# Better Sampling, towards Better End-to-end Small Object Detection

arXiv: https://arxiv.org/abs/2407.06127 · HTML: https://mlsanity.com/paper/2407.06127/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 32 references that are in the map.
- First posted on arXiv 17 May 2024.

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

- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [Exploring Plain Vision Transformer Backbones for Object Detection](https://mlsanity.com/paper/2203.16527/) (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)
- [Sparse R-CNN: End-to-End Object Detection with Learnable Proposals](https://mlsanity.com/paper/2011.12450/) (2020)
- [Conditional DETR for Fast Training Convergence](https://mlsanity.com/paper/2108.06152/) (2021)
- [R-FCN: Object Detection via Region-based Fully Convolutional Networks](https://mlsanity.com/paper/1605.06409/) (2016)
- [Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection](https://mlsanity.com/paper/2006.04388/) (2020)
- [Relation Networks for Object Detection](https://mlsanity.com/paper/1711.11575/) (2017)
- [VarifocalNet: An IoU-aware Dense Object Detector](https://mlsanity.com/paper/2008.13367/) (2020)
- [Scale-Aware Trident Networks for Object Detection](https://mlsanity.com/paper/1901.01892/) (2019)
- [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)
- [Towards Large-Scale Small Object Detection: Survey and Benchmarks](https://mlsanity.com/paper/2207.14096/) (2022)
- [Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks](https://mlsanity.com/paper/1512.04143/) (2015)
- [AugFPN: Improving Multi-scale Feature Learning for Object Detection](https://mlsanity.com/paper/1912.05384/) (2019)
- [A Normalized Gaussian Wasserstein Distance for Tiny Object Detection](https://mlsanity.com/paper/2110.13389/) (2021)
- [Anchor DETR: Query Design for Transformer-Based Object Detection](https://mlsanity.com/paper/2109.07107/) (2021)
- [MDSSD: Multi-scale Deconvolutional Single Shot Detector for Small Objects](https://mlsanity.com/paper/1805.07009/) (2018)
- [Learning Multilayer Channel Features for Pedestrian Detection](https://mlsanity.com/paper/1603.00124/) (2016)

## Abstract (arXiv)

While deep learning-based general object detection has made significant strides in recent years, the effectiveness and efficiency of small object detection remain unsatisfactory. This is primarily attributed not only to the limited characteristics of such small targets but also to the high density and mutual overlap among these targets. The existing transformer-based small object detectors do not leverage the gap between accuracy and inference speed. To address challenges, we propose methods enhancing sampling within an end-to-end framework. Sample Points Refinement (SPR) constrains localization and attention, preserving meaningful interactions in the region of interest and filtering out misleading information. Scale-aligned Target (ST) integrates scale information into target confidence, improving classification for small object detection. A task-decoupled Sample Reweighting (SR) mechanism guides attention toward challenging positive examples, utilizing a weight generator module to assess the difficulty and adjust classification loss based on decoder layer outcomes. Comprehensive experiments across various benchmarks reveal that our proposed detector excels in detecting small objects. Our model demonstrates a significant enhancement, achieving a 2.9% increase in average precision (AP) over the state-of-the-art (SOTA) on the VisDrone dataset and a 1.7% improvement on the SODA-D dataset.