Abstract Vision Transformers (ViTs) emerge to achieve impressive performance on many
data-abundant computer vision tasks by capturing long-range dependencies among local …

Abstract" A picture is worth a thousand words", significantly beyond mere a categorization.
Accompanied by that, many patches of the image could have completely irrelevant …

Single image-level annotations only correctly describe an often small subset of an image's
content, particularly when complex real-world scenes are depicted. While this might be …

Few-shot classification aims at leveraging knowledge learned in a deep learning model, in
order to obtain good classification performance on new problems, where only a few labeled …

The deep CNNs in image semantic segmentation typically require a large number of
densely-annotated images for training and have difficulties in generalizing to unseen object …

This paper presents new hierarchically cascaded transformers that can improve data
efficiency through attribute surrogates learning and spectral tokens pooling. Vision …

Continual semantic segmentation (CSS) aims to extend an existing model to tackle unseen
tasks while retaining its old knowledge. Naively fine-tuning the old model on new data leads …