# SCAI: A Spectral data Classification framework with Adaptive Inference for the IoT platform

arXiv: https://arxiv.org/abs/2206.12420 · HTML: https://mlsanity.com/paper/2206.12420/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 48 references that are in the map.
- First posted on arXiv 24 Jun 2022.

## Builds on (most cited first, 30 of 30)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adaptive Computation Time for Recurrent Neural Networks](https://mlsanity.com/paper/1603.08983/) (2016)
- [PointRend: Image Segmentation as Rendering](https://mlsanity.com/paper/1912.08193/) (2019)
- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [SkipNet: Learning Dynamic Routing in Convolutional Networks](https://mlsanity.com/paper/1711.09485/) (2017)
- [DynaBERT: Dynamic BERT with Adaptive Width and Depth](https://mlsanity.com/paper/2004.04037/) (2020)
- [BlockDrop: Dynamic Inference Paths in Residual Networks](https://mlsanity.com/paper/1711.08393/) (2017)
- [Adaptive Neural Networks for Efficient Inference](https://mlsanity.com/paper/1702.07811/) (2017)
- [Resolution Adaptive Networks for Efficient Inference](https://mlsanity.com/paper/2003.07326/) (2020)
- [Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition](https://mlsanity.com/paper/2105.15075/) (2021)
- [Spatially Adaptive Computation Time for Residual Networks](https://mlsanity.com/paper/1612.02297/) (2016)
- [Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification](https://mlsanity.com/paper/2010.05300/) (2020)
- [Convolutional Networks with Dense Connectivity](https://mlsanity.com/paper/2001.02394/) (2020)
- [Dynamic Convolutions: Exploiting Spatial Sparsity for Faster Inference](https://mlsanity.com/paper/1912.03203/) (2019)
- [Adaptive Inference through Early-Exit Networks: Design, Challenges and Directions](https://mlsanity.com/paper/2106.05022/) (2021)
- [DL-Traff: Survey and Benchmark of Deep Learning Models for Urban Traffic Prediction](https://mlsanity.com/paper/2108.09091/) (2021)
- [Differentiable Patch Selection for Image Recognition](https://mlsanity.com/paper/2104.03059/) (2021)
- [Dynamic Deep Neural Networks: Optimizing Accuracy-Efficiency Trade-offs by Selective Execution](https://mlsanity.com/paper/1701.00299/) (2017)
- [Spatially Adaptive Inference with Stochastic Feature Sampling and Interpolation](https://mlsanity.com/paper/2003.08866/) (2020)
- [Dynamic Region-Aware Convolution](https://mlsanity.com/paper/2003.12243/) (2020)
- [Triple Wins: Boosting Accuracy, Robustness and Efficiency Together by Enabling Input-Adaptive Inference](https://mlsanity.com/paper/2002.10025/) (2020)
- [Batch-Shaping for Learning Conditional Channel Gated Networks](https://mlsanity.com/paper/1907.06627/) (2019)
- [Global-local Enhancement Network for NMFs-aware Sign Language Recognition](https://mlsanity.com/paper/2008.10428/) (2020)
- [Coarse-Fine Networks for Temporal Activity Detection in Videos](https://mlsanity.com/paper/2103.01302/) (2021)
- [Graph Neural Networks in IoT: A Survey](https://mlsanity.com/paper/2203.15935/) (2022)
- [Deep Convolutional Neural Networks for Raman Spectrum Recognition: A Unified Solution](https://mlsanity.com/paper/1708.09022/) (2017)
- [Fully Dynamic Inference with Deep Neural Networks](https://mlsanity.com/paper/2007.15151/) (2020)
- [A Probabilistic Hard Attention Model For Sequentially Observed Scenes](https://mlsanity.com/paper/2111.07534/) (2021)
- [LightIoT: Lightweight and Secure Communication for Energy-Efficient IoT in Health Informatics](https://mlsanity.com/paper/2104.14906/) (2021)

## Abstract (arXiv)

Currently, it is a hot research topic to realize accurate, efficient, and real-time identification of massive spectral data with the help of deep learning and IoT technology. Deep neural networks played a key role in spectral analysis. However, the inference of deeper models is performed in a static manner, and cannot be adjusted according to the device. Not all samples need to allocate all computation to reach confident prediction, which hinders maximizing the overall performance. To address the above issues, we propose a Spectral data Classification framework with Adaptive Inference. Specifically, to allocate different computations for different samples while better exploiting the collaboration among different devices, we leverage Early-exit architecture, place intermediate classifiers at different depths of the architecture, and the model outputs the results when the prediction confidence reaches a preset threshold. We propose a training paradigm of self-distillation learning, the deepest classifier performs soft supervision on the shallow ones to maximize their performance and training speed. At the same time, to mitigate the vulnerability of performance to the location and number settings of intermediate classifiers in the Early-exit paradigm, we propose a Position-Adaptive residual network. It can adjust the number of layers in each block at different curve positions, so it can focus on important positions of the curve (e.g.: Raman peak), and accurately allocate the appropriate computational budget based on task performance and computing resources. To the best of our knowledge, this paper is the first attempt to conduct optimization by adaptive inference for spectral detection under the IoT platform. We conducted many experiments, the experimental results show that our proposed method can achieve higher performance with less computational budget than existing methods.