More Like this

1. Adapting Convolutional Neural Networks for Indoor Localization with Smart Mobile Devices

   Mittal, A.; Tiku, S.; Pasricha, S. (January 2018, ACM Great Lakes Symposium on VLSI (GLSVLSI))

   Indoor localization is emerging as an important application domain for enhanced navigation (or tracking) of people and assets in indoor locales such as buildings, malls, and underground mines. Most indoor localization solutions proposed in prior work do not deliver good accuracy without expensive infrastructure (and even then, the results may lack consistency). Ambient wireless received signal strength indication (RSSI) based fingerprinting using smart mobile devices is a low-cost approach to the problem. However, creating an accurate ‘fingerprinting-only’ solution remains a challenge. This paper presents a novel approach to transform Wi-Fi signatures into images, to create a scalable fingerprinting framework based on Convolutional Neural Networks (CNNs). Our proposed CNN based indoor localization framework (CNN-LOC) is validated across several indoor environments and shows improvements over the best known prior works, with an average localization error of < 2 meters. 

   more » « less
2. An Abstraction-Refinement Approach to Verifying Convolutional Neural Networks

   https://doi.org/10.1007/978-3-031-19992-9_25  

   Ostrovsky, Matan; Barrett, Clark; Katz, Guy (October 2022, Proceedings of the 20th International Symposium on Automated Technology for Verification and Analysis (ATVA))

   Bouajjani, Ahmed; Holk, Lukas; Wu, Zhilin (Ed.)

   Convolutional neural networks (CNNs) have achieved immense popularity in areas like computer vision, image processing, speech proccessing, and many others. Unfortunately, despite their excellent performance, they are prone to producing erroneous results — for example, minor perturbations to their inputs can result in severe classification errors. In this paper, we present the CNN-ABS framework, which implements an abstraction-refinement based scheme for CNN verification. Specifically, CNN-ABS simplifies the verification problem through the removal of convolutional connections in a way that soundly creates an over-approximation of the original problem; it then iteratively restores these connections if the resulting problem becomes too abstract. CNN-ABS is designed to use existing verification engines as a backend, and our evaluation demonstrates that it can significantly boost the performance of a state-of-the-art DNN verification engine, reducing runtime by 15.7% on average. 

   more » « less
3. Adaptive Deep Learning for Soft Real-Time Image Classification

   https://doi.org/https://doi.org/10.3390/technologies9010020  

   Chai, F; Kang, K. D. (March 2021, Technologies)

   null (Ed.)

   CNNs (Convolutional Neural Networks) are becoming increasingly important for real-time applications, such as image classification in traffic control, visual surveillance, and smart manufacturing. It is challenging, however, to meet timing constraints of image processing tasks using CNNs due to their complexity. Performing dynamic trade-offs between the inference accuracy and time for image data analysis in CNNs is challenging too, since we observe that more complex CNNs that take longer to run even lead to lower accuracy in many cases by evaluating hundreds of CNN models in terms of time and accuracy using two popular data sets, MNIST and CIFAR-10. To address these challenges, we propose a new approach that (1) generates CNN models and analyzes their average inference time and accuracy for image classification, (2) stores a small subset of the CNNs with monotonic time and accuracy relationships offline, and (3) efficiently selects an effective CNN expected to support the highest possible accuracy among the stored CNNs subject to the remaining time to the deadline at run time. In our extensive evaluation, we verify that the CNNs derived by our approach are more flexible and cost-efficient than two baseline approaches. We verify that our approach can effectively build a compact set of CNNs and efficiently support systematic time vs. accuracy trade-offs, if necessary, to meet the user-specified timing and accuracy requirements. Moreover, the overhead of our approach is little/acceptable in terms of latency and memory consumption. 

   more » « less
4. ViP: Virtual Pooling for Accelerating CNN-based Image Classification and Object Detection

   https://doi.org/10.1109/WACV45572.2020.9093418  

   Chen, Zhuo; Zhang, Jiyuan; Ding, Ruizhou; Marculescu, Diana (March 2020, 2020 IEEE Winter Conference on Applications of Computer Vision (WACV))

   In recent years, Convolutional Neural Networks (CNNs) have shown superior capability in visual learning tasks. While accuracy-wise CNNs provide unprecedented performance, they are also known to be computationally intensive and energy demanding for modern computer systems. In this paper, we propose Virtual Pooling (ViP), a model-level approach to improve speed and energy consumption of CNN-based image classification and object detection tasks, with a provable error bound. We show the efficacy of ViP through experiments on four CNN models, three representative datasets, both desktop and mobile platforms, and two visual learning tasks, i.e., image classification and object detection. For example, ViP delivers 2.1x speedup with less than 1.5% accuracy degradation in ImageNet classification on VGG16, and 1.8x speedup with 0.025 mAP degradation in PASCAL VOC object detection with Faster-RCNN. ViP also reduces mobile GPU and CPU energy consumption by up to 55% and 70%, respectively. As a complementary method to existing acceleration approaches, ViP achieves 1.9x speedup on ThiNet leading to a combined speedup of 5.23x on VGG16. Furthermore, ViP provides a knob for machine learning practitioners to generate a set of CNN models with varying trade-offs between system speed/energy consumption and accuracy to better accommodate the requirements of their tasks. Code is available at https://github.com/cmu-enyac/VirtualPooling. 

   more » « less
5. Position-Aware Recalibration Module: Learning From Feature Semantics and Feature Position

   https://doi.org/10.24963/ijcai.2020/111  

   Ma, Xu; Fu, Song (July 2020, Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence)

   null (Ed.)

   We present a new method to improve the representational power of the features in Convolutional Neural Networks (CNNs). By studying traditional image processing methods and recent CNN architectures, we propose to use positional information in CNNs for effective exploration of feature dependencies. Rather than considering feature semantics alone, we incorporate spatial positions as an augmentation for feature semantics in our design. From this vantage, we present a Position-Aware Recalibration Module (PRM in short) which recalibrates features leveraging both feature semantics and position. Furthermore, inspired by multi-head attention, our module is capable of performing multiple recalibrations where results are concatenated as the output. As PRM is efficient and easy to implement, it can be seamlessly integrated into various base networks and applied to many position-aware visual tasks. Compared to original CNNs, our PRM introduces a negligible number of parameters and FLOPs, while yielding better performance. Experimental results on ImageNet and MS COCO benchmarks show that our approach surpasses related methods by a clear margin with less computational overhead. For example, we improve the ResNet50 by absolute 1.75% (77.65% vs. 75.90%) on ImageNet 2012 validation dataset, and 1.5%~1.9% mAP on MS COCO validation dataset with almost no computational overhead. Codes are made publicly available. 

   more » « less