GAF-Det: gated adaptive fusion detector for lightweight real-time object detection

Information-Preserving Lightweight Object Detection Network Utilizing Dynamic Gating and Multi-Scale Selection

Visual object detection is essential for environment perception in intelligent robots, automated assembly, unmanned inspection, and industrial detection systems. Although lightweight detectors reduce complexity through compact architectures, fixed convolutional units, and progressive downsampling, their limited scale r...

A lightweight transformer-based real-time object detection method for edge devices

Achieving high-accuracy, low-latency real-time object detection on resource-constrained edge devices is a core challenge in computer vision. Existing Transformer-based detectors are accurate, but their large parameter counts and computational cost hinder direct edge deployment. This paper proposes LT-Det, a lightweight...

Multimodal UAV Object Detection Using a YOLOv10-Transformer Hybrid Architecture for Balancing Precision and Speed

A global–local Transformer head, alternating depthwise convolutions with sparse self-attention, restores the small-target recall normally lost in attention-heavy designs, while CycleGAN-based cross-modal synthesis and an improved NMS-Free pipeline complete the training and inference path.

BMF-DETR: Pseudo-Depth-Guided Bidirectional Multi-Strategy Fusion for End-to-End Object Detection

Transformer-based detectors model long-range context effectively, yet their representations remain dominated by RGB appearance and can become unreliable in cluttered, occluded, or crowded scenes. We present BMF-DETR, a pseudo-depth-guided detector that introduces RGB-derived geometric structure without requiring a dept...

WD-DETR: a lightweight spatial–frequency Transformer for real-time UAV object detection

CIE-Det: a low-light object detector via cascaded illumination enhancement and dynamic semantic alignment

The proposed CIE-Det is an end-to-end lightweight object detection framework that jointly optimizes illumination enhancement and feature learning and achieves a favorable trade-off between detection accuracy and efficiency in low-light scenarios.