English(EN)On the Interaction Between Model Compression and Test-Time Adaptation
AI模型通过新的测试时自适应技术增强部署性能 · 跟踪5个来源
作者PulseAugur 编辑部·[7 个来源]·
近期研究论文探讨了测试时自适应（TTA）的高级技术，这是一种允许AI模型在部署期间无需标签即可优化其性能的方法。一篇综述论文提出了一个统一的框架“测试时智能”（TTI），以连接测试时自适应、学习和扩展等各种方法。其他论文引入了新颖的方法，例如在教师-学生框架中使用“固执的教师”来提高稳定性，在严格的在线设置中使用敏感度引导擦除方法（SEGA）进行持续TTA，以及用于动态图的时间记忆感知框架（DGOTTA）。此外，一种称为DESA-TTA的方法可以动态调整教师更新并锚定学生参数，以增强视觉-语言对象检测器在分布变化下的鲁棒性。
AI
arXiv:2609.03604v1 Announce Type: cross Abstract: Deep neural networks deployed in the wild must be both efficient and adaptable, requiring model compression and test-time adaptation (TTA). While both are well studied in isolation, their interaction remains poorly understood. We …
arXiv:2609.04141v1 Announce Type: new Abstract: AI agents are trained on population-scale data to encode broad capabilities spanning those of many practitioners. Yet the artifacts they produce rarely meet the personal bar professionals need to stake their reputation on. On realis…
arXiv cs.LG
TIER_1English(EN)·Damian S\'ojka, Marc Masana, Bart{\l}omiej Twardowski, Sebastian Cygert·
arXiv:2609.02507v1 Announce Type: new Abstract: Test-Time Adaptation (TTA) has recently emerged as a promising strategy that allows the adaptation of pre-trained models to changing data distributions at deployment time, without access to any labels. To mitigate error accumulation…
arXiv:2609.01679v1 Announce Type: new Abstract: The ability of AI systems to improve their behavior during deployment is becoming increasingly important. As inference moves beyond the static execution of a fixed trained model, a growing body of work studies how models can refine …
arXiv cs.LG
TIER_1English(EN)·Chandler Timm C. Doloriel, Yunbei Zhang, Muhammad Salman Siddiqui, Tor Kristian Stevik, Fadi Al Machot, Kristian Hovde Liland, Habib Ullah·
arXiv:2608.29920v1 Announce Type: cross Abstract: Test-time adaptation (TTA) promises robustness under distribution shift by updating a pretrained model on unlabeled test data, but strict online TTA with batch size one and no access to source data is especially prone to drift or …
arXiv cs.LG
TIER_1English(EN)·Bo Li, Xin Zheng, Ming Jin, Can Wang, Shirui Pan·
arXiv:2608.27948v1 Announce Type: new Abstract: Test-time adaptation (TTA) on graphs aims to adapt a graph neural network (GNN) that is well-trained on the training graph to the test graph, which involves potential distribution shifts that may harm model generalization and test-t…
arXiv cs.CV
TIER_1English(EN)·Atif Belal, Lilian Hollard, Marco Pedersoli, Eric Granger·
arXiv:2609.01795v1 Announce Type: new Abstract: Vision-language object detectors (VLODs) achieve strong zero-shot performance but remain vulnerable to distribution shifts during deployment. Mean-teacher methods for test-time adaptation (TTA) can improve robustness by updating a s…
