👱‍♂️ Multiface: A Dataset for Neural Face Rendering

Github: https://github.com/facebookresearch/multiface

Paper: https://arxiv.org/abs/2207.11243v1

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

@ai_machinelearning_big_data

☀️ MAPIE - Model Agnostic Prediction Interval Estimator

MAPIE allows you to easily estimate prediction intervals (or prediction sets) using your favourite scikit-learn-compatible model for single-output regression or multi-class classification settings.

Github: https://github.com/scikit-learn-contrib/mapie

Paper: https://arxiv.org/abs/2207.12274v1

Docs: https://mapie.readthedocs.io/en/latest/

@ai_machinelearning_big_data

🔥 Practical Course Deep Learning

A 🚀free course from fast.ai learn how to apply deep learning and machine learning to practical problems.

Course
Lesson 1
Git

@ai_machinelearning_big_data

🦾 Learning Visual Representation from Modality-Shared Contrastive Language-Image Pre-training

Github: https://github.com/hxyou/msclip

Paper: https://arxiv.org/abs/2207.12661v1

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

@ai_machinelearning_big_data

🦠 Learning Protein Representations via Complete 3D Graph Networks

DIG: Dive into Graphs is a turnkey library for graph deep learning research.

Github: https://github.com/divelab/DIG

Paper: https://arxiv.org/abs/2207.12600v1

Tutorials: https://diveintographs.readthedocs.io/en/latest/tutorials/graphdf.html

Documentation: https://diveintographs.readthedocs.io/

Benchmarks: https://github.com/divelab/DIG/tree/dig-stable/benchmarks

Dataset: https://paperswithcode.com/dataset/atom3d

@ai_machinelearning_big_data

🔘 ALBench: A Framework for Evaluating Active Learning in Object Detection

An active learning benchmark framework named as ALBench for evaluating active learning in object detection.

Github: https://github.com/industryessentials/ymir

Paper: https://arxiv.org/abs/2207.13339v1

Projects: https://github.com/IndustryEssentials/ymir/projects

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

@ai_machinelearning_big_data

🔥 CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation

Github: https://github.com/huawei-noah/noah-research/tree/master/CLIFF

Paper: https://arxiv.org/abs/2208.00571v1

Pretrained checkpoints : https://drive.google.com/drive/folders/1EmSZwaDULhT9m1VvH7YOpCXwBWgYrgwP

Dataset: https://paperswithcode.com/dataset/human3-6m

@ai_machinelearning_big_data

💬 Expanding Language-Image Pretrained Models for General Video Recognition by Microsoft.

Video-specific prompting scheme, which leverages video content information for generating discriminative textual prompts.

Github: https://github.com/microsoft/VideoX/tree/master/X-CLIP

Paper: https://arxiv.org/abs/2208.02816v1

Dataset: https://paperswithcode.com/dataset/ucf101

@ai_machinelearning_big_data

➡️ Prompt Tuning for Generative Multimodal Pretrained Models

Github: https://github.com/ofa-sys/ofa

Paper: https://arxiv.org/abs/2208.02532v1

Dataset: https://paperswithcode.com/dataset/snli-ve

Demo: https://huggingface.co/spaces/OFA-Sys/OFA-Generic_Interface

@ai_machinelearning_big_data

🚀 @machinelearning_interview - в Канале собраны все возможные вопросы и ответы с собеседований по Аналитике данных и Машинному обучению. Канал от Data Analytics.

Материалы канала реально помогут подготовиться к data science собеседованию.

👉Перейти

💻 P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel Prompting

Github: https://github.com/wangzy22/P2P

Paper: https://arxiv.org/abs/2208.02812v1

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

Model: https://shapenet.cs.stanford.edu/media/modelnet40_normal_resampled.zip

@ai_machinelearning_big_data

🧩 Per-Clip Video Object Segmentation

Progressive matching mechanism for efficient information-passing within a clip.

Github: https://github.com/pkyong95/PCVOS

Paper: https://arxiv.org/abs/2208.01924v1

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

Video: https://youtu.be/6QATHDwrUx0

@ai_machinelearning_big_data

Эволюция машинного обучения и проблема «черного ящика»

Какие бенчмарки используются в ML?
Благодаря чему произошел прорыв в технологиях машинного обучения?
Как метод LIME помогает интерпретировать алгоритмы ИИ?
Почему нейронки по-прежнему работают не так, как хотелось бы ученым?

Ученые Yandex Research рассказали, как они исследуют логику нейросетей и почему людям до сих пор сложно прочитать их «мысли».

🧠 Free AI for Beginners Course

Artificial Intelligence for Beginners
MindMap
Denoscription

@ai_machinelearning_big_data

🐚 Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers

Github: https://github.com/lkeab/BCNet

Paper: https://arxiv.org/abs/2208.04438v1

Dataset: https://paperswithcode.com/dataset/bdd100k

Video: https://www.youtube.com/watch?v=iHlGJppJGiQ

@ai_machinelearning_big_data