# Small Object Detection by DETR via Information Augmentation and Adaptive Feature Fusion

arXiv: https://arxiv.org/abs/2401.08017 · HTML: https://mlsanity.com/paper/2401.08017/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 37 references that are in the map.
- First posted on arXiv 16 Jan 2024.

## Builds on (most cited first, 23 of 23)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [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)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://mlsanity.com/paper/1707.01083/) (2017)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://mlsanity.com/paper/2207.02696/) (2022)
- [DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR](https://mlsanity.com/paper/2201.12329/) (2022)
- [DETRs Beat YOLOs on Real-time Object Detection](https://mlsanity.com/paper/2304.08069/) (2023)
- [DN-DETR: Accelerate DETR Training by Introducing Query DeNoising](https://mlsanity.com/paper/2203.01305/) (2022)
- [A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects](https://mlsanity.com/paper/2004.02806/) (2020)
- [Dynamic Head: Unifying Object Detection Heads with Attentions](https://mlsanity.com/paper/2106.08322/) (2021)
- [Rethinking Transformer-based Set Prediction for Object Detection](https://mlsanity.com/paper/2011.10881/) (2020)
- [Small Object Detection using Context and Attention](https://mlsanity.com/paper/1912.06319/) (2019)
- [Beyond Self-Supervision: A Simple Yet Effective Network Distillation Alternative to Improve Backbones](https://mlsanity.com/paper/2103.05959/) (2021)
- [Enhancing Object Detection for Autonomous Driving by Optimizing Anchor Generation and Addressing Class Imbalance](https://mlsanity.com/paper/2104.03888/) (2021)
- [Optimisation of the PointPillars network for 3D object detection in point clouds](https://mlsanity.com/paper/2007.00493/) (2020)
- [Achieving Real-Time Object Detection on MobileDevices with Neural Pruning Search](https://mlsanity.com/paper/2106.14943/) (2021)

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

- [Assessing the Capability of YOLO- and Transformer-based Object Detectors for Real-time Weed Detection](https://mlsanity.com/paper/2501.17387/) (2025)
- [Enhancing Maritime Object Detection in Real-Time with RT-DETR and Data Augmentation](https://mlsanity.com/paper/2510.07346/) (2025)

## Abstract (arXiv)

The main challenge for small object detection algorithms is to ensure accuracy while pursuing real-time performance. The RT-DETR model performs well in real-time object detection, but performs poorly in small object detection accuracy. In order to compensate for the shortcomings of the RT-DETR model in small object detection, two key improvements are proposed in this study. Firstly, The RT-DETR utilises a Transformer that receives input solely from the final layer of Backbone features. This means that the Transformer's input only receives semantic information from the highest level of abstraction in the Deep Network, and ignores detailed information such as edges, texture or color gradients that are critical to the location of small objects at lower levels of abstraction. Including only deep features can introduce additional background noise. This can have a negative impact on the accuracy of small object detection. To address this issue, we propose the fine-grained path augmentation method. This method helps to locate small objects more accurately by providing detailed information to the deep network. So, the input to the transformer contains both semantic and detailed information. Secondly, In RT-DETR, the decoder takes feature maps of different levels as input after concatenating them with equal weight. However, this operation is not effective in dealing with the complex relationship of multi-scale information captured by feature maps of different sizes. Therefore, we propose an adaptive feature fusion algorithm that assigns learnable parameters to each feature map from different levels. This allows the model to adaptively fuse feature maps from different levels and effectively integrate feature information from different scales. This enhances the model's ability to capture object features at different scales, thereby improving the accuracy of detecting small objects.