Deep Learning
Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition
They split every 2D image into a fixed number of patches, each of which is treated as a token.
Training Spiking Neural Networks with Local Tandem Learning
Our experimental results have also shown that the SNNs thus trained can achieve comparable accuracies to their teacher ANNs on CIFAR-10, CIFAR-100, and Tiny ImageNet datasets.
Man develops psychosis following ChatGPT's salt-free diet
Breakthroughs, discoveries, and DIY tips sent every weekday. Reducing salt intake is often a solid way to improve your overall health. However, swapping out classic sodium chloride for sodium bromide is a solid way to give yourself acne, involuntary muscle spasms, and paranoid psychosis. Knowing this, it's probably best to avoid that chemical compound entirely--even if ChatGPT tells you otherwise. In the recent case, one patient that was allegedly following the generative AI's nutritional suggestion was placed in hospital's involuntary psychiatric hold for three weeks.
Batch Active Learning at Scale
Acquiring this data can easily become a bottleneck in cost, time, and computational resources.
Learning Dense Object Descriptors from Multiple Views for Low-shot Category Generalization
A hallmark of the deep learning era for computer vision is the successful use of large-scale labeled datasets to train feature representations. This has been done for tasks ranging from object recognition and semantic segmentation to optical flow estimation and novel view synthesis of 3D scenes.
Detecting Moments and Highlights in Videos via Natural Language Queries
Each video in the dataset is annotated with: (1) a human-written free-form NL query, (2) relevant moments in the video w.r.t. the query, and (3) five-point scale saliency scores for all query-relevant clips.
The Neural Testbed: Evaluating Joint Predictions
Predictive distributions quantify uncertainties ignored by point estimates.