Toward few-shot domain adaptation with perturbation-invariant representation and transferable prototypes  

作　　者：Junsong FAN Yuxi WANG He GUAN Chunfeng SONG Zhaoxiang ZHANG 

机构地区：[1]Center for Research on Intelligent Perception and Computing,National Laboratory of Pattern Recognition,Institute of Automation,Chinese Academy of Sciences,Beijing 100190,China [2]University of Chinese Academy of Sciences,Beijing 100049,China [3]Centre for Artificial Intelligence and Robotics,HKISI CAS,HongKong 999077,China

出　　处：《Frontiers of Computer Science》2022年第3期83-93,共11页中国计算机科学前沿（英文版）

基　　金：This work was supported in part by the National Key R&D Program of China(2019QY1604);the Major Project for New Generation of AI(2018AAA0100400);the National Youth Talent Support Program,and the National Natural Science Foundation of China(Grant Nos.U21B2042,62006231,and 62072457).

摘　　要：Domain adaptation(DA)for semantic segmentation aims to reduce the annotation burden for the dense pixellevel prediction task.It focuses on tackling the domain gap problem and manages to transfer knowledge learned from abundant source data to new target scenes.Although recent works have achieved rapid progress in this field,they still underperform fully supervised models with a large margin due to the absence of any available hints in the target domain.Considering that few-shot labels are cheap to obtain in practical applications,wc attempt to leverage them to mitigate the performance gap between DA and fully supervised methods.The key to this problem is to leverage the few-shot labels to learn robust domain-invariant predictions effectively.To this end,we first design a data perturbation strategy to enhance the robustness of the representations.Furthermore,a transferable prototype module is proposed to bridge the domain gap based on the source data and few-shot targets.By means of these proposed methods,our approach can perform on par with the fully supervised models to some extent.We conduct extensive experiments to demonstrate the effectiveness of the proposed methods and report the state-of-the-art performance on two popular DA tasks,i.e.,from GTA5 to Cityscapes and SYNTHIA to Cityscapes.

关 键 词：domain adaptation semantic segmentation 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]