AI Technology & Industry Review
A research team from Google Cloud AI, Google Research and Rutgers University simplifies vision transformers’ complex design, proposing nested transformers (NesT) that simply stack basic transformer layers to process non-overlapping image blocks individually. The approach achieves superior ImageNet classification accuracy and improves model training efficiency.
DeepMind has designed a family of Normalizer-Free ResNets (NFNets) that can be trained in larger batch sizes and stronger data augmentations and have set new SOTA validation accuracies on ImageNet.
Is it possible for machines to understand and integrate human emotions in visual arts? Meet ArtEmis, a new large-scale dataset of emotional reactions and explanations for visual artworks.
Despite being less accurate on ImageNet, adversarially robust neural networks can match or improve their standard counterparts’ transfer performance.
Google Brain in Zürich and DeepMind London researchers believe one of the world’s most popular image databases may need a makeover.
Synced Global AI Weekly February 23rd
Researchers have proposed a simple but powerful “SimCLR” framework for contrastive learning of visual representations.
Synced Global AI Weekly February 16th
Researchers from Google Brain and Carnegie Mellon University have released models trained with a semi-supervised learning method called “Noisy Student” that achieve 88.4 percent top-1 accuracy on ImageNet.
Researchers from UC Berkeley and the Universities of Washington and Chicago have released a set of natural adversarial examples, which they call “ImageNet-A.”
Facebook AI research team show how they trained a large convolutional network to predict hashtags on some 3.5 billion social media images. The research returned a state-of-the-art top-1 accuracy result of 85.4 percent on ImageNet.
A new paper from Google’s UK-based research company DeepMind addresses this with a model based on Contrastive Predictive Coding (CPC) that outperforms the fully-supervised AlexNet model in Top-1 and Top-5 accuracy on ImageNet.
Chinese AI unicorn Megvii Technology has proposed a new single-path, one-shot NAS design approach which makes various applications more convenient and achieves start-of-the-art performance on the large dataset ImageNet.
Researchers from Beijing-based AI unicorn SenseTime and Nanyang Technological University have trained ImageNet/AlexNet in a record-breaking 1.5 minutes, a significant 2.6 times speedup over the previous record of 4 minutes.
ImageNet Pre-training is common in a variety of CV (Computer Vision) tasks, as something of a consensus has emerged that pre-training can help a model learn transferrable information that can be useful for target tasks.
Synced Global AI Weekly November 25th
Researchers from Japanese electronics giant Sony have trained the ResNet-50 neural network model on ImageNet in a record-breaking 224 seconds — 43.4 percent better than the previous fastest time for the benchmark task.
Artificial general intelligence (AGI) is the long-range, human-intelligence-level target of contemporary AI researchers worldwide. It’s believed AGI has the potential to meet basic human needs globally, end poverty, cure diseases, extend life, and even mitigate climate change. In short, AGI is the tech that could not only save the world, but build a utopia.
Since 2010, the annual ImageNet Large-Scale Visual Recognition Challenge has been the most widely recognized benchmark for testing image recognition algorithms. Tencent Machine Learning picks up the challenge with its new paper Highly Scalable Deep Learning Training System with Mixed-Precision: Training ImageNet in Four Minutes.
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.
This paper proposes not only a method as a useful tool but also a new concept for modeling complex annotation as a simple polygon.
This paper systematically studies how a convolutional neural network, trained on ImageNet for image classification tasks, works on medical images – or more precisely on ultrasound images – for the “Kidney Detection” problem.
AI companies require accurate data for specialized applications, and seemingly little things such as labelling and tagging demand accuracy. At present, only humans are up for the task.
This paper proposed a computationally efficient convolutional layer to upscale the final low-resolution feature map to a high-resolution output.