BigData
3.3K subscribers
754 photos
89 videos
3 files
835 links
Data Science : Big Data : Machine Learning : Deep Learning. По всем вопросам @evgenycarter
加入频道
🔍 TOOD: Task-aligned One-stage Object Detection

Github: https://github.com/fcjian/TOOD

Paper: https://arxiv.org/abs/2108.07755v2

Dataset: https://paperswithcode.com/dataset/coco
This media is not supported in your browser
VIEW IN TELEGRAM
SOLD² - Self-supervised Occlusion-aware Line Description and Detection

Github: https://github.com/cvg/SOLD2

Paper: https://arxiv.org/abs/2104.03362
🎩 Mr. TyDi: A Multi-lingual Benchmark for Dense Retrieval

Mr. TyDi is a multi-lingual benchmark dataset built on TyDi, covering eleven typologically diverse languages.

Github: https://github.com/castorini/mr.tydi

Paper: https://arxiv.org/abs/2108.08787

Tasks: https://paperswithcode.com/task/representation-learning
👉 @bigdata_1
MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement

Github: https://github.com/speechbrain/speechbrain/tree/develop/recipes/Voicebank/enhance/MetricGAN

Paper: https://arxiv.org/abs/1905.04874
👉 @bigdata_1
AutoGL: A Library for Automated Graph Learning

Github: https://github.com/THUMNLab/AutoGL

Paper: https://arxiv.org/abs/2104.04987v1
👉 @bigdata_1
🕸 Bag of Tricks for Training Deeper Graph Neural Networks: A Comprehensive Benchmark Study

Github: https://github.com/VITA-Group/Deep_GCN_Benchmarking

Paper: https://arxiv.org/abs/2108.10521v1
👉 @bigdata_1
👍1
💡Volunteer computing: статья про коллаборативное обучение нейросети

Если вы хотите создавать большие модели, не имея суперкомпьютер за спиной, то вам понадобится технология, способная разделить вычисления между теми, кто готов предоставить вам мощности. В этом поможет технология DeDLOC, разработанная в Yandex Research, Hugging Face и University of Toronto.

Хабр: https://habr.com/ru/company/yandex/blog/574466/
👉 @bigdata_1
👍1
💬 Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation

Github: https://github.com/ofirpress/attention_with_linear_biases

Paper: https://ofir.io/train_short_test_long.pdf

Fairseq: https://github.com/pytorch/fairseq
👉 @bigdata_1
ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentation

Github: https://github.com/hanchaoleng/shapeconv

Paper: https://arxiv.org/abs/2108.10528v1
👉 @bigdata_1
👍1
📶 ISNet: Integrate Image-Level and Semantic-Level Context for Semantic Segmentation

Github: https://github.com/segmentationblwx/sssegmentation

Paper: https://arxiv.org/abs/2108.12382v1

Dataset: https://cs.stanford.edu/~roozbeh/pascal-context/
👉 @bigdata_1
Essential Math for Data Science: Linear Transformation with Matrices

https://hadrienj.github.io/posts/Essential-Math-for-Data-Science-linear_transformations/
👉 @bigdata_1
👍1
🔎 Efficient Person Search: An Anchor-Free Approach.

Github: https://github.com/daodaofr/AlignPS

Paper: https://arxiv.org/abs/2109.00211v1

Dataset: https://paperswithcode.com/dataset/cuhk-sysu
👉 @bigdata_1
👍1