適應還是不適應？語義分割的即時適應

摘要

在語義分割的線上領域適應中，目標是處理在部署過程中發生的無法預見的領域變化，例如突發的天氣事件。然而，與暴力適應相關的高計算成本使得這種範式對於真實應用來說不可行。在本文中，我們提出了 HAMLET，一個針對即時領域適應的硬體感知模塊化最經濟訓練框架。我們的方法包括一個硬體感知反向傳播協調代理（HAMT）和一個專用的領域變化檢測器，使得可以主動控制模型何時以及如何進行適應（LT）。由於這些進步，我們的方法能夠在單個消費級 GPU 上以超過 29FPS 的速度執行語義分割並同時進行適應。我們的框架在 OnDA 和 SHIFT 基準測試中通過實驗結果展示了令人鼓舞的準確性和速度折衷。

English

The goal of Online Domain Adaptation for semantic segmentation is to handle unforeseeable domain changes that occur during deployment, like sudden weather events. However, the high computational costs associated with brute-force adaptation make this paradigm unfeasible for real-world applications. In this paper we propose HAMLET, a Hardware-Aware Modular Least Expensive Training framework for real-time domain adaptation. Our approach includes a hardware-aware back-propagation orchestration agent (HAMT) and a dedicated domain-shift detector that enables active control over when and how the model is adapted (LT). Thanks to these advancements, our approach is capable of performing semantic segmentation while simultaneously adapting at more than 29FPS on a single consumer-grade GPU. Our framework's encouraging accuracy and speed trade-off is demonstrated on OnDA and SHIFT benchmarks through experimental results.

適應還是不適應？語義分割的即時適應

To Adapt or Not to Adapt? Real-Time Adaptation for Semantic Segmentation

摘要

Support