AI Technology & Industry Review
A team from Facebook AI Research and UC Berkeley proposes ConvNeXts, a pure ConvNet model that achieves performance comparable with state-of-the-art hierarchical vision transformers on computer vision benchmarks while retaining the simplicity and efficiency of standard ConvNets.
In the new paper Can Vision Transformers Perform Convolution?, a research team from Peking University, UCLA and Microsoft Research proves that a single ViT layer with image patches as the input can perform any convolution operation constructively, and show that ViT performance in low data regimes can be significantly improved using their proposed ViT training pipeline.
Researchers combine the effectiveness of the inductive bias in CNNs with the expressivity of transformers to model and synthesize high resolution images.
Researchers have developed a new technique for self-supervised training of convolutional networks used for image classification and other computer vision tasks.
The earliest evidence of China’s recorded history is found in the Shang dynasty (~1600 to 1046 BC), and this hasContinue Reading
Researchers proposed a new training scheme that targets this bias by controlling and exposing textural information slowly through the training process.
Might there be a more efficient approach to scaling up CNNs to improve accuracy? Researchers from Google AI say “yes” and have proposed a new model scaling method in their ICML 2019 paper EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks.
Researchers from Technische Universität Wien, Austria, and Politecnico di Torino, Italy, explored adversarial attacks on Capsule Networks, proposing an algorithm which automatically generates targeted adversarial examples in black-box attack scenarios.
Synced Global AI Weekly June 2nd
Deep Learning has become an essential toolbox which is used in a wide variety of applications, research labs, industries, etc. In this tutorial given at NIPS 2017, the speakers provide a set of guidelines which will help newcomers to the field understand the most recent and advanced models and their application to diverse data modalities.
To boost CNN performance, industry leaders and startups alike are now racing to develop specialized AI chips.
Recently, CNNs have been successfully used in estimating optical flow. Compared with traditional methods, these methods achieved a large improvement in quality. Here, we will give a brief review on the following papers.
The ShuffleNet utilizes pointwise group convolution and channel shuffle to reduce computation cost while maintaining accuracy. It manages to obtain lower top-1 error than the MobileNet system on ImageNet classification, and achieves ~13x actual speedup over AlexNet while maintaining comparable accuracy.
The reason why TensorFlow is so widely used is due to its automatic derivation of functions and distributed computing capability. This increase in interest can also be found in commercial applications.
A practical way to make an autonomous vehicle is not by programming a car to drive in any environment, but by showing the car how to drive and make the car learn by itself. NVIDIA created a system of this kind, named PilotNet.
This paper proposed a computationally efficient convolutional layer to upscale the final low-resolution feature map to a high-resolution output.
Google released a method for recovering pictures from low resolution to high resolution using pixel recursive super resolution model.
Compared to simplifying or approximating the solution of a complicated equation, deep learning provides a highly flexible model and might serve as a perfect walk-around method.