A simpler design but better performance! It aims to bridge the gap between research and industrial communities.
Paper:
https://arxiv.org/pdf/2107.08430v1.pdf
Github:
https://github.com/Megvii-BaseDetection/YOLOX
👉@computer_science_and_programming
Paper:
https://arxiv.org/pdf/2107.08430v1.pdf
Github:
https://github.com/Megvii-BaseDetection/YOLOX
👉@computer_science_and_programming
👍13
Practical image restoration
Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data
👉@computer_science_and_programming
Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data
👉@computer_science_and_programming
👍12👨💻1
Paper:
https://arxiv.org/pdf/2103.14030.pdf
Github:
https://github.com/SwinTransformer/Swin-Transformer-Object-Detection
Demo:
https://www.youtube.com/watch?v=FQVS_0Bja6o
👉@computer_science_and_programming
https://arxiv.org/pdf/2103.14030.pdf
Github:
https://github.com/SwinTransformer/Swin-Transformer-Object-Detection
Demo:
https://www.youtube.com/watch?v=FQVS_0Bja6o
👉@computer_science_and_programming
GitHub
GitHub - SwinTransformer/Swin-Transformer-Object-Detection: This is an official implementation for "Swin Transformer: Hierarchical…
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Object Detection and Instance Segmentation. - SwinTransformer/S...
👍16
This media is not supported in your browser
VIEW IN TELEGRAM
Now removing, duplicating or enhancing objects in video is more realistic with the assist of AI
"We need to talk about the car in the room."
This paper: what car? 🙈
"We need to talk about the car in the room."
This paper: what car? 🙈
👍25
Paper:
https://arxiv.org/pdf/2105.06993.pdf
Github:
https://github.com/erikalu/omnimatte
Project Page:
https://omnimatte.github.io/
Supplimentary material:
https://omnimatte.github.io/supplementary/index.html
Explained:
https://www.youtube.com/watch?v=lCBSGOwV-_o
👉@computer_science_and_programming
https://arxiv.org/pdf/2105.06993.pdf
Github:
https://github.com/erikalu/omnimatte
Project Page:
https://omnimatte.github.io/
Supplimentary material:
https://omnimatte.github.io/supplementary/index.html
Explained:
https://www.youtube.com/watch?v=lCBSGOwV-_o
👉@computer_science_and_programming
GitHub
GitHub - erikalu/omnimatte
Contribute to erikalu/omnimatte development by creating an account on GitHub.
👍14
This media is not supported in your browser
VIEW IN TELEGRAM
Unseen Object Amodal Instance Segmentation (UOAIS)
👍5
This media is not supported in your browser
VIEW IN TELEGRAM
PASS: Pictures without humAns for Self-Supervised Pretraining
PASS is a large-scale image dataset that does not include any humans, human parts, or other personally identifiable information
Github
https://github.com/yukimasano/PASS
Paper
https://arxiv.org/abs/2109.13228v1
Dataset
https://paperswithcode.com/dataset/pass
Documentation
https://www.robots.ox.ac.uk/~vgg/research/pass/
PASS is a large-scale image dataset that does not include any humans, human parts, or other personally identifiable information
Github
https://github.com/yukimasano/PASS
Paper
https://arxiv.org/abs/2109.13228v1
Dataset
https://paperswithcode.com/dataset/pass
Documentation
https://www.robots.ox.ac.uk/~vgg/research/pass/
👍13
8-bit optimizers – a replacement for regular optimizers. 🚀, 75% less memory, same with upwards trend, no hyperparam tuning needed Input symbol for numbers: #Lightweight, #LessMemory
👍14👎2
Under review as a conference paper at ICLR 2022
8-BIT OPTIMIZERS VIA BLOCK-WISE QUANTIZATION
Paper:
https://arxiv.org/abs/2110.02861
Github:
https://github.com/facebookresearch/bitsandbytes
Video:
https://www.youtube.com/watch?v=IxrlHAJtqKE
Documentation:
https://bitsandbytes.readthedocs.io/en/latest/
👉@computer_science_and_programming
8-BIT OPTIMIZERS VIA BLOCK-WISE QUANTIZATION
Paper:
https://arxiv.org/abs/2110.02861
Github:
https://github.com/facebookresearch/bitsandbytes
Video:
https://www.youtube.com/watch?v=IxrlHAJtqKE
Documentation:
https://bitsandbytes.readthedocs.io/en/latest/
👉@computer_science_and_programming
GitHub
GitHub - facebookresearch/bitsandbytes: Library for 8-bit optimizers and quantization routines.
Library for 8-bit optimizers and quantization routines. - facebookresearch/bitsandbytes
👍19
One of the best reference book is definately "Deep Learning with Python" (1st edition) by François Chollet (creator of Keras)
Deep Learning with Python (2nd edition) has been released with 500 pages of code examples, theory, context, practical tips...
Book:
https://www.manning.com/books/deep-learning-with-python-second-edition?a_aid=keras
For online reading:
https://livebook.manning.com/book/deep-learning-with-python-second-edition/chapter-1/
Jupyter notebooks on Github:
https://github.com/fchollet/deep-learning-with-python-notebooks
👉👉@computer_science_and_programming
Deep Learning with Python (2nd edition) has been released with 500 pages of code examples, theory, context, practical tips...
Book:
https://www.manning.com/books/deep-learning-with-python-second-edition?a_aid=keras
For online reading:
https://livebook.manning.com/book/deep-learning-with-python-second-edition/chapter-1/
Jupyter notebooks on Github:
https://github.com/fchollet/deep-learning-with-python-notebooks
👉👉@computer_science_and_programming
👍48
ESPnet: end-to-end text-to-speech processing toolkit
ESPnet2-TTS: Extending the Edge of TTS Research
Github: https://github.com/espnet/espnet
Docs: https://espnet.github.io/espnet/
Paper: https://arxiv.org/abs/2110.07840v1
Dataset: https://paperswithcode.com/dataset/vctk
ESPnet2-TTS: Extending the Edge of TTS Research
Github: https://github.com/espnet/espnet
Docs: https://espnet.github.io/espnet/
Paper: https://arxiv.org/abs/2110.07840v1
Dataset: https://paperswithcode.com/dataset/vctk
👍24
Another state-of-the-art archtecture for Vision tasks:
Github: https://github.com/sail-sg/poolformer
Paper: https://arxiv.org/abs/2111.11418
Datasets: ImageNet, COCO, Ade20k
Colab: https://colab.research.google.com/github/sail-sg/poolformer/blob/main/misc/poolformer_demo.ipynb
👉👉@computer_science_and_programming
Github: https://github.com/sail-sg/poolformer
Paper: https://arxiv.org/abs/2111.11418
Datasets: ImageNet, COCO, Ade20k
Colab: https://colab.research.google.com/github/sail-sg/poolformer/blob/main/misc/poolformer_demo.ipynb
👉👉@computer_science_and_programming
👍13