Domain Specific Approximation for Object Detection
This work addresses speed bottlenecks in object detection for real-time applications like autonomous driving, but it is incremental as it builds on existing meta-architectures.
The paper tackles the need for faster object detection in systems like autonomous vehicles by exploring domain-specific approximations, such as category-aware image scaling, to balance speed and accuracy. It achieves up to 7.5x speedup without accuracy loss on the ImageNet VID dataset.
There is growing interest in object detection in advanced driver assistance systems and autonomous robots and vehicles. To enable such innovative systems, we need faster object detection. In this work, we investigate the trade-off between accuracy and speed with domain-specific approximations, i.e. category-aware image size scaling and proposals scaling, for two state-of-the-art deep learning-based object detection meta-architectures. We study the effectiveness of applying approximation both statically and dynamically to understand the potential and the applicability of them. By conducting experiments on the ImageNet VID dataset, we show that domain-specific approximation has great potential to improve the speed of the system without deteriorating the accuracy of object detectors, i.e. up to 7.5x speedup for dynamic domain-specific approximation. To this end, we present our insights toward harvesting domain-specific approximation as well as devise a proof-of-concept runtime, AutoFocus, that exploits dynamic domain-specific approximation.