Deep learning model inference on embedded devices is challenging due to the limited availability of computation resources. A popular alternative is to perform model inference on the cloud, which requires transmitting images from the embedded device to the cloud. Image compression techniques are commonly employed in such cloud-based architectures to reduce transmission latency over low bandwidth networks. This work proposes an end-to-end image compression framework that learns domain-specific features to achieve higher compression ratios than standard HEVC/JPEG compression techniques while maintaining accuracy on downstream tasks (e.g., recognition). Our framework does not require fine-tuning of the downstream task, which allows us to drop-in any off-the-shelf downstream task model without retraining. We choose faces as an application domain due to the ready availability of datasets and off-the-shelf recognition models as representative downstream tasks. We present a novel Identity Preserving Reconstruction (IPR) loss function which achieves Bits-Per-Pixel (BPP) values that are ~38% and ~42% of CRF-23 HEVC compression for LFW (low-resolution) and CelebA-HQ (high-resolution) datasets, respectively, while maintaining parity in recognition accuracy. The superior compression ratio is achieved as the model learns to retain the domain-specific features (e.g., facial features) while sacrificing details in the background. Furthermore, images reconstructed by our proposed compression model are robust to changes in downstream model architectures. We show at-par recognition performance on the LFW dataset with an unseen recognition model while retaining a lower BPP value of ~38% of CRF-23 HEVC compression.
翻译:嵌入装置的深学习模型推算因计算资源有限而具有挑战性。 一个流行的替代方案是在云层上进行模型推算, 需要将嵌入装置的图像传送到云层。 图像压缩技术通常在基于云的架构中使用, 以减少低带宽网络的传输延缓度。 这项工作提议了一个端到端图像压缩框架, 以学习特定域特性实现比特斯- Per- Pixel (BPP) 的标准压缩率更高, 并同时保持下游任务( 例如, 识别) 的准确性能。 我们的框架不需要对下游任务进行微调, 从而使我们能够在不再培训的情况下, 将任何现成的下游任务模型投放入任何超现的下游任务模型。 我们选择将图像压缩为应用程序域域域, 以现现成的识别模型和现成的下游图像模式。 我们的维护了比特斯- Per- Pixel (BPPP) (BPPP) 的减缩值, 值为~ 42% 用于下游任务, 为 LFW( 的 CREVC 缩压缩模型( 分辨率解) 的模型中, 和 Creal- recial recial recial recial recial recial recial) 的确认 的模型, 的确认 的模型的模型的精确度, 和C- recode reco reco reco recial deco recodeal deal 。