VisionTransformers have been shown to be powerful out-of-distribution
detectors for ImageNet-scale settings when finetuned from publicly available
checkpoints, often outperforming other model types on popular benchmarks. In
this work, we investigate the impact of both the pretraining and finetuning
scheme on the performance of ViTs on this task by analyzing a large pool of
models. We find that the exact type of pretraining has a strong impact on which
method works well and on OOD detection performance in general. We further show
that certain training schemes might only be effective for a specific type of
out-distribution, but not in general, and identify a best-practice training
recipe.

本研究探讨了 VisionTransformers 在 ImageNet 规模设置中作为强大的超出分布检测器的影响，通过对大量模型的分析，发现预训练和微调方案对 ViTs 性能以及 OOD 检测表现产生了强烈影响，并确定了最佳实践训练方法。

如何训练您的 ViT 用于异常检测

How to train your ViT for OOD Detection

Learning enabled components (LECs), while critical for decision making in
autonomous vehicles (AVs), are likely to make incorrect decisions when
presented with samples outside of their training distributions.
Out-of-distribution (OOD) detectors have been proposed to detect such samples,
thereby acting as a safety monitor, however, both OOD detectors and LECs
require heavy utilization of embedded hardware typically found in AVs. For both
components, there is a tradeoff between non-functional and functional
performance, and both impact a vehicle's safety. For instance, giving an OOD
detector a longer response time can increase its accuracy at the expense of the
LEC. We consider an LEC with binary output like an autonomous emergency braking
system (AEBS) and use risk, the combination of severity and occurrence of a
failure, to model the effect of both components' design parameters on each
other's functional and non-functional performance, as well as their impact on
system safety. We formulate a co-design methodology that uses this risk model
to find the design parameters for an OOD detector and LEC that decrease risk
below that of the baseline system and demonstrate it on a vision based AEBS.
Using our methodology, we achieve a 42.3% risk reduction while maintaining
equivalent resource utilization.

使用风险模型来找到能减少基线系统风险的 OOD 探测器和 LEC 的设计参数的协同设计方法，并应用于基于视觉的 AEBS，成功实现了 42.3% 的风险降低并保持等效资源利用。

自动紧急制动系统的区别分辨设计

Co-Design of Out-of-Distribution Detectors for Autonomous Emergency  Braking Systems

Open-world machine learning (ML) combines closed-world models trained on
in-distribution data with out-of-distribution (OOD) detectors, which aim to
detect and reject OOD inputs. Previous works on open-world ML systems usually
fail to test their reliability under diverse, and possibly adversarial
conditions. Therefore, in this paper, we seek to understand how resilient are
state-of-the-art open-world ML systems to changes in system components? With
our evaluation across 6 OOD detectors, we find that the choice of
in-distribution data, model architecture and OOD data have a strong impact on
OOD detection performance, inducing false positive rates in excess of $70\%$.
We further show that OOD inputs with 22 unintentional corruptions or
adversarial perturbations render open-world ML systems unusable with false
positive rates of up to $100\%$. To increase the resilience of open-world ML,
we combine robust classifiers with OOD detection techniques and uncover a new
trade-off between OOD detection and robustness.

本文针对开放世界机器学习系统，测试其在各种条件下的可靠性，并发现在组件的选择方面，包括原始数据、模型体系结构和 OOD 数据等选择均严重影响 OOD 检测的性能，可能引起超过 70％的误检率，而对于包含 22 种非故意损坏或对抗性扰动的 OOD 输入，误报率可以达到 100％，并提出了结合鲁棒分类器和 OOD 检测技术来解决 OOD 检测和适应性之间的新的权衡。