{"ID":2886460,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.03598","arxiv_id":"2508.03598","title":"DyCAF-Net: Dynamic Class-Aware Fusion Network","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2508.03598","url_pdf":"https://arxiv.org/pdf/2508.03598v1","authors":"[\"Md Abrar Jahin\",\"Shahriar Soudeep\",\"M. F. Mridha\",\"Nafiz Fahad\",\"Md. Jakir Hossen\"]","published":"2025-08-05T16:06:26Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.LG\"]","methods":"[]","has_code":false}