-image pairs, mined from pre-existing multi-modal datasets having explicit alignment between phrases in text and objects in the image.
Fine-tuning this model achieves new SOTA results on phrase grounding, referring expression comprehension, and segmentation tasks. The approach could be extended to visual question answering.
Furthermore, the model is capable of handling the long tail of object categories.

Paper: https://arxiv.org/abs/2104.12763
Code: https://github.com/ashkamath/mdetr

A detailed unofficial overview of the paper: https://andlukyane.com/blog/paper-review-mdetr

#deeplearning #multimodalreasoning #transformer