Sampling Strategies for Efficient Training of Deep Learning Object Detection Algorithms
This work addresses efficiency in training object detection algorithms, but it appears incremental as it builds on existing sampling methods under Lipschitz continuity assumptions.
The paper tackled the problem of inefficient training of deep learning object detection models by investigating two sampling strategies—uniform sampling and frame difference sampling—to reduce the need for manually labeled samples, resulting in good training performance with relatively few samples.
Two sampling strategies are investigated to enhance efficiency in training a deep learning object detection model. These sampling strategies are employed under the assumption of Lipschitz continuity of deep learning models. The first strategy is uniform sampling which seeks to obtain samples evenly yet randomly through the state space of the object dynamics. The second strategy of frame difference sampling is developed to explore the temporal redundancy among successive frames in a video. Experiment result indicates that these proposed sampling strategies provide a dataset that yields good training performance while requiring relatively few manually labelled samples.