# Learning to Borrow Features for Improved Detection of Small Objects in Single-Shot Detectors

arXiv: https://arxiv.org/abs/2505.00044 · HTML: https://mlsanity.com/paper/2505.00044/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 35 references that are in the map.
- First posted on arXiv 30 Apr 2025.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (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)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [YOLO9000: Better, Faster, Stronger](https://mlsanity.com/paper/1612.08242/) (2016)
- [Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition](https://mlsanity.com/paper/1406.4729/) (2014)
- [Understanding the Effective Receptive Field in Deep Convolutional Neural Networks](https://mlsanity.com/paper/1701.04128/) (2017)
- [S3FD: Single Shot Scale-invariant Face Detector](https://mlsanity.com/paper/1708.05237/) (2017)
- [DSSD : Deconvolutional Single Shot Detector](https://mlsanity.com/paper/1701.06659/) (2017)
- [Single-Shot Refinement Neural Network for Object Detection](https://mlsanity.com/paper/1711.06897/) (2017)
- [Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks](https://mlsanity.com/paper/1512.04143/) (2015)
- [RON: Reverse Connection with Objectness Prior Networks for Object Detection](https://mlsanity.com/paper/1707.01691/) (2017)
- [Diffusion Modeling with Domain-conditioned Prior Guidance for Accelerated MRI and qMRI Reconstruction](https://mlsanity.com/paper/2309.00783/) (2023)
- [An Optimization-Based Meta-Learning Model for MRI Reconstruction with Diverse Dataset](https://mlsanity.com/paper/2110.00715/) (2021)
- [What are the Receptive, Effective Receptive, and Projective Fields of Neurons in Convolutional Neural Networks?](https://mlsanity.com/paper/1705.07049/) (2017)
- [A Learnable Variational Model for Joint Multimodal MRI Reconstruction and Synthesis](https://mlsanity.com/paper/2204.03804/) (2022)
- [Feature-Fused SSD: Fast Detection for Small Objects](https://mlsanity.com/paper/1709.05054/) (2017)
- [Application of an ANN and LSTM-based Ensemble Model for Stock Market Prediction](https://mlsanity.com/paper/2410.20253/) (2024)
- [Seeing Small Faces from Robust Anchor's Perspective](https://mlsanity.com/paper/1802.09058/) (2018)
- [An Optimal Control Framework for Joint-channel Parallel MRI Reconstruction without Coil Sensitivities](https://mlsanity.com/paper/2109.09738/) (2021)
- [Deep Parallel MRI Reconstruction Network Without Coil Sensitivities](https://mlsanity.com/paper/2008.01410/) (2020)
- [Multi-task Magnetic Resonance Imaging Reconstruction using Meta-learning](https://mlsanity.com/paper/2403.19966/) (2024)
- [Optimization-Based Deep learning methods for Magnetic Resonance Imaging Reconstruction and Synthesis](https://mlsanity.com/paper/2303.01515/) (2023)
- [Detecting Small Signs from Large Images](https://mlsanity.com/paper/1706.08574/) (2017)

## Abstract (arXiv)

Detecting small objects remains a significant challenge in single-shot object detectors due to the inherent trade-off between spatial resolution and semantic richness in convolutional feature maps. To address this issue, we propose a novel framework that enables small object representations to "borrow" discriminative features from larger, semantically richer instances within the same class. Our architecture introduces three key components: the Feature Matching Block (FMB) to identify semantically similar descriptors across layers, the Feature Representing Block (FRB) to generate enhanced shallow features through weighted aggregation, and the Feature Fusion Block (FFB) to refine feature maps by integrating original, borrowed, and context information. Built upon the SSD framework, our method improves the descriptive capacity of shallow layers while maintaining real-time detection performance. Experimental results demonstrate that our approach significantly boosts small object detection accuracy over baseline methods, offering a promising direction for robust object detection in complex visual environments.