The ability of a document classifier to handle inputs that are drawn from a
distribution different from the training distribution is crucial for robust
deployment and generalizability. The RVL-CDIP corpus is the de facto standard
benchmark for document classification, yet to our knowledge all studies that
use this corpus do not include evaluation on out-of-distribution documents. In
this paper, we curate and release a new out-of-distribution benchmark for
evaluating out-of-distribution performance for document classifiers. Our new
out-of-distribution benchmark consists of two types of documents: those that
are not part of any of the 16 in-domain RVL-CDIP categories (RVL-CDIP-O), and
those that are one of the 16 in-domain categories yet are drawn from a
distribution different from that of the original RVL-CDIP dataset (RVL-CDIP-N).
While prior work on document classification for in-domain RVL-CDIP documents
reports high accuracy scores, we find that these models exhibit accuracy drops
of between roughly 15-30% on our new out-of-domain RVL-CDIP-N benchmark, and
further struggle to distinguish between in-domain RVL-CDIP-N and out-of-domain
RVL-CDIP-O inputs. Our new benchmark provides researchers with a valuable new
resource for analyzing out-of-distribution performance on document classifiers.
Our new out-of-distribution data can be found at
this https URL.

本文提出了一个新的文档分类器 “out-of-distribution” 测试基准，名为 RVL-CDIP，目的是测试分类器在不同分布的输入上的健壮部署和泛化性能。该基准包括两种类型的文档：不属于任何 16 个领域的 RVL-CDIP-O 类别的文档和来自于与原始数据集不同的分布的 16 个领域内的 RVL-CDIP-N 类别的文档。通过评估，发现模型对于新的 out-of-domain RVL-CDIP-N 测试基准的准确率下降了约 15-30％，而且还很难区分领域内 RVL-CDIP-N 和领域外 RVL-CDIP-O 输入。