paper-with-me

Papers

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

2026-04-28 · Xiong Zhouzhi, Zimo Zeng, Yi Chen, Shuqi Xu, Yunfeng Yan, Donglian Qi 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.

📄 PDF Abstract BibTeX arXiv:2604.25300

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Revisiting Wedge Sampling for Budgeted Maximum Inner Product Search

2019-08-23 · Stephan S. Lorenzen, Ninh Pham

Top-k maximum inner product search (MIPS) is a central task in many machine learning applications. This paper extends top-k MIPS with a budgeted setting, that asks for the best approximate top-k MIPS given a limit of B c…

Recommendation Systems

FairQuant: Fairness-Aware Mixed-Precision Quantization for Medical Image Classification

2026-02-26 · Thomas Woergaard, Raghavendra Selvan arxiv

Compressing neural networks by quantizing model parameters offers useful trade-off between performance and efficiency. Methods like quantization-aware training and post-training quantization strive to maintain the downst…

Medical Image Classification

TCUQ: Single-Pass Uncertainty Quantification from Temporal Consistency with Streaming Conformal Calibration for TinyML

2025-08-18 · Ismail Lamaakal, Chaymae Yahyati, Khalid El Makkaoui, Ibrahim Ouahbi 외 arxiv

We introduce TCUQ, a single pass, label free uncertainty monitor for streaming TinyML that converts short horizon temporal consistency captured via lightweight signals on posteriors and features into a calibrated risk sc…

Budgeted Classification with Rejection: An Evolutionary Method with Multiple Objectives

2022-05-01 · Nolan H. Hamilton, Errin Fulp

Classification systems are often deployed in resource-constrained settings where labels must be assigned to inputs on a budget of time, memory, etc. Budgeted, sequential classifiers (BSCs) address these scenarios by proc…

Tiny Machine Learning: Progress and Futures

2024-03-28 · Ji Lin, Ligeng Zhu, Wei-Ming Chen, Wei-Chen Wang 외

Tiny Machine Learning (TinyML) is a new frontier of machine learning. By squeezing deep learning models into billions of IoT devices and microcontrollers (MCUs), we expand the scope of AI applications and enable ubiquito…

Deep Learning