Textual prompt tuning has demonstrated significant performance improvements in adapting natural language processing models to a variety of downstream tasks by treating hand-engineered prompts as trainable parameters. Inspired by the success of textual prompting, several studies have investigated the efficacy of visual prompt tuning. In this work, we present Visual Prompt Adaptation (VPA), the first framework that generalizes visual prompting with test-time adaptation. VPA introduces a small number of learnable tokens, enabling fully test-time and storage-efficient adaptation without necessitating source-domain information. We examine our VPA design under diverse adaptation settings, encompassing single-image, batched-image, and pseudo-label adaptation. We evaluate VPA on multiple tasks, including out-of-distribution (OOD) generalization, corruption robustness, and domain adaptation. Experimental results reveal that VPA effectively enhances OOD generalization by 3.3% across various models, surpassing previous test-time approaches. Furthermore, we show that VPA improves corruption robustness by 6.5% compared to strong baselines. Finally, we demonstrate that VPA also boosts domain adaptation performance by relatively 5.2%. Our VPA also exhibits marked effectiveness in improving the robustness of zero-shot recognition for vision-language models.
In this paper, we propose a tree modeling-based data mining method to detect anomalies from crowdsourced network data. We design an algorithm to extract potential network anomalies from decision trees. Moreover, we propose a criteria to evaluate the severity of anomaly in terms of three factors: standard deviation, weight sum and impurity decrease. To enhance generalization performance, we randomly generate sample subspace of the original dataset as the input for each subtree and compact detected anomalies from all subtrees. We carry out experiments based on the crowdsourced network measurement dataset containing five million samples, which contains round trip time (RTT) from more than 5,000 users. Experiments show that the proposed method can effectively detect high-latency network anomalies. Moreover, the random forest-based approach can achieve an improvement of approximately 25% of generalization performance compared to the single decision tree approach.