Saved in:
Bibliographic Details
Main Authors: Zeng, Yangchen, Yu, Zhenyu, Jiang, Dongming, Zhang, Wenbo, Hong, Yifan, Hu, Zhanhua, Luo, Jiao, Cui, Kangning
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.15065
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913038366408704
author Zeng, Yangchen
Yu, Zhenyu
Jiang, Dongming
Zhang, Wenbo
Hong, Yifan
Hu, Zhanhua
Luo, Jiao
Cui, Kangning
author_facet Zeng, Yangchen
Yu, Zhenyu
Jiang, Dongming
Zhang, Wenbo
Hong, Yifan
Hu, Zhanhua
Luo, Jiao
Cui, Kangning
contents Transformer-based detectors have advanced small-object detection, but they often remain inefficient and vulnerable to background-induced query noise, which motivates deep decoders to refine low-quality queries. We present HELP (Heatmap-guided Embedding Learning Paradigm), a noise-aware positional-semantic fusion framework that studies where to embed positional information by selectively preserving positional encodings in foreground-salient regions while suppressing background clutter. 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. HPE is integrated into both the encoder and decoder: it guides noise-suppressed feature encoding by injecting heatmap-aware positional encoding, and it enables high-quality query retrieval by filtering background-dominant embeddings via a gradient-based mask filter before decoding. To address feature sparsity in complex small targets, we integrate Linear-Snake Convolution to enrich retrieval-relevant representations. The gradient-based heatmap supervision is used during training only, incurring no additional gradient computation at inference. As a result, our design reduces decoder layers from eight to three and achieves a 59.4% parameter reduction (66.3M vs. 163M) while maintaining consistent accuracy gains under a reduced compute budget across benchmarks. Code Repository: https://github.com/yidimopozhibai/Noise-Suppressed-Query-Retrieval
format Preprint
id arxiv_https___arxiv_org_abs_2604_15065
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Learning Where to Embed: Noise-Aware Positional Embedding for Query Retrieval in Small-Object Detection
Zeng, Yangchen
Yu, Zhenyu
Jiang, Dongming
Zhang, Wenbo
Hong, Yifan
Hu, Zhanhua
Luo, Jiao
Cui, Kangning
Computer Vision and Pattern Recognition
Transformer-based detectors have advanced small-object detection, but they often remain inefficient and vulnerable to background-induced query noise, which motivates deep decoders to refine low-quality queries. We present HELP (Heatmap-guided Embedding Learning Paradigm), a noise-aware positional-semantic fusion framework that studies where to embed positional information by selectively preserving positional encodings in foreground-salient regions while suppressing background clutter. 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. HPE is integrated into both the encoder and decoder: it guides noise-suppressed feature encoding by injecting heatmap-aware positional encoding, and it enables high-quality query retrieval by filtering background-dominant embeddings via a gradient-based mask filter before decoding. To address feature sparsity in complex small targets, we integrate Linear-Snake Convolution to enrich retrieval-relevant representations. The gradient-based heatmap supervision is used during training only, incurring no additional gradient computation at inference. As a result, our design reduces decoder layers from eight to three and achieves a 59.4% parameter reduction (66.3M vs. 163M) while maintaining consistent accuracy gains under a reduced compute budget across benchmarks. Code Repository: https://github.com/yidimopozhibai/Noise-Suppressed-Query-Retrieval
title Learning Where to Embed: Noise-Aware Positional Embedding for Query Retrieval in Small-Object Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.15065