# DenseScout: Algorithm-System Co-design for Budgeted Tiny Object Selection on Edge Platforms

arXiv: https://arxiv.org/abs/2604.25300 · HTML: https://mlsanity.com/paper/2604.25300/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 38 references that are in the map.
- First posted on arXiv 28 Apr 2026.

## Builds on (most cited first, 15 of 15)

- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [DOTA: A Large-scale Dataset for Object Detection in Aerial Images](https://mlsanity.com/paper/1711.10398/) (2017)
- [Detection and Tracking Meet Drones Challenge](https://mlsanity.com/paper/2001.06303/) (2020)
- [Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges](https://mlsanity.com/paper/2102.12219/) (2021)
- [Clustered Object Detection in Aerial Images](https://mlsanity.com/paper/1904.08008/) (2019)
- [AutoFocus: Efficient Multi-Scale Inference](https://mlsanity.com/paper/1812.01600/) (2018)
- [Learning RoI Transformer for Detecting Oriented Objects in Aerial Images](https://mlsanity.com/paper/1812.00155/) (2018)
- [InsPLAD: A Dataset and Benchmark for Power Line Asset Inspection in UAV Images](https://mlsanity.com/paper/2311.01619/) (2023)
- [AdaZoom: Adaptive Zoom Network for Multi-Scale Object Detection in Large Scenes](https://mlsanity.com/paper/2106.10409/) (2021)
- [AttentionMask: Attentive, Efficient Object Proposal Generation Focusing on Small Objects](https://mlsanity.com/paper/1811.08728/) (2018)
- [Improving Semantic Segmentation of Aerial Images Using Patch-based Attention](https://mlsanity.com/paper/1911.08877/) (2019)
- [Patch-based Selection and Refinement for Early Object Detection](https://mlsanity.com/paper/2311.02274/) (2023)
- [Deep Learning in Automated Power Line Inspection: A Review](https://mlsanity.com/paper/2502.07826/) (2025)
- [Uirapuru: Timely Video Analytics for High-Resolution Steerable Cameras on Edge Devices](https://mlsanity.com/paper/2509.01371/) (2025)

## Abstract (arXiv)

Deploying high-resolution tiny-object perception on edge platforms requires not only accurate localization, but also selecting a small set of informative patches under compute, transport, and latency constraints. We study budgeted tiny-object selection, where a frontend ranks patch centers from a lightweight proxy and a downstream detector processes only the selected regions. DenseScout is a 1.01M-parameter deployment-oriented dense-response selector that removes detector-style box regression and directly optimizes ranked patch-center prioritization. Its contribution lies in the task-specific selector formulation, the alignment among output representation, supervision, and decoding, and its joint design with transport-aware execution and QoS-oriented evaluation. Under unified protocols on VisDrone and DOTA, DenseScout provides stronger low-budget recall than the evaluated detector-derived selectors; controlled fixed-K inspection experiments further demonstrate advantages over selection-style proxy baselines. Cross-platform profiling on Jetson Orin NX and RK3588 shows that deployable utility depends jointly on selector quality, memory movement, and heterogeneous runtime realization. These results support treating edge tiny-object perception as a selection-and-deployment co-design problem rather than evaluating model accuracy and runtime in isolation.