MITE-Net: SWaP-Optimized 4K Video Tiny Target Perception for Embodied Edge SAR

• URL: http://arxiv.org/abs/2608.15830v1
• Date: Sun, 16 Aug 2026 16:02:56 GMT
• Title: MITE-Net: SWaP-Optimized 4K Video Tiny Target Perception for Embodied Edge SAR
• Abstract summary: Real-time tiny target perception in high-resolution imagery is critical for embodied Search-and-Rescue (SAR) missions.<n>This paper introduces a comprehensive framework encompassing a novel architecture, specialized datasets, and hardware-level benchmarks.
• Score: 9.484473274465303
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Real-time tiny target perception in high-resolution imagery is critical for embodied Search-and-Rescue (SAR) missions. However, strict Size, Weight, and Power (SWaP) constraints on edge devices like UAVs create a bottleneck: traditional image downsampling causes severe feature loss, while slice-based processing incurs prohibitive latency. To address this gap, this paper introduces a comprehensive framework encompassing a novel architecture, specialized datasets, and hardware-level benchmarks. First, we propose MITE-Net, a SWaP-optimized cascaded architecture, which couples a bio-inspired, learning-free Tiny Target Motion-Based Region Proposal Network (TTM-RPN) with a sub-0.14M-parameter R-CNN-like head. Second, to standardize 4K tiny target evaluation, we construct the SAR-Tiny Datasets by relabeling two challenging UAV datasets: SeaDroneSee-Tiny (dynamic maritime scenes, tiny targets predominantly of 64-256 pixels ) and UAVID-Tiny (cluttered urban scenes, extremely tiny targets, less than 64 pixels). Third, we benchmark against state-of-the-art YOLO models on an edge device, NVIDIA Jetson AGX Xavier, where MITE-Net directly processes 4K maritime imagery, achieving a 100\% search success rate at 30.33 FPS. Consuming merely 3.19 W (9.51 FPS/W), MITE-Net vastly outperforms YOLO baselines in target recall and energy efficiency. Conversely, UAVID-Tiny evaluations expose a compound structural limitation: the learning-free bionic front-end struggles against urban backgrounds, while the ultra-lightweight head lacks representational capacity for complex features. Ultimately, this work delivers an efficient onboard perception paradigm and a rigorous baseline guiding future end-to-end SAR architectures.

Related papers

• LCMamNet: A Lightweight Cross-scale Mamba Network for Infrared Small Target Detection [53.811713750107934]
  We propose LCMamNet, a lightweight cross-scale Mamba network for infrared small target detection.<n>A compact hierarchical encoder with cross-shaped directional bottleneck residual blocks strengthens direction-sensitive target structures.<n>Experiments on IRSTD-1k, NUAA-SIRST, and NUDT-SIRST show that the proposed network achieves mIoU scores of 71.25%, 79.60%, and 95.58%, respectively.
  arXiv  Detail & Related papers  (2026-07-27T09:06:14Z)
• DepthART: Scaling Foundation Monocular Depth to Tiny Models [51.10174763031444]
  DepthART is a compact MDE model for on-device deployment across diverse scenes.<n>We show how DepthART consistently surpasses previous tiny baselines in both zero-shot generalization and metric accuracy.<n>We also provide a scalable model family, with DepthART-S reaching 347/245 FPS (strict FP32) on an GTX A6000 at $2242/4482$, 102 FPS (TF32) on a Orin NX 8GB, and over 15 FPS (FP32) on a Jetson Nano 4GB.
  arXiv  Detail & Related papers  (2026-07-19T06:54:52Z)
• LocalNav: Distilling Frontier VLMs and Embodied RL for On-Device Object Goal Navigation [53.88286427894783]
  Vision Language Models (VLMs) have emerged in the robotic domain as a powerful tool that enables environmental perception with language context.<n>Yet, their computational footprint typically confines them to cloud execution, hindering low-latency inference with local deployment on resource-constrained robots.<n>We present a distillation strategy that transfers complex spatial-semantic reasoning from large frontier models into a lightweight, 4B- parameter local VLM for edge execution on embedded GPU devices.
  arXiv  Detail & Related papers  (2026-06-26T09:11:59Z)
• LightAVSeg: Lightweight Audio-Visual Segmentation [67.18006751024687]
  LightAVSeg replaces heavy attention with a decoupled design for semantic filtering and spatial grounding.<n>Experiments demonstrate it achieves a new state-of-the-art among lightweight methods.<n>It reaches 50.4 mIoU on the MS3 benchmark and enables efficient inference on a mobile processor.
  arXiv  Detail & Related papers  (2026-05-09T08:47:54Z)
• SDD-YOLO: A Small-Target Detection Framework for Ground-to-Air Anti-UAV Surveillance with Edge-Efficient Deployment [10.723885979419954]
  We propose SDD-YOLO, a small-target detection framework tailored for G2A anti-UAV surveillance.<n>To capture fine-grained spatial details critical for micro-targets, SDD-YOLO introduces a P2 high-resolution detection head operating at 4 times downsampling.<n>Experiments demonstrate that SDD-YOLO-n achieves a mAP@0.5 of 86.4% on DroneSOD-30K, surpassing the YOLOv5n baseline by 7.8 percentage points.
  arXiv  Detail & Related papers  (2026-03-26T09:17:39Z)
• PiLoT: Neural Pixel-to-3D Registration for UAV-based Ego and Target Geo-localization [26.426290913965456]
  We present PiLoT, a unified framework that tackles UAV-based ego and target geo-localization.<n>We introduce three key contributions: 1) a Dual-Thread Engine that decouples map rendering from core localization thread, ensuring both low latency and drift-free accuracy.<n>This dataset enables the training of a lightweight network that generalizes in a zero-shot manner from simulation to real data.
  arXiv  Detail & Related papers  (2026-03-21T12:08:46Z)
• TY-RIST: Tactical YOLO Tricks for Real-time Infrared Small Target Detection [6.0340092200636475]
  Infrared small target detection (IRSTD) is critical for defense and surveillance but remains challenging.<n>We propose TY-RIST, an optimized YOLOv12n architecture that integrates a stride-aware backbone with fine-grained receptive fields.<n>Experiments on four benchmarks and across 20 different models demonstrate state-of-the-art performance, improving mAP at 0.5 IoU by +7.9%, Precision by +3%, and Recall by +10.2%.
  arXiv  Detail & Related papers  (2025-09-26T20:36:57Z)
• High-Frequency Semantics and Geometric Priors for End-to-End Detection Transformers in Challenging UAV Imagery [6.902247657565531]
  We introduce HEDS-DETR, a holistically enhanced real-time Detection Transformer tailored for aerial scenes.<n>First, we propose a novel High-Frequency Enhanced Semantics Network (HFESNet) backbone, which yields highly discriminative features.<n>Second, our Efficient Small Object Pyramid (ESOP) counteracts information loss by efficiently fusing high-resolution features.<n>Third, we enhance decoder stability and localization precision with two synergistic components.
  arXiv  Detail & Related papers  (2025-07-01T14:56:56Z)
• NOVA: Navigation via Object-Centric Visual Autonomy for High-Speed Target Tracking in Unstructured GPS-Denied Environments [56.35569661650558]
  We introduce NOVA, a fully onboard, object-centric framework that enables robust target tracking and collision-aware navigation.<n>Rather than constructing a global map, NOVA formulates perception, estimation, and control entirely in the target's reference frame.<n>We validate NOVA across challenging real-world scenarios, including urban mazes, forest trails, and repeated transitions through buildings with intermittent GPS loss.
  arXiv  Detail & Related papers  (2025-06-23T14:28:30Z)
• A Lightweight Target-Driven Network of Stereo Matching for Inland Waterways [24.432957277833562]
  LTNet is a lightweight target-driven stereo matching neural network. In experiments on two datasets, LTNet achieves competitive results, with only 3.7M parameters.
  arXiv  Detail & Related papers  (2024-10-10T13:40:30Z)
• A lightweight and accurate YOLO-like network for small target detection in Aerial Imagery [94.78943497436492]
  We present YOLO-S, a simple, fast and efficient network for small target detection. YOLO-S exploits a small feature extractor based on Darknet20, as well as skip connection, via both bypass and concatenation. YOLO-S has an 87% decrease of parameter size and almost one half FLOPs of YOLOv3, making practical the deployment for low-power industrial applications.
  arXiv  Detail & Related papers  (2022-04-05T16:29:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.