Machine Learning Research
A recent generative adversarial network (GAN) produced more coherent images using modified transformers that replaced fully connected layers with convolutional layers. A new GAN achieved a similar end using transformers in their original form.
Machine Learning Research
In some animated games, different characters can perform the same actions — say, walking, jumping, or casting spells. A new system learned from unlabeled data to transfer such motions from one character to another.
Machine Learning Research
It’s well established that pretraining a model on a large dataset improves performance on fine-tuned tasks. In sufficient quantity and paired with a big model, even data scraped from the internet at random can contribute to the performance boost.
Machine Learning Research
Attention quantifies how each part of one input affects the various parts of another. Researchers added a step that reverses this comparison to produce more convincing images.
Machine Learning Research
Self-attention is a key element in state-of-the-art language models, but it struggles to process images because its memory requirement rises rapidly with the size of the input. New research addresses the issue with a simple twist on a convolutional neural network.
Machine Learning Research
When you lack labeled training data, pretraining a model on unlabeled data can compensate. New research pretrained a model three times to boost performance on a medical imaging task.
Machine Learning Research
A new system combines verbal descriptions and crude lines to visualize complex scenes. Google researchers led by Jing Yu Koh proposed Tag-Retrieve-Compose-Synthesize (TReCS), a system that generates photorealistic images by describing what they want to see while mousing around on a blank screen.
Machine Learning Research
What’s creepier than images from the sci-fi TV series Doctor Who? Images generated by a network designed to visualize what goes on in peoples’ brains while they watch Doctor Who.
Machine Learning Research
In training an image recognition model, it’s not uncommon to augment the data by cropping original images randomly. But if an image contains several objects, a cropped version may no longer match its label. Researchers developed a way to make sure random crops are labeled properly.
Machine Learning Research
The University of Hong Kong, and Cornell University to create Neural Body, a procedure that generates novel views of a single human character based on shots from only a few angles.
Machine Learning Research
It’s commonly assumed that models pretrained to achieve high performance on ImageNet will perform better on other visual tasks after fine-tuning. But is it always true? A new study reached surprising conclusions.
Machine Learning Research
The pandemic has pushed hospitals to their limits. A new machine learning system could help doctors make sure the most severe cases get timely, appropriate care.