# Learning cross space mapping via DNN using large scale click-through logs

arXiv: https://arxiv.org/abs/2302.13275 · HTML: https://mlsanity.com/paper/2302.13275/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 33 references that are in the map.
- First posted on arXiv 26 Feb 2023.

## Builds on (most cited first, 3 of 3)

- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Learning Fine-grained Image Similarity with Deep Ranking](https://mlsanity.com/paper/1404.4661/) (2014)

## Built on by (most cited first, 3 of 3)

- [Multi-view Fuzzy Representation Learning with Rules based Model](https://mlsanity.com/paper/2309.11473/) (2023)
- [A Novel Riemannian Sparse Representation Learning Network for Polarimetric SAR Image Classification](https://mlsanity.com/paper/2502.15302/) (2025)
- [Direction-adaptive Mamba: Spatial-Frequency Dual-Domain Collaborative Learning for PolSAR Image Classification](https://mlsanity.com/paper/2607.23464/) (2026)

## Abstract (arXiv)

The gap between low-level visual signals and high-level semantics has been progressively bridged by continuous development of deep neural network (DNN). With recent progress of DNN, almost all image classification tasks have achieved new records of accuracy. To extend the ability of DNN to image retrieval tasks, we proposed a unified DNN model for image-query similarity calculation by simultaneously modeling image and query in one network. The unified DNN is named the cross space mapping (CSM) model, which contains two parts, a convolutional part and a query-embedding part. The image and query are mapped to a common vector space via these two parts respectively, and image-query similarity is naturally defined as an inner product of their mappings in the space. To ensure good generalization ability of the DNN, we learn weights of the DNN from a large number of click-through logs which consists of 23 million clicked image-query pairs between 1 million images and 11.7 million queries. Both the qualitative results and quantitative results on an image retrieval evaluation task with 1000 queries demonstrate the superiority of the proposed method.