Weakly-Supervised Semantic Segmentation with Visual Words Learning and Hybrid Pooling

Github: https://github.com/rulixiang/vwe/tree/master/v2

Paper: https://arxiv.org/abs/2202.04812v1

Dataset: https://paperswithcode.com/dataset/pascal-voc

@ArtificialIntelligencedl

Image-to-Image Regression with Distribution-Free Uncertainty Quantification and Applications in Imaging

Github: https://github.com/aangelopoulos/im2im-uq

Paper: https://arxiv.org/abs/2202.05265v1

Dataset: https://paperswithcode.com/dataset/fastmri

@ArtificialIntelligencedl

The Shapley Value in Machine Learning

Github: https://github.com/benedekrozemberczki/shapley

Documentation: https://shapley.readthedocs.io/

Paper: https://arxiv.org/abs/2101.02153

Help: https://shapley.readthedocs.io/en/latest/notes/resources.html

@ArtificialIntelligencedl

3 февраля – 3 апреля участвуйте в соревновании Data Fusion Contest 2022 от ВТБ с призовым фондом в 2 000 000 рублей!

Прокачайтесь в современном индустриальном ML на прорывной задаче матчинга.

Вас ждёт 3 задачи, 2 специальные номинации и уникальный датасет от ВТБ, «Ростелекома» и Platforma.

Data Fusion Contest 2022 — это отличная возможность:

🔹 Принять участие в большом онлайн-соревновании с крупными призовыми

🔹 Прокачаться в DS/ML и новых методах на практической задаче

🔹 Участвовать в митапах, воркшопах и гостевых лекциях

🔹 Выиграть классный мерч

Подробности и регистрация — на сайте.

🔹 Expediting Vision Transformers via Token Reorganizations

Github: https://github.com/youweiliang/evit

Paper: https://arxiv.org/abs/2202.07800v1

Dataset: https://paperswithcode.com/dataset/imagenet

@ArtificialIntelligencedl

🔦 cosFormer: Rethinking Softmax in Attention

Github: https://github.com/davidsvy/cosformer-pytorch

Paper: https://arxiv.org/abs/2202.08791v1

@ArtificialIntelligencedl

🛠 ZeroGen: Efficient Zero-shot Learning via Dataset Generation

Github: https://github.com/jiacheng-ye/zerogen

Paper: https://arxiv.org/abs/2202.07922v1

Dataset: https://paperswithcode.com/dataset/sst

@ArtificialIntelligencedl

TransCG: A Large-Scale Real-World Dataset for Transparent Object Depth Completion and Grasping

Github: https://github.com/galaxies99/transcg

Paper: https://arxiv.org/pdf/2202.08471v1.pdf

Dataset: https://graspnet.net/transcg

@ArtificialIntelligencedl

Design-Bench: Benchmarks for Data-Driven Offline Model-Based Optimization

Github: https://github.com/rail-berkeley/design-bench

Paper: https://arxiv.org/abs/2202.08450v1

Dataset: https://paperswithcode.com/dataset/openai-gym

@ArtificialIntelligencedl

PointSCNet: Point Cloud Structure and Correlation Learning Based on Space Filling Curve-Guided Sampling

Github: https://github.com/Chenguoz/PointSCNet

Paper: https://arxiv.org/abs/2202.10251v1

Dataset: https://paperswithcode.com/dataset/modelnet

@ArtificialIntelligencedl

EIGNN: Efficient Infinite-Depth Graph Neural Networks

Github: https://github.com/liu-jc/eignn

Paper: https://arxiv.org/abs/2202.10720v1

Dataset: https://paperswithcode.com/dataset/ppi

@ArtificialIntelligencedl

Coverage-Guided Tensor Compiler Fuzzing with Joint IR-Pass Mutation

Github: https://github.com/tzer-anonbot/tzer

Docs: https://tzer.readthedocs.io/en/latest/markdown/artifact.html

Paper: https://arxiv.org/abs/2202.09947v1


@ai_machinelearning_big_data

Bag Graph: Multiple Instance Learning using Bayesian Graph Neural Networks

Github: https://github.com/networkslab/baggraph

Paper: https://arxiv.org/abs/2202.11132v1


@ai_machinelearning_big_data

✅ As-ViT: Auto-scaling Vision Transformers without Training

Github: https://github.com/vita-group/asvit

Paper: https://arxiv.org/abs/2202.11921v1

Dataset: https://paperswithcode.com/dataset/imagenet

@ArtificialIntelligencedl

DeepFusionMOT: A 3D Multi-Object Tracking Framework Based on Camera-LiDAR Fusion with Deep Association

Github: https://github.com/wangxiyang2022/DeepFusionMOT

Paper: https://arxiv.org/abs/2202.12100v1

Dataset: https://paperswithcode.com/dataset/kitti

@ArtificialIntelligencedl

Overcoming catastrophic forgetting in neural networks

Github: https://github.com/ContinualAI/avalanche

Paper: https://arxiv.org/abs/1612.00796v2

Dataset: https://paperswithcode.com/dataset/asc-til-19-tasks

@ArtificialIntelligencedl

The Neural Testbed

Github: https://github.com/deepmind/neural_testbed

Paper: https://arxiv.org/abs/2202.13509v1

@ArtificialIntelligencedl

FastFold: Reducing AlphaFold Training Time from 11 Days to 67 Hours

Github: https://github.com/hpcaitech/fastfold

Paper: https://arxiv.org/abs/2203.00854v1

@ArtificialIntelligencedl

💡 KG Inductive Link Prediction Challenge (ILPC) 2022

Github: https://github.com/pykeen/ilpc2022

Paper: https://arxiv.org/abs/2203.01520v1

@ArtificialIntelligencedl

Hello everyone. My name is Andrew and for several years I've been working on to make the learning path for ML
easier.

I wrote a manual on machine learning that
everyone understands - Machine Learning Simplified Book. The main purpose of my book is to build an intuitive
understanding of how algorithms work through basic examples. In order to understand the presented material,
it is enough to know basic mathematics and linear algebra.

After reading this book, you will know the basics of supervised learning, understand complex mathematical models, understand the entire pipeline of a typical ML project, and also be able to share your knowledge with colleagues from related industries and with technical
professionals.

And for those who find the theoretical part not enough - I supplemented the book with a repository on GitHub,
which has Python implementation of every method and algorithm that I describe in each chapter.

You can read the book absolutely free at the link below:
-> https://themlsbook.com

I’ve also started my Instagram page - feel free to subscribe! it’s mostly in Russian but I’ll be posting in English too.
-> https://instagram.com/5x12

KG Inductive Link Prediction Challenge (ILPC) 2022

Github: https://github.com/pykeen/ilpc2022

Paper: https://github.com/pykeen/ilpc2022

@ArtificialIntelligencedl