OD-DDA: Real-Time Object Detector with Dual Dynamic Adaptation in Variable Scenes

Object detection becomes challenging in variable scenarios, such as when object features change and cluttered backgrounds. We propose an object detector with dual dynamic adaptation (OD-DDA) to address these issues and enhance network performance in complex environments. First, we introduce a dynamic feature adaptation (DFA) module at each stage of the network, utilizing large kernel depthwise separable convolutions to capture multiscale contextual information, thereby enhancing the feature extraction capability of the model and effectively addressing object variations across different scenarios. Next, we design a dynamic fine-grained weight adaptation (DFGWA) module, which could selectively learn the fine-grained features of an image and calculate the corresponding weights before feature aggregation, thereby reducing interference among features and enhancing the model’s responsiveness to targets. Through the synergy of these modules, OD-DDA can flexibly handle the challenges faced during the detection of objects in complex scenarios and significantly improve the inference speed. We conduct rigorous experimental comparisons on five datasets, and the results show that OD-DDA exhibits excellent performance in different scenarios. Especially on the UAVDT dataset, $A{P}_{50}$ reaches 37.9% and FPS reaches 87.5, proving its ability to balance speed and accuracy.