Feature-Space Planes Searcher: A Universal Domain Adaptation Framework for Interpretability and Computational Efficiency
Zhitong Cheng, Yiran Jiang, Yulong Ge, Yufeng Li, Zhongheng Qin, Rongzhi Lin, Jianwei Ma

TL;DR
The paper introduces FPS, a universal domain adaptation framework that leverages geometric patterns in feature space to improve interpretability and efficiency without fine-tuning entire models.
Contribution
It proposes a novel method that optimizes decision boundaries using geometric patterns in feature space, avoiding full model fine-tuning for better scalability and interpretability.
Findings
FPS achieves competitive or superior performance on benchmarks.
It scales efficiently with large multimodal models.
Demonstrates versatility across diverse domains.
Abstract
Domain shift, characterized by degraded model performance during transition from labeled source domains to unlabeled target domains, poses a persistent challenge for deploying deep learning systems. Current unsupervised domain adaptation (UDA) methods predominantly rely on fine-tuning feature extractors - an approach limited by inefficiency, reduced interpretability, and poor scalability to modern architectures. Our analysis reveals that models pretrained on large-scale data exhibit domain-invariant geometric patterns in their feature space, characterized by intra-class clustering and inter-class separation, thereby preserving transferable discriminative structures. These findings indicate that domain shifts primarily manifest as boundary misalignment rather than feature degradation. Unlike fine-tuning entire pre-trained models - which risks introducing unpredictable feature…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
