Instance-level segmentation of documents consists in assigning a class-aware and instance-aware label to each pixel of the image. It is a key step in document parsing for their understanding. In this paper, we present a unified transformer encoder-decoder architecture for en-to-end instance segmentation of complex layouts in document images. The method adapts a contrastive training with a mixed query selection for anchor initialization in the decoder. Later on, it performs a dot product between the obtained query embeddings and the pixel embedding map (coming from the encoder) for semantic reasoning. Extensive experimentation on competitive benchmarks like PubLayNet, PRIMA, Historical Japanese (HJ), and TableBank demonstrate that our model with SwinL backbone achieves better segmentation performance than the existing state-of-the-art approaches with the average precision of \textbf{93.72}, \textbf{54.39}, \textbf{84.65} and \textbf{98.04} respectively under one billion parameters. The code is made publicly available at: \href{https://github.com/ayanban011/SwinDocSegmenter}{github.com/ayanban011/SwinDocSegmenter}

翻译：文档的实例级分割是指为图像中的每个像素分配类别感知与实例感知的标签，这是文档解析与理解中的关键步骤。本文提出了一种统一的Transformer编码器-解码器架构，用于文档图像中复杂布局的端到端实例分割。该方法采用对比训练策略，并结合混合查询选择机制进行解码器中的锚点初始化。随后，通过将获得的查询嵌入与来自编码器的像素嵌入图进行点积运算，实现语义推理。在PubLayNet、PRIMA、历史日语（HJ）及TableBank等竞争性基准上的大量实验表明，采用SwinL骨干网络的模型在十亿参数规模下，平均精度分别达到\textbf{93.72}、\textbf{54.39}、\textbf{84.65}与\textbf{98.04}，优于现有最先进方法。代码已公开发布于：\href{https://github.com/ayanban011/SwinDocSegmenter}{github.com/ayanban011/SwinDocSegmenter}