AI RESEARCH
Learning Where to Embed: Noise-Aware Positional Embedding for Query Retrieval in Small-Object Detection
arXiv CS.CV
•
ArXi:2604.15065v1 Announce Type: new 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.