DyCAF-Net: Dynamic Class-Aware Fusion Network
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908479429541888 |
|---|---|
| author | Jahin, Md Abrar Soudeep, Shahriar Mridha, M. F. Fahad, Nafiz Hossen, Md. Jakir |
| author_facet | Jahin, Md Abrar Soudeep, Shahriar Mridha, M. F. Fahad, Nafiz Hossen, Md. Jakir |
| contents | Recent advancements in object detection rely on modular architectures with multi-scale fusion and attention mechanisms. However, static fusion heuristics and class-agnostic attention limit performance in dynamic scenes with occlusions, clutter, and class imbalance. We introduce Dynamic Class-Aware Fusion Network (DyCAF-Net) that addresses these challenges through three innovations: (1) an input-conditioned equilibrium-based neck that iteratively refines multi-scale features via implicit fixed-point modeling, (2) a dual dynamic attention mechanism that adaptively recalibrates channel and spatial responses using input- and class-dependent cues, and (3) class-aware feature adaptation that modulates features to prioritize discriminative regions for rare classes. Through comprehensive ablation studies with YOLOv8 and related architectures, alongside benchmarking against nine state-of-the-art baselines, DyCAF-Net achieves significant improvements in precision, mAP@50, and mAP@50-95 across 13 diverse benchmarks, including occlusion-heavy and long-tailed datasets. The framework maintains computational efficiency ($\sim$11.1M parameters) and competitive inference speeds, while its adaptability to scale variance, semantic overlaps, and class imbalance positions it as a robust solution for real-world detection tasks in medical imaging, surveillance, and autonomous systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_03598 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DyCAF-Net: Dynamic Class-Aware Fusion Network Jahin, Md Abrar Soudeep, Shahriar Mridha, M. F. Fahad, Nafiz Hossen, Md. Jakir Computer Vision and Pattern Recognition Machine Learning Recent advancements in object detection rely on modular architectures with multi-scale fusion and attention mechanisms. However, static fusion heuristics and class-agnostic attention limit performance in dynamic scenes with occlusions, clutter, and class imbalance. We introduce Dynamic Class-Aware Fusion Network (DyCAF-Net) that addresses these challenges through three innovations: (1) an input-conditioned equilibrium-based neck that iteratively refines multi-scale features via implicit fixed-point modeling, (2) a dual dynamic attention mechanism that adaptively recalibrates channel and spatial responses using input- and class-dependent cues, and (3) class-aware feature adaptation that modulates features to prioritize discriminative regions for rare classes. Through comprehensive ablation studies with YOLOv8 and related architectures, alongside benchmarking against nine state-of-the-art baselines, DyCAF-Net achieves significant improvements in precision, mAP@50, and mAP@50-95 across 13 diverse benchmarks, including occlusion-heavy and long-tailed datasets. The framework maintains computational efficiency ($\sim$11.1M parameters) and competitive inference speeds, while its adaptability to scale variance, semantic overlaps, and class imbalance positions it as a robust solution for real-world detection tasks in medical imaging, surveillance, and autonomous systems. |
| title | DyCAF-Net: Dynamic Class-Aware Fusion Network |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2508.03598 |