DeepMind’s Upgraded Hierarchical Perceiver Is Faster, Scales to Larger Data Without Preprocessing, and Delivers Higher Resolution and Accuracy
DeepMind researchers propose Hierarchical Perceiver (HiP), a model that retains the original Perceiver’s ability to process arbitrary modalities but is faster, can scale up to even more inputs/outputs, reduces the need for input engineering, and improves both efficiency and accuracy on classical computer vision benchmarks.