Detecting out-of-distribution (OOD) instances is crucial for the reliable
deployment of machine learning models in real-world scenarios. OOD inputs are
commonly expected to cause a more uncertain prediction in the primary task;
however, there are OOD cases for which the model returns a highly confident
prediction. This phenomenon, denoted as "overconfidence", presents a challenge
to OOD detection. Specifically, theoretical evidence indicates that
overconfidence is an intrinsic property of certain neural network
architectures, leading to poor OOD detection. In this work, we address this
issue by measuring extreme activation values in the penultimate layer of neural
networks and then leverage this proxy of overconfidence to improve on several
OOD detection baselines. We test our method on a wide array of experiments
spanning synthetic data and real-world data, tabular and image datasets,
multiple architectures such as ResNet and Transformer, different training loss
functions, and include the scenarios examined in previous theoretical work.
Compared to the baselines, our method often grants substantial improvements,
with double-digit increases in OOD detection AUC, and it does not damage
performance in any scenario.

通过测量神经网络次最后一层的极端激活值并利用这一特征改进各种 OOD 检测基线，我们解决了模型 “过度自信” 现象造成的 OOD 检测问题，在各类实验中得到了显著提升，不损害任何场景的性能。

通过捕捉极端激活来减轻对于外部分布检测中的过度自信

Mitigating Overconfidence in Out-of-Distribution Detection by Capturing  Extreme Activations

In classification problems with large output spaces (up to millions of
labels), the last layer can require an enormous amount of memory. Using sparse
connectivity would drastically reduce the memory requirements, but as we show
below, it can result in much diminished predictive performance of the model.
Fortunately, we found that this can be mitigated by introducing a penultimate
layer of intermediate size. We further demonstrate that one can constrain the
connectivity of the sparse layer to be uniform, in the sense that each output
neuron will have the exact same number of incoming connections. This allows for
efficient implementations of sparse matrix multiplication and connection
redistribution on GPU hardware. Via a custom CUDA implementation, we show that
the proposed approach can scale to datasets with 670,000 labels on a single
commodity GPU with only 4GB memory.

在大规模输出空间分类问题中，通过使用中间大小的倒数第二层和限制稀疏层的连通性为均匀，可有效降低 GPU 硬件上的内存需求，并缓解由稀疏层连通性引起的模型预测力度下降问题。