ADVMEM：基于小轨迹基准测试的面向真实测试时自适应的对抗性记忆初始化
ADVMEM: Adversarial Memory Initialization for Realistic Test-Time Adaptation via Tracklet-Based Benchmarking
- Center of Excellence in Generative AI, KAUST, Saudi Arabia（人工智能生成技术卓越中心，KAUST，沙特阿拉伯）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
该研究提出含时间依赖性的ITD基准数据集以弥补现有TTA测试的不足，并基于分析提出ADVMEM对抗性记忆初始化策略，有效提升了多种基于记忆的TTA方法在真实场景下的性能。
AI中文摘要：
我们提出了一个全新的基于小轨迹（tracklet）的数据集，用于对测试时自适应（test-time adaptation, TTA）方法进行基准测试。该数据集旨在模拟真实世界环境中遇到的复杂挑战，例如手持相机、自动驾驶汽车等拍摄的图像。当前的TTA基准测试主要关注模型部署时如何应对分布偏移，以及机器学习中常见的独立同分布（independent-and-identically-distributed, i.i.d.）假设被违反的情况。然而，这些基准无法忠实地呈现天然存在时间依赖性的真实场景，例如视频流中的连续帧很可能在不同时间点显示同一物体。\n我们通过提出一个名为“固有时间依赖性”（Inherent Temporal Dependencies, ITD）数据集的新型TTA基准，来弥补当前数据集的这一缺陷。我们从目标跟踪数据集的边界框中编译出以物体为中心的图像序列即小轨迹，再从中收集样本，确保ITD数据集中的实例天然具备时间依赖性。我们利用ITD对当前的TTA方法开展了全面的实验分析，揭示了这些方法在面对时间依赖性挑战时的局限性。此外，我们基于这些洞察提出了一种全新的对抗性记忆初始化策略，用于改进基于记忆的TTA方法。我们发现，在我们的高难度基准测试中，该策略显著提升了多种方法的性能。
英文摘要：
We introduce a novel tracklet-based dataset for benchmarking test-time adaptation (TTA) methods. The aim of this dataset is to mimic the intricate challenges encountered in real-world environments such as images captured by hand-held cameras, self-driving cars, etc. The current benchmarks for TTA focus on how models face distribution shifts, when deployed, and on violations to the customary independent-and-identically-distributed (i.i.d.) assumption in machine learning. Yet, these benchmarks fail to faithfully represent realistic scenarios that naturally display temporal dependencies, such as how consecutive frames from a video stream likely show the same object across time. We address this shortcoming of current datasets by proposing a novel TTA benchmark we call the "Inherent Temporal Dependencies" (ITD) dataset. We ensure the instances in ITD naturally embody temporal dependencies by collecting them from tracklets-sequences of object-centric images we compile from the bounding boxes of an object-tracking dataset. We use ITD to conduct a thorough experimental analysis of current TTA methods, and shed light on the limitations of these methods when faced with the challenges of temporal dependencies. Moreover, we build upon these insights and propose a novel adversarial memory initialization strategy to improve memory-based TTA methods. We find this strategy substantially boosts the performance of various methods on our challenging benchmark.
