# Group Evidence Matters: Tiling-based Semantic Gating for Dense Object Detection

Source: [Group Evidence Matters: Tiling-based Semantic Gating for Dense Object Detection](<https://www.sota2.com/research/paper/68fa7ba71e209131cea89ac4>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:45:26.405Z

Authors: Yilun Xiao

Published: 2025-09-13T01:55:08.000Z

## Abstract

Dense small objects in UAV imagery are often missed due to long-range viewpoints, occlusion, and clutter\[cite: 5\]. This paper presents a detector-agnostic post-processing framework that converts overlap-induced redundancy into group evidence\[cite: 6\]. Overlapping tiling first recovers low-confidence candidates\[cite: 7\]. A Spatial Gate (DBSCAN on box centroids) and a Semantic Gate (DBSCAN on ResNet-18 embeddings) then validates group evidence\[cite: 7\]. Validated groups receive controlled confidence reweighting before class-aware NMS fusion\[cite: 8\]. Experiments on VisDrone show a recall increase from 0.685 to 0.778 (+0.093) and a precision adjustment from 0.801 to 0.595, yielding F1=0.669\[cite: 9\]. Post-processing latency averages 0.095 s per image\[cite: 10\]. These results indicate recall-first, precision-trade-off behavior that benefits recall-sensitive applications such as far-field counting and monitoring\[cite: 10\]. Ablation confirms that tiling exposes missed objects, spatial clustering stabilizes geometry, semantic clustering enforces appearance coherence, and reweighting provides calibrated integration with the baseline\[cite: 11\]. The framework requires no retraining and integrates with modern detectors\[cite: 12\]. Future work will reduce semantic gating cost and extend the approach with temporal cues\[cite: 13\].

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2509.10779>)

[PDF](<https://arxiv.org/pdf/2509.10779.pdf>)
