Fine-Grained Object Detection over Scientific Document Images with Region Embeddings
This addresses the problem of fine-grained object detection for researchers and practitioners working with scientific document analysis, representing a novel method for a known bottleneck.
The paper tackles object detection in scientific document images where current detectors fail to localize varied elements like tables and equations, presenting Attentive-RCNN which uses region embeddings with neighbor context and multi-head attention, achieving a 17% mAP improvement over standard models.
We study the problem of object detection over scanned images of scientific documents. We consider images that contain objects of varying aspect ratios and sizes and range from coarse elements such as tables and figures to fine elements such as equations and section headers. We find that current object detectors fail to produce properly localized region proposals over such page objects. We revisit the original R-CNN model and present a method for generating fine-grained proposals over document elements. We also present a region embedding model that uses the convolutional maps of a proposal's neighbors as context to produce an embedding for each proposal. This region embedding is able to capture the semantic relationships between a target region and its surrounding context. Our end-to-end model produces an embedding for each proposal, then classifies each proposal by using a multi-head attention model that attends to the most important neighbors of a proposal. To evaluate our model, we collect and annotate a dataset of publications from heterogeneous journals. We show that our model, referred to as Attentive-RCNN, yields a 17% mAP improvement compared to standard object detection models.