# Connecting Images through Time and Sources: Introducing Low-data, Heterogeneous Instance Retrieval

arXiv: https://arxiv.org/abs/2103.10729 · HTML: https://mlsanity.com/paper/2103.10729/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 23 references that are in the map.
- First posted on arXiv 19 Mar 2021.

## Builds on (most cited first, 15 of 15)

- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Fine-tuning CNN Image Retrieval with No Human Annotation](https://mlsanity.com/paper/1711.02512/) (2017)
- [Re-ranking Person Re-identification with k-reciprocal Encoding](https://mlsanity.com/paper/1701.08398/) (2017)
- [Large-Scale Image Retrieval with Attentive Deep Local Features](https://mlsanity.com/paper/1612.06321/) (2016)
- [Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking](https://mlsanity.com/paper/1803.11285/) (2018)
- [University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localization](https://mlsanity.com/paper/2002.12186/) (2020)
- [End-to-end Learning of Deep Visual Representations for Image Retrieval](https://mlsanity.com/paper/1610.07940/) (2016)
- [Smooth-AP: Smoothing the Path Towards Large-Scale Image Retrieval](https://mlsanity.com/paper/2007.12163/) (2020)
- [Few-Shot Learning Through an Information Retrieval Lens](https://mlsanity.com/paper/1707.02610/) (2017)
- [Understanding Image Retrieval Re-Ranking: A Graph Neural Network Perspective](https://mlsanity.com/paper/2012.07620/) (2020)
- [Efficient Image Retrieval via Decoupling Diffusion into Online and Offline Processing](https://mlsanity.com/paper/1811.10907/) (2018)
- [Unifying Deep Local and Global Features for Image Search](https://mlsanity.com/paper/2001.05027/) (2020)
- [Challenging deep image descriptors for retrieval in heterogeneous iconographic collections](https://mlsanity.com/paper/1909.08866/) (2019)
- [Unifying Remote Sensing Image Retrieval and Classification with Robust Fine-tuning](https://mlsanity.com/paper/2102.13392/) (2021)

## Abstract (arXiv)

With impressive results in applications relying on feature learning, deep learning has also blurred the line between algorithm and data. Pick a training dataset, pick a backbone network for feature extraction, and voil`a ; this usually works for a variety of use cases. But the underlying hypothesis that there exists a training dataset matching the use case is not always met. Moreover, the demand for interconnections regardless of the variations of the content calls for increasing generalization and robustness in features. An interesting application characterized by these problematics is the connection of historical and cultural databases of images. Through the seemingly simple task of instance retrieval, we propose to show that it is not trivial to pick features responding well to a panel of variations and semantic content. Introducing a new enhanced version of the Alegoria benchmark, we compare descriptors using the detailed annotations. We further give insights about the core problems in instance retrieval, testing four state-of-the-art additional techniques to increase performance.