Characterizing and Taming Resolution in Convolutional Neural Networks
Image resolution has a significant effect on the accuracy and computational, storage, and bandwidth costs of computer vision model inference. These costs are exacerbated when scaling out models to large inference serving systems and make image resolution an attractive target for optimization. However, the choice of resolution inherently introduces additional tightly coupled choices, such as image crop size, image detail, and compute kernel implementation that impact computational, storage, and bandwidth costs. Further complicating this setting, the optimal choices from the perspective of these metrics are highly dependent on the dataset and problem scenario. We characterize this tradeoff space, quantitatively studying the accuracy and efficiency tradeoff via systematic and automated tuning of image resolution, image quality and convolutional neural network operators. With the insights from this study, we propose a dynamic resolution mechanism that removes the need to statically choose a resolution ahead of time.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Taming Transformers for High-Resolution Image Synthesis
Designed to learn long-range interactions on sequential data, transformers continue to show state-of-the-art results on a wide variety of tasks. In contrast to CNNs, they contain no inductive bias that prioritizes local …
DeepFake DetectionImage GenerationImage OutpaintingImage Reconstruction+4Towards understanding feedback from supermassive black holes using convolutional neural networks
Supermassive black holes at centers of clusters of galaxies strongly interact with their host environment via AGN feedback. Key tracers of such activity are X-ray cavities -- regions of lower X-ray brightness within the …
Efficient Convolutional Forward Model for Passive Acoustic Mapping and Temporal Monitoring
Passive acoustic mapping (PAM) is a key imaging technique for characterizing cavitation activity in therapeutic ultrasound applications. Recent model-based beamforming algorithms offer high reconstruction quality and str…
mdctGAN: Taming transformer-based GAN for speech super-resolution with Modified DCT spectra
Speech super-resolution (SSR) aims to recover a high resolution (HR) speech from its corresponding low resolution (LR) counterpart. Recent SSR methods focus more on the reconstruction of the magnitude spectrogram, ignori…
Super-ResolutionTaming Stable Diffusion for Computed Tomography Blind Super-Resolution
High-resolution computed tomography (CT) imaging is essential for medical diagnosis but requires increased radiation exposure, creating a critical trade-off between image quality and patient safety. While deep learning m…
Blind Super-ResolutionComputed Tomography (CT)Language ModelingLanguage Modelling+2