AutoFocusFormer: Image Segmentation off the Grid

      Real world images often have highly imbalanced content density. Some areas are very uniform, e.g., large patches of blue sky, while other areas are scattered with many small objects. Yet, the commonly used successive grid downsampling strategy in convolutional deep networks treats all areas equally. Hence, small objects are represented in very few spatial locations, leading to worse results in tasks such as segmentation. Intuitively, retaining more pixels representing small objects during downsampling helps to preserve important information. To achieve this, we propose AutoFocusFormer (AFF), a… Read More Apple Machine Learning Research 

​  


Posted

in

by

Tags:

Comments

Leave a Reply

Your email address will not be published. Required fields are marked *