Click the “CVer” above to add it to your “Favorites” list. Essential insights delivered promptly. This article is reprinted from: Smarter Since the introduction of the Transformer, it has dominated the NLP field. However, its impact in the CV domain has been moderate, with initial thoughts suggesting it was unsuitable for CV until recently. A … Read more
Original by Machine Heart Author: Chen Ping Since the introduction of the Transformer, it has swept through the entire NLP field. In fact, it can also be used for object detection. Researchers at Facebook AI first launched the visual version of the Transformer—Detection Transformer (DETR), filling the gap of using Transformer for object detection, surpassing … Read more
Inspired by these studies, Shilong Liu and others conducted an in-depth study on the cross-attention module in the Transformer decoder and proposed using 4D box coordinates (x, y, w, h) as queries in DETR, namely anchor boxes. By updating layer by layer, this new query method introduces better spatial priors in the cross-attention module, simplifying … Read more