# Needles in Haystacks: On Classifying Tiny Objects in Large Images

arXiv: https://arxiv.org/abs/1908.06037 · HTML: https://mlsanity.com/paper/1908.06037/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Aug 2019.

## Built on by (most cited first, 13 of 13)

- [Multimodal Needle in a Haystack: Benchmarking Long-Context Capability of Multimodal Large Language Models](https://mlsanity.com/paper/2406.11230/) (2024)
- [Efficient Classification of Very Large Images with Tiny Objects](https://mlsanity.com/paper/2106.02694/) (2021)
- [Quantum Tensor Network in Machine Learning: An Application to Tiny Object Classification](https://mlsanity.com/paper/2101.03154/) (2021)
- [ACAT: Adversarial Counterfactual Attention for Classification and Detection in Medical Imaging](https://mlsanity.com/paper/2303.15421/) (2023)
- [GRASP: GRAph-Structured Pyramidal Whole Slide Image Representation](https://mlsanity.com/paper/2402.03592/) (2024)
- [Weakly Supervised Faster-RCNN+FPN to classify animals in camera trap images](https://mlsanity.com/paper/2208.14060/) (2022)
- [Prospector Heads: Generalized Feature Attribution for Large Models & Data](https://mlsanity.com/paper/2402.11729/) (2024)
- [OTI: A Model-free and Visually Interpretable Measure of Image Attackability](https://mlsanity.com/paper/2601.17536/) (2026)
- [Interpretable and Interactive Deep Multiple Instance Learning for Dental Caries Classification in Bitewing X-rays](https://mlsanity.com/paper/2112.09694/) (2021)
- [Efficient Classification of Histopathology Images](https://mlsanity.com/paper/2409.13720/) (2024)
- [On the Generalizability of Iterative Patch Selection for Memory-Efficient High-Resolution Image Classification](https://mlsanity.com/paper/2412.11237/) (2024)
- [Learning to Zoom Efficiently with a Contrastive Curriculum](https://mlsanity.com/paper/2609.03206/) (2026)
- [Beyond Resolution: Object-to-Image Ratio Mismatch in Instance Retrieval](https://mlsanity.com/paper/2610.11489/) (2026)

## Abstract (arXiv)

In some important computer vision domains, such as medical or hyperspectral imaging, we care about the classification of tiny objects in large images. However, most Convolutional Neural Networks (CNNs) for image classification were developed using biased datasets that contain large objects, in mostly central image positions. To assess whether classical CNN architectures work well for tiny object classification we build a comprehensive testbed containing two datasets: one derived from MNIST digits and one from histopathology images. This testbed allows controlled experiments to stress-test CNN architectures with a broad spectrum of signal-to-noise ratios. Our observations indicate that: (1) There exists a limit to signal-to-noise below which CNNs fail to generalize and that this limit is affected by dataset size - more data leading to better performances; however, the amount of training data required for the model to generalize scales rapidly with the inverse of the object-to-image ratio (2) in general, higher capacity models exhibit better generalization; (3) when knowing the approximate object sizes, adapting receptive field is beneficial; and (4) for very small signal-to-noise ratio the choice of global pooling operation affects optimization, whereas for relatively large signal-to-noise values, all tested global pooling operations exhibit similar performance.