Dynamic Tiling: A Model-Agnostic, Adaptive, Scalable, and Inference-Data-Centric Approach for Efficient and Accurate Small Object Detection
This work addresses small object detection for computer vision applications, presenting an incremental improvement over model-agnostic uniform cropping methods.
The paper tackles the problem of small object detection by introducing Dynamic Tiling, a model-agnostic and adaptive approach that uses non-overlapping tiles with dynamic overlapping rates and a tile minimizer to resolve fragmented objects and reduce computational overhead, resulting in improved accuracy and efficiency over existing methods.
We introduce Dynamic Tiling, a model-agnostic, adaptive, and scalable approach for small object detection, anchored in our inference-data-centric philosophy. Dynamic Tiling starts with non-overlapping tiles for initial detections and utilizes dynamic overlapping rates along with a tile minimizer. This dual approach effectively resolves fragmented objects, improves detection accuracy, and minimizes computational overhead by reducing the number of forward passes through the object detection model. Adaptable to a variety of operational environments, our method negates the need for laborious recalibration. Additionally, our large-small filtering mechanism boosts the detection quality across a range of object sizes. Overall, Dynamic Tiling outperforms existing model-agnostic uniform cropping methods, setting new benchmarks for efficiency and accuracy.