# Small Object Detection via Coarse-to-fine Proposal Generation and Imitation Learning

arXiv: https://arxiv.org/abs/2308.09534 · HTML: https://mlsanity.com/paper/2308.09534/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 54 references that are in the map.
- First posted on arXiv 18 Aug 2023.

## Builds on (most cited first, 30 of 37)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [CornerNet: Detecting Objects as Paired Keypoints](https://mlsanity.com/paper/1808.01244/) (2018)
- [Focal Loss for Dense Object Detection](https://mlsanity.com/paper/1708.02002/) (2017)
- [Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection](https://mlsanity.com/paper/1912.02424/) (2019)
- [Sparse R-CNN: End-to-End Object Detection with Learnable Proposals](https://mlsanity.com/paper/2011.12450/) (2020)
- [RepPoints: Point Set Representation for Object Detection](https://mlsanity.com/paper/1904.11490/) (2019)
- [Exploring Cross-Image Pixel Contrast for Semantic Segmentation](https://mlsanity.com/paper/2101.11939/) (2021)
- [Oriented R-CNN for Object Detection](https://mlsanity.com/paper/2108.05699/) (2021)
- [UnitBox: An Advanced Object Detection Network](https://mlsanity.com/paper/1608.01471/) (2016)
- [DetCo: Unsupervised Contrastive Learning for Object Detection](https://mlsanity.com/paper/2102.04803/) (2021)
- [Align Deep Features for Oriented Object Detection](https://mlsanity.com/paper/2008.09397/) (2020)
- [Dynamic Head: Unifying Object Detection Heads with Attentions](https://mlsanity.com/paper/2106.08322/) (2021)
- [S3FD: Single Shot Scale-invariant Face Detector](https://mlsanity.com/paper/1708.05237/) (2017)
- [Gliding vertex on the horizontal bounding box for multi-oriented object detection](https://mlsanity.com/paper/1911.09358/) (2019)
- [Towards Large-Scale Small Object Detection: Survey and Benchmarks](https://mlsanity.com/paper/2207.14096/) (2022)
- [Anchor-free Oriented Proposal Generator for Object Detection](https://mlsanity.com/paper/2110.01931/) (2021)
- [Oriented RepPoints for Aerial Object Detection](https://mlsanity.com/paper/2105.11111/) (2021)
- [Region Proposal by Guided Anchoring](https://mlsanity.com/paper/1901.03278/) (2019)

## Built on by (most cited first, 27 of 27)

- [CYCLO: Cyclic Graph Transformer Approach to Multi-Object Relationship Modeling in Aerial Videos](https://mlsanity.com/paper/2406.01029/) (2024)
- [Visible and Clear: Finding Tiny Objects in Difference Map](https://mlsanity.com/paper/2405.11276/) (2024)
- [Inspiring the Next Generation of Segment Anything Models: Comprehensively Evaluate SAM and SAM 2 with Diverse Prompts Towards Context-Dependent Concepts under Different Scenes](https://mlsanity.com/paper/2412.01240/) (2024)
- [RAW-Diffusion: RGB-Guided Diffusion Models for High-Fidelity RAW Image Generation](https://mlsanity.com/paper/2411.13150/) (2024)
- [Real, Fake, or Manipulated? Detecting Machine-Influenced Text](https://mlsanity.com/paper/2509.15350/) (2025)
- [XS-VID: A Large-Scale Benchmark for Small Object Detection and Tracking in Videos](https://mlsanity.com/paper/2407.18137/) (2024)
- [Oriented Tiny Object Detection: A Dataset, Benchmark, and Dynamic Unbiased Learning](https://mlsanity.com/paper/2412.11582/) (2024)
- [Constellation Dataset: Benchmarking High-Altitude Object Detection for an Urban Intersection](https://mlsanity.com/paper/2404.16944/) (2024)
- [YOLOMG: Vision-based Drone-to-Drone Detection with Appearance and Pixel-Level Motion Fusion](https://mlsanity.com/paper/2503.07115/) (2025)
- [CM-Diff: A Single Generative Network for Bidirectional Cross-Modality Translation Diffusion Model Between Infrared and Visible Images](https://mlsanity.com/paper/2503.09514/) (2025)
- [COST: Contrastive One-Stage Transformer for Vision-Language Small Object Tracking](https://mlsanity.com/paper/2504.01321/) (2025)
- [FADE: A Dataset for Detecting Falling Objects around Buildings in Video](https://mlsanity.com/paper/2408.05750/) (2024)
- [Multi-Point Positional Insertion Tuning for Small Object Detection](https://mlsanity.com/paper/2412.18090/) (2024)
- [Cross-DINO: Cross the Deep MLP and Transformer for Small Object Detection](https://mlsanity.com/paper/2505.21868/) (2025)
- [Power Battery Detection](https://mlsanity.com/paper/2508.07797/) (2025)
- [Global Context or Local Detail? Adaptive Visual Grounding for Hallucination Mitigation](https://mlsanity.com/paper/2604.24396/) (2026)
- [Learning Collective Dynamics of Multi-Agent Systems using Event-based Vision](https://mlsanity.com/paper/2411.07039/) (2024)
- [Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection](https://mlsanity.com/paper/2504.20602/) (2025)
- [PerioDet: Large-Scale Panoramic Radiograph Benchmark for Clinical-Oriented Apical Periodontitis Detection](https://mlsanity.com/paper/2507.18958/) (2025)
- [Revisiting DETR for Small Object Detection via Noise-Resilient Query Optimization](https://mlsanity.com/paper/2507.19059/) (2025)
- [Inter-Class Relational Loss for Small Object Detection: A Case Study on License Plates](https://mlsanity.com/paper/2508.14343/) (2025)
- [Scale-Aware Relay and Scale-Adaptive Loss for Tiny Object Detection in Aerial Images](https://mlsanity.com/paper/2511.09891/) (2025)
- [CGC: Compositional Grounded Contrast for Fine-Grained Multi-Image Understanding](https://mlsanity.com/paper/2604.22498/) (2026)
- [Denoising-Enhanced Coarse-to-Fine Infrared Small Target Detection with Attention Prior-Guided Knowledge Distillation](https://mlsanity.com/paper/2606.21956/) (2026)
- [Adaptive Spectrum-Aware Feature Disentangled Network for Small Object Detection](https://mlsanity.com/paper/2606.29029/) (2026)
- [DyFrDet: Towards Accurate Small Object Detection via Dynamic Frequency Suppression with Label Disambiguation](https://mlsanity.com/paper/2608.02495/) (2026)
- [EECTracker: Swarm Motion Prior-Guided Feature Compensation for Airborne Optical UAV Swarm Tracking](https://mlsanity.com/paper/2609.15171/) (2026)

## Abstract (arXiv)

The past few years have witnessed the immense success of object detection, while current excellent detectors struggle on tackling size-limited instances. Concretely, the well-known challenge of low overlaps between the priors and object regions leads to a constrained sample pool for optimization, and the paucity of discriminative information further aggravates the recognition. To alleviate the aforementioned issues, we propose CFINet, a two-stage framework tailored for small object detection based on the Coarse-to-fine pipeline and Feature Imitation learning. Firstly, we introduce Coarse-to-fine RPN (CRPN) to ensure sufficient and high-quality proposals for small objects through the dynamic anchor selection strategy and cascade regression. Then, we equip the conventional detection head with a Feature Imitation (FI) branch to facilitate the region representations of size-limited instances that perplex the model in an imitation manner. Moreover, an auxiliary imitation loss following supervised contrastive learning paradigm is devised to optimize this branch. When integrated with Faster RCNN, CFINet achieves state-of-the-art performance on the large-scale small object detection benchmarks, SODA-D and SODA-A, underscoring its superiority over baseline detector and other mainstream detection approaches.