Towards SSD accelerating for embedded environments: a compressive sensing based approach

Since the rise of convolutional neural networks (CNN), deep learning-based computer vision has been a dynamic field of research. Nevertheless, modern CNN architectures have not given sufficient consideration to real-time applications within limited computation settings and always compromise speed and accuracy. To this end, a novel approach to CNN design, based on the emerging technology of compressive sensing (CS), is proposed. For instance, CS networks function in a compression-reconstruction approach as an encoder-decoder neural network. This approach transforms the computer vision problem into a multioutput learning problem by incorporating the CS network into a recognition network for joint training. As to the deployment phase, images are obtained from a CS-acquisition device and fed directly, without reconstruction, to the new recognition network. Following such an approach considerably improves transmission bandwidth and reduces the computational burden. Furthermore, the redesigned CNN holds fewer parameters than its original counterpart, thus reducing model complexity. To validate our findings, object detection using the Single-Shot Detector (SSD) network was redesigned to operate in our CS-based ecosystem using different datasets. The results show that the lightweight CS network offers good performance at a faster running speed. For instance, the number of FLOPS was reduced by 57% compared to the SSD baseline. Furthermore, the proposed CS_SSD achieves a compelling accuracy while being 30% faster than its original counterpart on small GPUs. Code is available at: littps://github.com/Bouderbal-Imene/CS-SSD.