# Deep-NFA: a Deep textita contrario Framework for Small Object Detection

arXiv: https://arxiv.org/abs/2303.01363 · HTML: https://mlsanity.com/paper/2303.01363/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 51 references that are in the map.
- First posted on arXiv 2 Mar 2023.

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation](https://mlsanity.com/paper/2102.04306/) (2021)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks](https://mlsanity.com/paper/1910.03151/) (2019)
- [Stand-Alone Self-Attention in Vision Models](https://mlsanity.com/paper/1906.05909/) (2019)
- [Recurrent Models of Visual Attention](https://mlsanity.com/paper/1406.6247/) (2014)
- [Road Extraction by Deep Residual U-Net](https://mlsanity.com/paper/1711.10684/) (2017)
- [Attention Mechanisms in Computer Vision: A Survey](https://mlsanity.com/paper/2111.07624/) (2021)
- [Asymmetric Contextual Modulation for Infrared Small Target Detection](https://mlsanity.com/paper/2009.14530/) (2020)
- [Dense Nested Attention Network for Infrared Small Target Detection](https://mlsanity.com/paper/2106.00487/) (2021)
- [UIU-Net: U-Net in U-Net for Infrared Small Object Detection](https://mlsanity.com/paper/2212.00968/) (2022)
- [Attentional Local Contrast Networks for Infrared Small Target Detection](https://mlsanity.com/paper/2012.08573/) (2020)
- [Slicing Aided Hyper Inference and Fine-tuning for Small Object Detection](https://mlsanity.com/paper/2202.06934/) (2022)
- [Augmentation for small object detection](https://mlsanity.com/paper/1902.07296/) (2019)
- [Extended Feature Pyramid Network for Small Object Detection](https://mlsanity.com/paper/2003.07021/) (2020)
- [Infrared Small-Dim Target Detection with Transformer under Complex Backgrounds](https://mlsanity.com/paper/2109.14379/) (2021)
- [Automatic Crack Detection on Road Pavements Using Encoder Decoder Architecture](https://mlsanity.com/paper/2007.00477/) (2020)
- [Efficient Evaluation of the Number of False Alarm Criterion](https://mlsanity.com/paper/1807.03594/) (2018)

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

- [textitA Contrario Paradigm for YOLO-based Infrared Small Target Detection](https://mlsanity.com/paper/2402.02288/) (2024)
- [Cross-View Localization via Redundant Sliced Observations and A-Contrario Validation](https://mlsanity.com/paper/2508.05369/) (2025)

## Abstract (arXiv)

The detection of small objects is a challenging task in computer vision. Conventional object detection methods have difficulty in finding the balance between high detection and low false alarm rates. In the literature, some methods have addressed this issue by enhancing the feature map responses, but without guaranteeing robustness with respect to the number of false alarms induced by background elements. To tackle this problem, we introduce an textita contrario decision criterion into the learning process to take into account the unexpectedness of small objects. This statistic criterion enhances the feature map responses while controlling the number of false alarms (NFA) and can be integrated into any semantic segmentation neural network. Our add-on NFA module not only allows us to obtain competitive results for small target and crack detection tasks respectively, but also leads to more robust and interpretable results.