Super-Efficient Super Resolution for Fast Adversarial Defense at the Edge

• URL: http://arxiv.org/abs/2112.14340v1
• Date: Wed, 29 Dec 2021 00:35:41 GMT
• Title: Super-Efficient Super Resolution for Fast Adversarial Defense at the Edge
• Authors: Kartikeya Bhardwaj, Dibakar Gope, James Ward, Paul Whatmough, Danny Loh
• Abstract summary: A new technique has emerged for mitigating attacks on image classification Deep Neural Networks (DNNs) Super resolution incurs a heavy computational cost. We show that Super-Efficient Super Resolution (SESR) achieves similar or better image quality than prior art while requiring 2x to 330x fewer Multiply-Accumulate (MAC) operations.
• Score: 4.2698418800007865
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Autonomous systems are highly vulnerable to a variety of adversarial attacks on Deep Neural Networks (DNNs). Training-free model-agnostic defenses have recently gained popularity due to their speed, ease of deployment, and ability to work across many DNNs. To this end, a new technique has emerged for mitigating attacks on image classification DNNs, namely, preprocessing adversarial images using super resolution -- upscaling low-quality inputs into high-resolution images. This defense requires running both image classifiers and super resolution models on constrained autonomous systems. However, super resolution incurs a heavy computational cost. Therefore, in this paper, we investigate the following question: Does the robustness of image classifiers suffer if we use tiny super resolution models? To answer this, we first review a recent work called Super-Efficient Super Resolution (SESR) that achieves similar or better image quality than prior art while requiring 2x to 330x fewer Multiply-Accumulate (MAC) operations. We demonstrate that despite being orders of magnitude smaller than existing models, SESR achieves the same level of robustness as significantly larger networks. Finally, we estimate end-to-end performance of super resolution-based defenses on a commercial Arm Ethos-U55 micro-NPU. Our findings show that SESR achieves nearly 3x higher FPS than a baseline while achieving similar robustness.

Related papers

• LSwinSR: UAV Imagery Super-Resolution based on Linear Swin Transformer [7.3817359680010615]
  Super-resolution technology is especially beneficial for Unmanned Aerial Vehicles (UAV) In this paper, for the super-resolution of UAV images, a novel network based on the state-of-the-art Swin Transformer is proposed with better efficiency and competitive accuracy.
  arXiv  Detail & Related papers  (2023-03-17T20:14:10Z)
• SDM: Spatial Diffusion Model for Large Hole Image Inpainting [106.90795513361498]
  We present a novel spatial diffusion model (SDM) that uses a few iterations to gradually deliver informative pixels to the entire image. Also, thanks to the proposed decoupled probabilistic modeling and spatial diffusion scheme, our method achieves high-quality large-hole completion.
  arXiv  Detail & Related papers  (2022-12-06T13:30:18Z)
• Efficient and Accurate Quantized Image Super-Resolution on Mobile NPUs, Mobile AI & AIM 2022 challenge: Report [144.41960648643564]
  In this paper, we propose the participants to design an efficient quantized image super-resolution solution. The solution can demonstrate a real-time performance on mobile NPUs. The runtime of all models was evaluated on the Synaptics VS680 Smart Home board with a dedicated edge NPU.
  arXiv  Detail & Related papers  (2022-11-07T22:27:58Z)
• Image Super-resolution with An Enhanced Group Convolutional Neural Network [102.2483249598621]
  CNNs with strong learning abilities are widely chosen to resolve super-resolution problem. We present an enhanced super-resolution group CNN (ESRGCNN) with a shallow architecture. Experiments report that our ESRGCNN surpasses the state-of-the-arts in terms of SISR performance, complexity, execution speed, image quality evaluation and visual effect in SISR.
  arXiv  Detail & Related papers  (2022-05-29T00:34:25Z)
• BSRA: Block-based Super Resolution Accelerator with Hardware Efficient Pixel Attention [0.10547353841674209]
  This paper proposes a super resolution hardware accelerator with hardware efficient pixel attention. The final implementation can support full HD image reconstruction at 30 frames per second with TSMC 40nm CMOS process.
  arXiv  Detail & Related papers  (2022-05-02T09:56:29Z)
• SwiftSRGAN -- Rethinking Super-Resolution for Efficient and Real-time Inference [0.0]
  We present an architecture that is faster and smaller in terms of its memory footprint. A real-time super-resolution enables streaming high resolution media content even under poor bandwidth conditions.
  arXiv  Detail & Related papers  (2021-11-29T04:20:15Z)
• Projected GANs Converge Faster [50.23237734403834]
  Generative Adversarial Networks (GANs) produce high-quality images but are challenging to train. We make significant headway on these issues by projecting generated and real samples into a fixed, pretrained feature space. Our Projected GAN improves image quality, sample efficiency, and convergence speed.
  arXiv  Detail & Related papers  (2021-11-01T15:11:01Z)
• Extremely Lightweight Quantization Robust Real-Time Single-Image Super Resolution for Mobile Devices [0.0]
  Single-Image Super Resolution (SISR) is a classical computer vision problem and it has been studied for over decades. Recent work on SISR focuses solutions with deep learning methodologies and achieves state-of-the-art results. We propose a hardware (Synaptics Dolphin NPU) aware, extremely lightweight quantization robust real-time super resolution network (XLSR)
  arXiv  Detail & Related papers  (2021-05-21T11:29:48Z)
• Real-Time Quantized Image Super-Resolution on Mobile NPUs, Mobile AI 2021 Challenge: Report [67.86837649834636]
  We introduce the first Mobile AI challenge, where the target is to develop an end-to-end deep learning-based image super-resolution solution. The proposed solutions are fully compatible with all major mobile AI accelerators and are capable of reconstructing Full HD images under 40-60 ms.
  arXiv  Detail & Related papers  (2021-05-17T13:34:15Z)
• Collapsible Linear Blocks for Super-Efficient Super Resolution [3.5554418329811557]
  Single Image Super Resolution (SISR) has become an important computer vision problem. We propose SESR, a new class of Super-Efficient Super Resolution networks. Detailed experiments across six benchmark datasets demonstrate that SESR achieves similar or better image quality.
  arXiv  Detail & Related papers  (2021-03-17T02:16:31Z)
• AIM 2020 Challenge on Efficient Super-Resolution: Methods and Results [222.26973543552327]
  This paper reviews the AIM 2020 challenge on efficient single image super-resolution. The challenge task was to super-resolve an input image with a magnification factor x4. The goal is to devise a network that reduces one or several aspects such as runtime, parameter count, FLOPs, activations, and memory consumption.
  arXiv  Detail & Related papers  (2020-09-15T09:25:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.