Operators devoid of multiplication, such as Shift and Add, have gained prominence for their compatibility with hardware. However, neural networks (NNs) employing these operators typically exhibit lower accuracy compared to conventional NNs with identical structures. ShiftAddAug uses costly multiplication to augment efficient but less powerful multiplication-free operators, improving performance without any inference overhead. It puts a ShiftAdd tiny NN into a large multiplicative model and encourages it to be trained as a sub-model to obtain additional supervision. In order to solve the weight discrepancy problem between hybrid operators, a new weight sharing method is proposed. Additionally, a novel two stage neural architecture search is used to obtain better augmentation effects for smaller but stronger multiplication-free tiny neural networks. The superiority of ShiftAddAug is validated through experiments in image classification and semantic segmentation, consistently delivering noteworthy enhancements. Remarkably, it secures up to a 4.95% increase in accuracy on the CIFAR100 compared to its directly trained counterparts, even surpassing the performance of multiplicative NNs.

As particle accelerators increase their collision rates, and deep learning solutions prove their viability, there is a growing need for lightweight and fast neural network architectures for low-latency tasks such as triggering. We examine the potential of one recent Lorentz- and permutation-symmetric architecture, PELICAN, and present its instances with as few as 19 trainable parameters that outperform generic architectures with tens of thousands of parameters when compared on the binary classification task of top quark jet tagging.

We present a systematic study of domain generalization (DG) for tiny neural networks. This problem is critical to on-device machine learning applications but has been overlooked in the literature where research has been merely focused on large models. Tiny neural networks have much fewer parameters and lower complexity and therefore should not be trained the same way as their large counterparts for DG applications. By conducting extensive experiments, we find that knowledge distillation (KD), a well-known technique for model compression, is much better for tackling the on-device DG problem than conventional DG methods. Another interesting observation is that the teacher-student gap on out-of-distribution data is bigger than that on in-distribution data, which highlights the capacity mismatch issue as well as the shortcoming of KD. We further propose a method called out-of-distribution knowledge distillation (OKD) where the idea is to teach the student how the teacher handles out-of-distribution data synthesized via disruptive data augmentation. Without adding any extra parameter to the model -- hence keeping the deployment cost unchanged -- OKD significantly improves DG performance for tiny neural networks in a variety of on-device DG scenarios for image and speech applications. We also contribute a scalable approach for synthesizing visual domain shifts, along with a new suite of DG datasets to complement existing testbeds.

We present a systematic study of domain generalization (DG) for tiny neural networks, a problem that is critical to on-device machine learning applications but has been overlooked in the literature where research has been focused on large models only. Tiny neural networks have much fewer parameters and lower complexity, and thus should not be trained the same way as their large counterparts for DG applications. We find that knowledge distillation is a strong candidate for solving the problem: it outperforms state-of-the-art DG methods that were developed using large models with a large margin. Moreover, we observe that the teacher-student performance gap on test data with domain shift is bigger than that on in-distribution data. To improve DG for tiny neural networks without increasing the deployment cost, we propose a simple idea called out-of-distribution knowledge distillation (OKD), which aims to teach the student how the teacher handles (synthetic) out-of-distribution data and is proved to be a promising framework for solving the problem.

We introduce Network Augmentation (NetAug), a new training method for improving the performance of tiny neural networks. Existing regularization techniques (e.g., data augmentation, dropout) have shown much success on large neural networks (e.g., ResNet50) by adding noise to overcome over-fitting. However, we found these techniques hurt the performance of tiny neural networks. We argue that training tiny models are different from large models: rather than augmenting the data, we should augment the model, since tiny models tend to suffer from under-fitting rather than over-fitting due to limited capacity. To alleviate this issue, NetAug augments the network (reverse dropout) instead of inserting noise into the dataset or the network. It puts the tiny model into larger models and encourages it to work as a sub-model of larger models to get extra supervision, in addition to functioning as an independent model. At test time, only the tiny model is used for inference, incurring zero inference overhead. We demonstrate the effectiveness of NetAug on image classification and object detection. NetAug consistently improves the performance of tiny models, achieving up to 2.1% accuracy improvement on ImageNet, and 4.3% on Cars. On Pascal VOC, NetAug provides 2.96% mAP improvement with the same computational cost. Tiny IoT devices are witnessing rapid growth, reaching 75.44 billion by 2025 (iot).