🔘 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

📲LAMDA-SSL: Semi-Supervised Learning in Python


Github: https://github.com/ygzwqzd/lamda-ssl

Paper: https://arxiv.org/pdf/2208.04610.pdf

Docs: https://ygzwqzd.github.io/LAMDA-SSL

@ai_machinelearning_big_data

🎼 ROC: A New Paradigm for Lyric-to-Melody Generation

Muzic is a research project on AI music that empowers music understanding and generation with deep learning and artificial intelligence.

Github: https://github.com/microsoft/muzic

Paper: https://arxiv.org/abs/2208.05697v1

Project: https://www.microsoft.com/en-us/research/project/ai-music/

@ai_machinelearning_big_data

🗣 Speech Enhancement and Dereverberation with Diffusion-based Generative Models

Github: https://github.com/sp-uhh/sgmse

Paper: https://arxiv.org/abs/2208.05830v1

Pretrained checkpoints: https://drive.google.com/drive/folders/1CSnkhUSoiv3RG0xg7WEcVapyLuwDaLbe?usp=sharing

@ai_machinelearning_big_data

✅ The Complete Collection of Data Science Projects

@ai_machinelearning_big_data

🧔 StyleFaceV - Official PyTorch Implementation

StyleFaceV produces high-fidelity identity-preserving face videos with vivid movements

Github: https://github.com/arthur-qiu/stylefacev

Project: http://haonanqiu.com/projects/StyleFaceV.html

Video: https://youtu.be/BZNLcD04-Fc

Paper: https://arxiv.org/abs/2208.07862v1

Dataset: https://paperswithcode.com/dataset/faceforensics-1

@ai_machinelearning_big_data