Sense, Predict, Adapt, Repeat: A Blueprint for Design of New Adaptive AI-Centric Sensing Systems
Not on the map. Why?
Abstract (arXiv)
As Moore's Law loses momentum, improving size, performance, and efficiency of processors has become increasingly challenging, ending the era of predictable improvements in hardware performance. Meanwhile, the widespread incorporation of high-definition sensors in consumer devices and autonomous technologies has fueled a significant upsurge in sensory data. Current global trends reveal that the volume of generated data already exceeds human consumption capacity, making AI algorithms the primary consumers of data worldwide. To address this, a novel approach to designing AI-centric sensing systems is needed that can bridge the gap between the increasing capabilities of high-definition sensors and the limitations of AI processors. This paper provides an overview of efficient sensing and perception methods in both AI and sensing domains, emphasizing the necessity of co-designing AI algorithms and sensing systems for dynamic perception. The proposed approach involves a framework for designing and analyzing dynamic AI-in-the-loop sensing systems, suggesting a fundamentally new method for designing adaptive sensing systems through inference-time AI-to-sensor feedback and end-to-end efficiency and performance optimization.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 26 of its 35 references that are in the map. First posted on arXiv 11 Dec 2023.
Builds on
26 of 35 references.
References · 26
- 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
- 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
- 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
- 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
- 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,200
- 2023ImageBind: One Embedding Space To Bind Them Allcited by 1,175
- 2016Temporal Segment Networks: Towards Good Practices for Deep Action Recognitioncited by 902
- 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 849
- 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 815
- 2018Path Aggregation Network for Instance Segmentationcited by 798
- 2016Adaptive Computation Time for Recurrent Neural Networkscited by 506
- 2017Efficient Processing of Deep Neural Networks: A Tutorial and Surveycited by 434
14 more
- 2021Dynamic Neural Networks: A Surveycited by 408
- 2022MultiMAE: Multi-modal Multi-task Masked Autoencoderscited by 291
- 2020Resolution Adaptive Networks for Efficient Inferencecited by 146
- 2023Neural Architecture Search: Insights from 1000 Paperscited by 139
- 2016Convolutional Neural Networks using Logarithmic Data Representationcited by 99
- 2020AR-Net: Adaptive Frame Resolution for Efficient Action Recognitioncited by 88
- 2021Adaptive Inference through Early-Exit Networks: Design, Challenges and Directionscited by 75
- 2021ACTION-Net: Multipath Excitation for Action Recognitioncited by 63
- 2021A Comprehensive Survey on Hardware-Aware Neural Architecture Searchcited by 61
- 2018Automatic Brain Tumor Segmentation using Convolutional Neural Networks with Test-Time Augmentationcited by 36
- 2022P2M: A Processing-in-Pixel-in-Memory Paradigm for Resource-Constrained TinyML Applicationscited by 16
- 2020Fully Embedding Fast Convolutional Networks on Pixel Processor Arrayscited by 13
- 2021On the Adversarial Robustness of Quantized Neural Networkscited by 11
- 2014Cognitive Internet of Things: A New Paradigm beyond Connectioncited by 5
Built on by
Citing papers per year: 2024: 1.
1 paper.
- 2024Recall: Empowering Multimodal Embedding for Edge Devicescited by 3
- 2024Recall: Empowering Multimodal Embedding for Edge Devices9 Sep 2024