Is Generative Modeling-based Stylization Necessary for Domain Adaptation in Regression Tasks?
원문 초록
Unsupervised domain adaptation (UDA) aims to bridge the gap between source and target domains in the absence of target domain labels using two main techniques: input-level alignment (such as generative modeling and stylization) and feature-level alignment (which matches the distribution of the feature maps, e.g. gradient reversal layers). Motivated from the success of generative modeling for image classification, stylization-based methods were recently proposed for regression tasks, such as pose estimation. However, use of input-level alignment via generative modeling and stylization incur additional overhead and computational complexity which limit their use in real-world DA tasks. To investigate the role of input-level alignment for DA, we ask the following question: Is generative modeling-based stylization necessary for visual domain adaptation in regression? Surprisingly, we find that input-alignment has little effect on regression tasks as compared to classification. Based on these insights, we develop a non-parametric feature-level domain alignment method -- Implicit Stylization (ImSty) -- which results in consistent improvements over SOTA regression task, without the need for computationally intensive stylization and generative modeling. Our work conducts a critical evaluation of the role of generative modeling and stylization, at a time when these are also gaining popularity for domain generalization.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Learning Generalized Segmentation for Foggy-scenes by Bi-directional Wavelet Guidance
Topology-Aware Modeling for Unsupervised Simulation-to-Reality Point Cloud Recognition
Unlocking Constraints: Source-Free Occlusion-Aware Seamless Segmentation
Prmpt2Adpt: Prompt-Based Zero-Shot Domain Adaptation for Resource-Constrained Environments
One-Shot Neural Architecture Search with Network Similarity Directed Initialization for Pathological Image Classification
MUDAS: Mote-scale Unsupervised Domain Adaptation in Multi-label Sound Classification
토론
이 논문과 연결된 포럼 글이 아직 없습니다.