HGSQ: Heatmap-Guided Sparse Query Detector for Real-Time Aerial Small Object Detection

• URL: http://arxiv.org/abs/2609.13306v1
• Date: Thu, 10 Sep 2026 12:52:34 GMT
• Title: HGSQ: Heatmap-Guided Sparse Query Detector for Real-Time Aerial Small Object Detection
• Abstract summary: Real-time aerial small object detection requires a detector to preserve fine-grained localization while avoiding redundant computation on large background regions.<n>This paper proposes HGSQ, a Heatmap-Guided Sparse Query Detector for real-time aerial small object detection.<n>HGSQ treats the heatmap as a real-time computation budget rather than a visualization map during deployment.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Real-time aerial small object detection is an important visual signal and image processing problem, requiring a detector to preserve fine-grained localization while avoiding redundant computation on large background regions. This paper focuses on this deployment-oriented aerial/UAV setting rather than claiming a universal detector for all object detection scenarios. Existing Transformer-based detectors provide strong global modeling, but their dense query initialization and multi-layer decoder still spend substantial computation on background tokens, which is inefficient when small objects occupy only sparse image regions. To address this problem, this paper proposes HGSQ, a Heatmap-Guided Sparse Query Detector for real-time aerial small object detection. HGSQ uses a lightweight Heatmap Budget Predictor (HBP) to predict a foreground budget map in a single forward pass. The predicted heatmap is then used by three fixed components: Heatmap-Guided Sparse Query Selection (HSQS), which initializes decoder queries from high-confidence foreground positions; Heatmap-Gated Lite Snake Convolution (HGLSConv), which performs local shape refinement only on heatmap-activated small-object regions; and Adaptive Query-Decoder Budgeting (AQDB), which adjusts the query budget and decoder depth according to the estimated object density. Unlike post-hoc heatmap generation, HGSQ treats the heatmap as a real-time computation budget rather than a visualization map during deployment. Experiments on NWPU VHR-10 and VisDrone2019 show that HGSQ achieves 95.10 mAP50 on NWPU VHR-10 and 54.8 mAP50 on VisDrone2019, while reducing GFLOPs to 48.6 and running at 96.0 FPS on an RTX 4070 under our TensorRT FP16 deployment protocol.

Related papers

• Gaze-DETR: Top-Down Guidance Through Priority Maps for Infrared Weak-Small UAV Detection with DETR [60.12701295852494]
  We propose Gaze-DETR, a detector that learns an internal priority map before localization.<n> Priority head predicts a normalized priority map from image features,RPFM enhances high-priority responses, and PAQI converts high-priority locations into decoder anchor queries.<n>Results show that explicit spatial-priority learning provides pre-localization guidance complementary to bounding-box supervision.
  arXiv  Detail & Related papers  (2026-07-21T12:29:58Z)
• Learning Where to Embed: Noise-Aware Positional Embedding for Query Retrieval in Small-Object Detection [2.2251429968996947]
  Transformer-based detectors have advanced small-object detection, but they often remain inefficient and vulnerable to background-induced query noise.<n>We present HELP, a noise-aware positional-semantic fusion framework that studies where to embed positional information.<n>Within HELP, we introduce Heatmap-guided Positional Embedding (HPE) as the core embedding mechanism and visualize it with a heatbar for interpretable diagnosis and fine-tuning.
  arXiv  Detail & Related papers  (2026-04-16T14:28:36Z)
• SparseFormer: Detecting Objects in HRW Shots via Sparse Vision Transformer [62.11796778482088]
  We present a novel model-agnostic sparse vision transformer, dubbed SparseFormer, to bridge the gap of object detection between close-up and HRW shots.<n>The proposed SparseFormer selectively uses attentive tokens to scrutinize the sparsely distributed windows that may contain objects.<n> experiments on two HRW benchmarks, PANDA and DOTA-v1.0, demonstrate that the proposed SparseFormer significantly improves detection accuracy (up to 5.8%) and speed (up to 3x) over the state-of-the-art approaches.
  arXiv  Detail & Related papers  (2025-02-11T03:21:25Z)
• DetToolChain: A New Prompting Paradigm to Unleash Detection Ability of MLLM [81.75988648572347]
  We present DetToolChain, a novel prompting paradigm to unleash the zero-shot object detection ability of multimodal large language models (MLLMs) Our approach consists of a detection prompting toolkit inspired by high-precision detection priors and a new Chain-of-Thought to implement these prompts. We show that GPT-4V with our DetToolChain improves state-of-the-art object detectors by +21.5% AP50 on MS Novel class set for open-vocabulary detection.
  arXiv  Detail & Related papers  (2024-03-19T06:54:33Z)
• Deep Homography Estimation for Visual Place Recognition [49.235432979736395]
  We propose a transformer-based deep homography estimation (DHE) network. It takes the dense feature map extracted by a backbone network as input and fits homography for fast and learnable geometric verification. Experiments on benchmark datasets show that our method can outperform several state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-02-25T13:22:17Z)
• SpirDet: Towards Efficient, Accurate and Lightweight Infrared Small Target Detector [60.42293239557962]
  We propose SpirDet, a novel approach for efficient detection of infrared small targets. We employ a new dual-branch sparse decoder to restore the feature map. Extensive experiments show that the proposed SpirDet significantly outperforms state-of-the-art models.
  arXiv  Detail & Related papers  (2024-02-08T05:06:14Z)
• V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detection [73.37781484123536]
  We introduce a highly performant 3D object detector for point clouds using the DETR framework. To address the limitation, we introduce a novel 3D Relative Position (3DV-RPE) method. We show exceptional results on the challenging ScanNetV2 benchmark.
  arXiv  Detail & Related papers  (2023-08-08T17:14:14Z)
• DisPlacing Objects: Improving Dynamic Vehicle Detection via Visual Place Recognition under Adverse Conditions [29.828201168816243]
  We investigate whether a prior map can be leveraged to aid in the detection of dynamic objects in a scene without the need for a 3D map. We contribute an algorithm which refines an initial set of candidate object detections and produces a refined subset of highly accurate detections using a prior map.
  arXiv  Detail & Related papers  (2023-06-30T10:46:51Z)
• KeyPosS: Plug-and-Play Facial Landmark Detection through GPS-Inspired True-Range Multilateration [28.96448680048584]
  KeyPoint Positioning System (KeyPosS) is first framework to deduce exact landmark coordinates by triangulating distances between points of interest and anchor points predicted by a fully convolutional network. Experiments on four datasets demonstrate state-of-the-art performance, with KeyPosS outperforming existing methods in low-resolution settings despite minimal computational overhead.
  arXiv  Detail & Related papers  (2023-05-25T19:30:21Z)
• HM-Net: A Regression Network for Object Center Detection and Tracking on Wide Area Motion Imagery [1.2249546377051437]
  We present our deep neural network-based combined object detection and tracking model, namely, Heat Map Network (HM-Net) HM-Net is significantly faster than state-of-the-art frame differencing and background subtraction-based methods. It outperforms state-of-the-art WAMI moving object detection and tracking methods on WPAFB dataset.
  arXiv  Detail & Related papers  (2021-10-19T11:56:30Z)
• Guiding Query Position and Performing Similar Attention for Transformer-Based Detection Heads [20.759022922347697]
  We propose the Guided Query Position (GQPos) method to embed the latest location information of object queries to query position iteratively. Besides the feature maps is fused, SiA also fuse the attention weights maps to accelerate the learning of high-resolution attention weight map. Our experiments show that the proposed GQPos improves the performance of a series of models, including DETR, SMCA, YoloS, and HoiTransformer.
  arXiv  Detail & Related papers  (2021-08-22T11:32:34Z)

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.