paper-with-me

Papers

SdcNet: A Computation-Efficient CNN for Object Recognition

2018-05-03 · Yunlong Ma, Chunyan Wang

Extracting features from a huge amount of data for object recognition is a challenging task. Convolution neural network can be used to meet the challenge, but it often requires a large number of computation resources. In this paper, a computation-efficient convolutional module, named SdcBlock, is proposed and based on it, the convolution network SdcNet is introduced for object recognition tasks. In the proposed module, optimized successive depthwise convolutions supported by appropriate data management is applied in order to generate vectors containing high density and more varieties of feature information. The hyperparameters can be easily adjusted to suit varieties of tasks under different computation restrictions without significantly jeopardizing the performance. The experiments have shown that SdcNet achieved an error rate of 5.60% in CIFAR-10 with only 55M Flops and also reduced further the error rate to 5.24% using a moderate volume of 103M Flops. The expected computation efficiency of the SdcNet has been confirmed.

📄 PDF Abstract BibTeX arXiv:1805.01317

Code (0)

등록된 구현이 없습니다.

Tasks

ManagementObjectObject Recognition

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

SDCNet: Smoothed Dense-Convolution Network for Restoring Low-Dose Cerebral CT Perfusion

2019-10-18 · Peng Liu, Ruogu Fang

With substantial public concerns on potential cancer risks and health hazards caused by the accumulated radiation exposure in medical imaging, reducing radiation dose in X-ray based medical imaging such as Computed Tomog…

Computational EfficiencyDenoisingImage Denoising

Spacecraft depth completion based on the gray image and the sparse depth map

2022-08-30 · Xiang Liu, Hongyuan Wang, Zhiqiang Yan, Yu Chen 외

Perceiving the three-dimensional (3D) structure of the spacecraft is a prerequisite for successfully executing many on-orbit space missions, and it can provide critical input for many downstream vision algorithms. In thi…

Depth CompletionForeground SegmentationPose EstimationSpacecraft Pose Estimation

Fast Neuromimetic Object Recognition using FPGA Outperforms GPU Implementations

2015-10-31 · Garrick Orchard, Jacob G. Martin, R. Jacob Vogelstein, Ralph Etienne-Cummings

Recognition of objects in still images has traditionally been regarded as a difficult computational problem. Although modern automated methods for visual object recognition have achieved steadily increasing recognition a…

GPUObjectObject Recognition

SDCNet: Video Prediction Using Spatially-Displaced Convolution

2018-11-02 · Fitsum A. Reda, Guilin Liu, Kevin J. Shih, Robert Kirby 외

We present an approach for high-resolution video frame prediction by conditioning on both past frames and past optical flows. Previous approaches rely on resampling past frames, guided by a learned future optical flow, o…

Optical Flow EstimationPredictionSSIMVideo Prediction

Performance Evaluation of Raster Based Shape Vectors in Object Recognition

2014-03-28 · Akbar Khan, Pratap Reddy L

Object recognition is still an impediment in the field of computer vision and multimedia retrieval.Defining an object model is a critical task. Shape information of an object play a critical role in the process of object…

ObjectObject RecognitionRetrieval