Improving the Deployment of Recycling Classification through Efficient Hyper-Parameter Analysis
This work addresses the need for efficient recycling classification on low-power devices, offering incremental improvements to an existing model.
The paper tackled the problem of deploying waste classification models on embedded devices by proposing a method to reduce model parameters without accuracy loss and accelerating inference, achieving 95.8% test accuracy and a 750% throughput increase to 24 inferences per second on an NVIDIA Jetson Nano.
The paradigm of automated waste classification has recently seen a shift in the domain of interest from conventional image processing techniques to powerful computer vision algorithms known as convolutional neural networks (CNN). Historically, CNNs have demonstrated a strong dependency on powerful hardware for real-time classification, yet the need for deployment on weaker embedded devices is greater than ever. The work in this paper proposes a methodology for reconstructing and tuning conventional image classification models, using EfficientNets, to decrease their parameterisation with no trade-off in model accuracy and develops a pipeline through TensorRT for accelerating such models to run at real-time on an NVIDIA Jetson Nano embedded device. The train-deployment discrepancy, relating how poor data augmentation leads to a discrepancy in model accuracy between training and deployment, is often neglected in many papers and thus the work is extended by analysing and evaluating the impact real world perturbations had on model accuracy once deployed. The scope of the work concerns developing a more efficient variant of WasteNet, a collaborative recycling classification model. The newly developed model scores a test-set accuracy of 95.8% with a real world accuracy of 95%, a 14% increase over the original. Our acceleration pipeline boosted model throughput by 750% to 24 inferences per second on the Jetson Nano and real-time latency of the system was verified through servomotor latency analysis.