SSR: SAM is a Strong Regularizer for domain adaptive semantic segmentation
release_hpm532rtvrc4bkdtzt3flnsega
by
Yanqi Ge, Ye Huang, Wen Li, Lixin Duan
2024
Abstract
We introduced SSR, which utilizes SAM (segment-anything) as a strong
regularizer during training, to greatly enhance the robustness of the image
encoder for handling various domains. Specifically, given the fact that SAM is
pre-trained with a large number of images over the internet, which cover a
diverse variety of domains, the feature encoding extracted by the SAM is
obviously less dependent on specific domains when compared to the traditional
ImageNet pre-trained image encoder. Meanwhile, the ImageNet pre-trained image
encoder is still a mature choice of backbone for the semantic segmentation
task, especially when the SAM is category-irrelevant. As a result, our SSR
provides a simple yet highly effective design. It uses the ImageNet pre-trained
image encoder as the backbone, and the intermediate feature of each stage (ie
there are 4 stages in MiT-B5) is regularized by SAM during training. After
extensive experimentation on GTA5→Cityscapes, our SSR significantly
improved performance over the baseline without introducing any extra inference
overhead.
In text/plain
format
Archived Files and Locations
application/pdf 1.0 MB
file_z5av5vhh3ffjlbr6dtaxwsh5dq
|
arxiv.org (repository) web.archive.org (webarchive) |
2401.14686v1
access all versions, variants, and formats of this works (eg, pre-prints)