AI Technology & Industry Review
In the new paper What Do Vision Transformers Learn? A Visual Exploration, a research team from the University of Maryland and New York University uses large-scale feature visualizations from a wide range of vision transformers to gain insights into what they learn from images and how they differ from convolutional neural networks.
A research team proposes ConvMixer, an extremely simple model designed to support the argument that the impressive performance of vision transformers (ViTs) is mainly attributable to their use of patches as the input representation. The study shows that ConvMixer can outperform ViTs, MLP-Mixers and classical vision models.
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.