提出可抑制背景噪声的定位嵌入方法，提升小目标检测查询质量
Learning Where to Embed: Noise-Aware Positional Embedding for Query Retrieval in Small-Object Detection
- 基于热图引导选择性保留前景位置编码，抑制背景干扰
- 减少解码层至3层，参数量降低59.4%（163M→66.3M）且精度不降
- 适合小目标密集场景，尤其对计算资源受限的应用友好
基于Transformer的检测器虽推动了小目标检测发展，但常因背景引发的查询噪声而效率低下。本文提出HELP（热图引导嵌入学习范式），一种面向噪声感知的位置-语义融合框架，通过有选择地保留前景显著区域的位置编码来决定嵌入位置，同时抑制背景杂波。核心机制HPE（热图引导位置嵌入）在编码器和解码器中均被集成：编码阶段注入热图感知的位置编码以实现抗噪特征编码；解码前使用基于梯度的掩码滤波器过滤主导背景的嵌入，提升查询质量。为应对复杂小目标的特征稀疏问题，引入Linear-Snake卷积增强检索相关表示。梯度引导的热图监督仅在训练时使用，推理无额外开销。实验表明，该设计将解码层数从8降至3，参数量减少59.4%（163M → 66.3M），在多个基准上保持一致精度提升，同时降低计算开销。代码已开源。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。