# Large-Scale Classification of Structured Objects using a CRF with Deep Class Embedding

arXiv: https://arxiv.org/abs/1705.07420 · HTML: https://mlsanity.com/paper/1705.07420/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 May 2017.

## Built on by (most cited first, 2 of 2)

- [FiNER: Financial Numeric Entity Recognition for XBRL Tagging](https://mlsanity.com/paper/2203.06482/) (2022)
- [An Improved Deep Learning Approach For Product Recognition on Racks in Retail Stores](https://mlsanity.com/paper/2202.13081/) (2022)

## Abstract (arXiv)

This paper presents a novel deep learning architecture to classify structured objects in datasets with a large number of visually similar categories. We model sequences of images as linear-chain CRFs, and jointly learn the parameters from both local-visual features and neighboring classes. The visual features are computed by convolutional layers, and the class embeddings are learned by factorizing the CRF pairwise potential matrix. This forms a highly nonlinear objective function which is trained by optimizing a local likelihood approximation with batch-normalization. This model overcomes the difficulties of existing CRF methods to learn the contextual relationships thoroughly when there is a large number of classes and the data is sparse. The performance of the proposed method is illustrated on a huge dataset that contains images of retail-store product displays, taken in varying settings and viewpoints, and shows significantly improved results compared to linear CRF modeling and unnormalized likelihood optimization.