TY  - CONF
AU  - Ayan Banerjee
AU  - Sanket Biswas
AU  - Josep Llados
AU  - Umapada Pal
A2  - ICDAR
PY  - 2023//
TI  - SwinDocSegmenter: An End-to-End Unified Domain Adaptive Transformer for Document Instance Segmentation
T2  - LNCS
BT  - 17th International Conference on Document Analysis and Recognition
SP  - 307–325
VL  - 14187
N2  - 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 93.72, 54.39, 84.65 and 98.04 respectively under one billion parameters. The code is made publicly available at: github.com/ayanban011/SwinDocSegmenter .
UR  - https://link.springer.com/chapter/10.1007/978-3-031-41676-7_18
N1  - DAG
ID  - Ayan Banerjee2023
ER  -