2431
Data Science : Big Data : Machine Learning : Deep Learning. По всем вопросам @evgenycarter
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
👉 @bigdata_1
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
👉 @bigdata_1
Weakly Supervised Object Localization via Transformer with Implicit Spatial Calibration
learnable parameter to dynamically adjust the semantic correlations and spatial context intensities for effective information propagation.
Github: https://github.com/164140757/scm
Paper: https://arxiv.org/abs/2207.10447v1
Dataset: https://paperswithcode.com/dataset/cub-200-2011
👉 @bigdata_1
Generative Multiplane Images: Making a 2D GAN 3D-Aware
What is really needed to make an existing 2D GAN 3D-aware? To answer this question, we modify a classical GAN, i.e., StyleGANv2, as little as possible. We find that only two modifications are absolutely necessary: 1) a multiplane image style generator branch which produces a set of alpha maps conditioned on their depth; 2) a pose-conditioned discriminator.
Github: https://github.com/apple/ml-gmpi
Paper: https://arxiv.org/abs/2207.10642v1
Dataset: https://paperswithcode.com/dataset/metfaces
Project: https://xiaoming-zhao.github.io/projects/gmpi/
Pretrained checkpoints: https://drive.google.com/drive/folders/1MEIjen0XOIW-kxEMfBUONnKYrkRATSR_
👉 @bigdata_1
FSD: Fully Sparse 3D Object Detection & SST: Single-stride Sparse Transformer
Github: https://github.com/tusimple/sst
Paper: http://arxiv.org/abs/2207.10035
Dataset: https://paperswithcode.com/dataset/waymo-open-dataset
👉 @bigdata_1
HiFormer: Hierarchical Multi-scale Representations Using Transformers for Medical Image Segmentation
Github: https://github.com/amirhossein-kz/hiformer
Paper: https://arxiv.org/abs/2207.08518v1
Tasks: https://paperswithcode.com/task/medical-image-segmentation
👉 @bigdata_1
Language Modelling with Pixels
PIXEL is a language model that operates on text rendered as images, fully removing the need for a fixed vocabulary.
Github: https://github.com/xplip/pixel
Paper: https://arxiv.org/abs/2207.06991v1
Dataset: https://paperswithcode.com/dataset/glue
Pretrained: https://huggingface.co/Team-PIXEL/pixel-base
👉 @bigdata_1
Benchmarking Omni-Vision Representation through the Lens of Visual Realms
Github: https://github.com/ZhangYuanhan-AI/OmniBenchmark
Project: https://zhangyuanhan-ai.github.io/OmniBenchmark
Paper: https://arxiv.org/abs/2207.07106v1
Competition: https://codalab.lisn.upsaclay.fr/competitions/6043
👉 @bigdata_1
Class-incremental Novel Class Discovery
Github: https://github.com/oatmealliu/class-incd
Paper: https://arxiv.org/abs/2207.08605v1
Dataset: https://paperswithcode.com/dataset/tiny-imagenet
👉 @bigdata_1
PeopleSansPeople: A Synthetic Data Generator for Human-Centric Computer Vision
Human-centric privacy-preserving synthetic data generator with highly parametrized domain randomization.
Github: https://github.com/unity-technologies/peoplesanspeople
Paper: https://arxiv.org/abs/2207.05025v1
Demo Video: https://www.youtube.com/watch?v=mQ_DUdB70dc
👉 @bigdata_1
The 5 Best Places To Host Your Data Science Portfolio
https://www.kdnuggets.com/2022/07/5-best-places-host-data-science-portfolio.html
👉 @bigdata_1
Object Centric Open Vocabulary Detection
Object-centric alignment of the language embeddings from the CLIP model.
Github: https://github.com/hanoonaR/object-centric-ovd
Paper: https://arxiv.org/abs/2207.03482v1
Dataset: https://paperswithcode.com/dataset/imagenet
👉 @bigdata_1
Understanding the Design of a Convolutional Neural Network
https://machinelearningmastery.com/understanding-the-design-of-a-convolutional-neural-network/
👉 @bigdata_1
Bounding Box Deep Learning: The Future of Video Annotation
https://www.kdnuggets.com/2022/07/bounding-box-deep-learning-future-video-annotation.html
👉 @bigdata_1
FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Sampling
Github: https://github.com/timothyhtimothy/fast-vqa
Paper: https://arxiv.org/abs/2207.02595v1
Dataset: https://paperswithcode.com/dataset/kinetics
👉 @bigdata_1
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/
👉 @bigdata_1
SimAM: A Simple, Parameter-Free Attention Module for Convolutional Neural Networks
Simple but very effective attention module for Convolutional Neural Networks (ConvNets).
Github: https://github.com/ZjjConan/SimAM
Paper: http://proceedings.mlr.press/v139/yang21o.html
Dataset: https://paperswithcode.com/dataset/cifar-10
Google Drive: https://drive.google.com/drive/folders/1rRT0UCPeRLPdTCJvv43hvAnGnS49nIWn?usp=sharing
👉 @bigdata_1
Machine Learning Algorithms Explained in Less Than 1 Minute Each
https://www.kdnuggets.com/2022/07/machine-learning-algorithms-explained-less-1-minute.html
👉 @bigdata_1
Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification
Tip-Adapter is a training-free adaption method for CLIP to conduct few-shot classification.
Github: https://github.com/gaopengcuhk/tip-adapter
Paper: https://arxiv.org/abs/2207.09519v1
Dataset: https://paperswithcode.com/dataset/oxford-102-flower
👉 @bigdata_1
Automated Crossword Solving
Pretrained models, precomputed FAISS embeddings, and a crossword clue-answer dataset.
Github: https://github.com/albertkx/berkeley-crossword-solver
Paper: https://arxiv.org/abs/2205.09665v1
Dataset: https://www.xwordinfo.com/JSON/
👉 @bigdata_1
CLOSE: Curriculum Learning On the Sharing Extent Towards Better One-shot NAS
Github: https://github.com/walkerning/aw_nas
Paper: https://arxiv.org/abs/2207.07868v1
Dataset: https://paperswithcode.com/dataset/nas-bench-201
👉 @bigdata_1
Dynamic Low-Resolution Distillation for Cost-Efficient End-to-End Text Spotting
Github: https://github.com/hikopensource/davar-lab-ocr
Paper: https://arxiv.org/abs/2207.06694v1
Dataset: https://paperswithcode.com/dataset/total-text
👉 @bigdata_1
KGI (Knowledge Graph Induction) for slot filling
Github: https://github.com/ibm/kgi-slot-filling
KILT data and knowledge source: https://github.com/facebookresearch/KILT
Paper: https://arxiv.org/abs/2207.06300v1
Dataset: https://paperswithcode.com/dataset/natural-questions
👉 @bigdata_1
Instance Shadow Detection with A Single-Stage Detector
Deep framework, and an evaluation metric to approach this new task.
Github: https://github.com/stevewongv/InstanceShadowDetection
Instance Shadow Detection: https://github.com/stevewongv/SSIS
Video: https://www.youtube.com/watch?v=p0b_2SsFypw
Colab: https://colab.research.google.com/drive/1y9UpS5uA1YuoMyvYVzcKL4ltA_FDu_x0?usp=sharing
Paper: https://arxiv.org/abs/2207.04614v1
Datasets: https://paperswithcode.com/dataset/soba
👉 @bigdata_1
An Efficiency Study for SPLADE Models
SParse Lexical AnD Expansion Model for First Stage Ranking.
Github: https://github.com/naver/splade
Paper: https://arxiv.org/abs/2207.03834v1
Dataset: https://paperswithcode.com/dataset/ms-marco
👉 @bigdata_1
#вакансия #job #vacancy #remote #parttime #преподаватель #educator #ML #AI #DS #Medicine
Время делиться знаниями!
Компания: OTUS – образовательная платформа. За более чем 6 лет работы мы создали более 170 авторских курсов для IT-специалистов разного уровня от Junior до Senior. Практически на каждом нашем курсе есть вступительное тестирование для наших студентов, плюс более 650 преподавателей-практиков из крупнейших компаний. Мы учимся друг у друга, советуемся, помогаем, делимся опытом и обсуждаем новости как в преподавании, так и в IT.
Вакансия: преподаватель онлайн-курса «Искусственный интеллект в медицине»
Эта вакансия будет интересна для экспертов с практическим опытом в области AI, Machine Learning, Data Science по направлению анализа медицинских данных. Можно без опыта преподавания. Мы с удовольствием поможем Вам освоить Best Practices преподавания: для этого у нас есть вводный курс по преподаванию и пробные уроки с методистом.
Преподаватель раскрывает тему урока с помощью теории и примеров из практики.
Условия:
✅ удаленное сотрудничество, занятость part-time.
✅стандартное занятие длится 1,5 часа с 20:00 до 21:30 по МСК.
✅ уроки проводятся в онлайн формате в Zoom.
✅ на занятиях используется презентация с теорией и практические примеры, чтобы раскрыть тему урока.
✅ наши методисты помогают освоить лучшие инструменты и практики преподавания.
Еще Вы сможете:
✅ внести свой вклад в развитие IT.
✅ структурировать свой опыт и знания.
✅ развивать личный бренд.
✅ прокачать софт-скиллы.
✅ получать от 3000 до 5000 руб. за проведение одного вебинара (полтора часа), плюс отдельно оплачивается разработка материалов к лекциям на выбранные темы, проведение открытых уроков и другие активности.
Бонусы:
✅ наши курсы со скидкой/бесплатно.
✅ возможность приглашать в свою команду на работу лучших выпускников.
✅ воркшопы и конференции для наших преподавателей.
Подробнее в telegram: @ElenaAlias
YOLOv7
YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
Github: https://github.com/wongkinyiu/yolov7
Paper: https://arxiv.org/abs/2207.02696v1
Dataset: https://paperswithcode.com/dataset/coco
👉 @bigdata_1
SeqDeepFake: Detecting and Recovering Sequential DeepFake Manipulation
First Seq-DeepFake dataset, where face images are manipulated sequentially with corresponding annotations of sequential facial manipulation vectors.
Github: https://github.com/rshaojimmy/seqdeepfake
Project: https://rshaojimmy.github.io/Projects/SeqDeepFake
Paper: https://arxiv.org/pdf/2207.02204.pdf
Dataset: https://paperswithcode.com/dataset/imagenet
👉 @bigdata_1
Aug-NeRF: Training Stronger Neural Radiance Fields with Triple-Level Physically-Grounded Augmentations
For the first time brings the power of robust data augmentations into regularizing the NeRF training.
Github: https://github.com/vita-group/aug-nerf
Paper: https://arxiv.org/abs/2207.01164v1
Cloud Drive: https://drive.google.com/drive/folders/128yBriW1IG_3NJ5Rp7APSTZsJqdJdfc1
👉 @bigdata_1
Identifying and Combating Bias in Segmentation Networks by leveraging multiple resolutions
Github: https://github.com/Deep-MI/FastSurfer
Colab: https://colab.research.google.com/github/Deep-MI/FastSurfer/blob/master/Tutorial/Tutorial_FastSurferCNN_QuickSeg.ipynb
Paper: https://arxiv.org/abs/2206.14919v1
👉 @bigdata_1