Low-Power Multi-Camera Object Re-Identification using Hierarchical
Neural Networks
- URL: http://arxiv.org/abs/2106.10588v1
- Date: Sat, 19 Jun 2021 23:59:26 GMT
- Title: Low-Power Multi-Camera Object Re-Identification using Hierarchical
Neural Networks
- Authors: Abhinav Goel, Caleb Tung, Xiao Hu, Haobo Wang, James C. Davis, George
K. Thiruvathukal, Yung-Hsiang Lu
- Abstract summary: State-of-the-art techniques rely on large, computationally-intensive Deep Neural Networks (DNNs)
We propose a novel hierarchical DNN architecture that uses attribute labels in the training dataset to perform efficient object reID.
With a 4% loss in accuracy, our approach realizes significant resource savings: 74% less memory, 72% fewer operations, and 67% lower query latency, yielding 65% less energy consumption.
- Score: 9.884285377021044
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Low-power computer vision on embedded devices has many applications. This
paper describes a low-power technique for the object re-identification (reID)
problem: matching a query image against a gallery of previously seen images.
State-of-the-art techniques rely on large, computationally-intensive Deep
Neural Networks (DNNs). We propose a novel hierarchical DNN architecture that
uses attribute labels in the training dataset to perform efficient object reID.
At each node in the hierarchy, a small DNN identifies a different attribute of
the query image. The small DNN at each leaf node is specialized to re-identify
a subset of the gallery: only the images with the attributes identified along
the path from the root to a leaf. Thus, a query image is re-identified
accurately after processing with a few small DNNs. We compare our method with
state-of-the-art object reID techniques. With a 4% loss in accuracy, our
approach realizes significant resource savings: 74% less memory, 72% fewer
operations, and 67% lower query latency, yielding 65% less energy consumption.
Related papers
- Learning cross space mapping via DNN using large scale click-through
logs [38.94796244812248]
The gap between low-level visual signals and high-level semantics has been progressively bridged by continuous development of deep neural network (DNN)
We propose a unified DNN model for image-query similarity calculation by simultaneously modeling image and query in one network.
Both the qualitative results and quantitative results on an image retrieval evaluation task with 1000 queries demonstrate the superiority of the proposed method.
arXiv Detail & Related papers (2023-02-26T09:00:35Z) - Learning Enriched Features for Fast Image Restoration and Enhancement [166.17296369600774]
This paper presents a holistic goal of maintaining spatially-precise high-resolution representations through the entire network.
We learn an enriched set of features that combines contextual information from multiple scales, while simultaneously preserving the high-resolution spatial details.
Our approach achieves state-of-the-art results for a variety of image processing tasks, including defocus deblurring, image denoising, super-resolution, and image enhancement.
arXiv Detail & Related papers (2022-04-19T17:59:45Z) - Deep Structured Instance Graph for Distilling Object Detectors [82.16270736573176]
We present a simple knowledge structure to exploit and encode information inside the detection system to facilitate detector knowledge distillation.
We achieve new state-of-the-art results on the challenging COCO object detection task with diverse student-teacher pairs on both one- and two-stage detectors.
arXiv Detail & Related papers (2021-09-27T08:26:00Z) - Efficient Classification of Very Large Images with Tiny Objects [15.822654320750054]
We present an end-to-end CNN model termed Zoom-In network for classification of large images with tiny objects.
We evaluate our method on two large-image datasets and one gigapixel dataset.
arXiv Detail & Related papers (2021-06-04T20:13:04Z) - Image Restoration by Deep Projected GSURE [115.57142046076164]
Ill-posed inverse problems appear in many image processing applications, such as deblurring and super-resolution.
We propose a new image restoration framework that is based on minimizing a loss function that includes a "projected-version" of the Generalized SteinUnbiased Risk Estimator (GSURE) and parameterization of the latent image by a CNN.
arXiv Detail & Related papers (2021-02-04T08:52:46Z) - Searching for Controllable Image Restoration Networks [57.23583915884236]
Existing methods require separate inference through the entire network per each output.
We propose a novel framework based on a neural architecture search technique that enables efficient generation of multiple imagery effects.
arXiv Detail & Related papers (2020-12-21T10:08:18Z) - Computational efficient deep neural network with difference attention
maps for facial action unit detection [3.73202122588308]
We propose a computational efficient end-to-end training deep neural network (CEDNN) model and spatial attention maps based on difference images.
A large number of experimental results show that the proposed CEDNN is obviously better than the traditional deep learning method on DISFA+ and CK+ datasets.
arXiv Detail & Related papers (2020-11-24T13:34:58Z) - Learning Deep Interleaved Networks with Asymmetric Co-Attention for
Image Restoration [65.11022516031463]
We present a deep interleaved network (DIN) that learns how information at different states should be combined for high-quality (HQ) images reconstruction.
In this paper, we propose asymmetric co-attention (AsyCA) which is attached at each interleaved node to model the feature dependencies.
Our presented DIN can be trained end-to-end and applied to various image restoration tasks.
arXiv Detail & Related papers (2020-10-29T15:32:00Z) - An Ultra Lightweight CNN for Low Resource Circuit Component Recognition [11.085448830542568]
We present an ultra lightweight system that can effectively recognize different circuit components in an image with very limited training data.
The accuracy of our system reaches 93.4%, outperforming the support vector machine (SVM) baseline (75.50%) and the existing state-of-the-art RetinaNet solutions (92.80%)
arXiv Detail & Related papers (2020-10-01T15:54:08Z) - Low-Power Object Counting with Hierarchical Neural Networks [1.203768341415124]
Object counting takes two inputs: an image and an object query and reports the number of occurrences of the queried object.
Deep Neural Networks (DNNs) can achieve state-of-the-art accuracy in many computer vision tasks, such as object counting.
DNNs require billions of operations, making them difficult to deploy on resource-constrained, low-power devices.
arXiv Detail & Related papers (2020-07-02T20:13:01Z) - Neural Sparse Representation for Image Restoration [116.72107034624344]
Inspired by the robustness and efficiency of sparse coding based image restoration models, we investigate the sparsity of neurons in deep networks.
Our method structurally enforces sparsity constraints upon hidden neurons.
Experiments show that sparse representation is crucial in deep neural networks for multiple image restoration tasks.
arXiv Detail & Related papers (2020-06-08T05:15:17Z)
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.