Google MorphNet makes your neural net faster and smaller MorphNet is a Google Model to Build Faster and Smaller Neural Networks Towards...

Facebook segments objects in image or video with no supervision Advancing the state of the art in computer vision with self-supervised...

Removing haze in images Contrastive Learning for Compact Single Image Dehazing arXiv paper abstract https://arxiv.org/abs/2104.09367v1...

Unsupervised shape completion of 3D data Unsupervised 3D Shape Completion through GAN Inversion arXiv paper abstract...

Get summary video from a text search GPT2MVS: Generative Pre-trained Transformer-2 for Multi-modal Video Summarization arXiv paper...

Multiscale Vision Transformers Outperform Prior Work Multiscale Vision Transformers arXiv paper abstract https://arxiv.org/abs/2104.11227...

Survey of deep learning to enhance dim images Lighting the Darkness in the Deep Learning Era arXiv paper abstract...

Shapash library for making ML models understandable Shapash: Making Machine Learning Models Understandable KDnuggets...

Kornia Computer Vision Library for PyTorch Kornia: an Open Source Differentiable Computer Vision Library for PyTorch OpenCV article...

Ensemble deep learning: A review arXiv paper abstract https://arxiv.org/abs/2104.02395 arXiv PDF paper https://arxiv.org/pdf/2104.02395.p...

Transformers for action recognition 40 times faster by focus attention in time An Image is Worth 16x16 Words, What is a Video Worth?...

NVIDIA, Stanford, Microsoft Efficient Trillion-Parameter Model Training on GPU Clusters NVIDIA, Stanford & Microsoft Propose Efficient...

15 graphs show state of AI in 2021 15 Graphs You Need to See to Understand AI in 2021 IEEE article https://spectrum.ieee.org/tech-talk/ar...

Transformer for face recognition comparable to CNN Face Transformer for Recognition arXiv paper abstract https://arxiv.org/abs/2103.14803...

Microsoft DeepSpeed lets 1 GPU train 40 billion parameter neural net Microsoft Releases AI Training Library ZeRO-3 Offload InfoQ article...

Wearable fabric with display and touch input available next year. It can be bent, stretched, pressed, washed, and dried. Futuristic...

Vision transformer for object detection beats state-of-art ResNet-50 Will Transformers Replace CNNs in Computer Vision? In less than 5...

CPU beats GPU by 15x for neural net training with Rice Univ method CPU algorithm trains deep neural nets up to 15 times faster than top...

Fourier transformers for super-resolution images and CT scans Fourier Image Transformer arXiv paper abstract https://arxiv.org/abs/2104.0...

Top 10 AI and Machine Learning Papers in 2020 2020's Top AI & Machine Learning Research Papers TOPBOTS https://www.topbots.com/ai-machine...