RefineDetLite: A Lightweight One-stage Object Detection Framework for CPU-only Devices

Chen, Chen; Liu, Mengyuan; Meng, Xiandong; Xiao, Wanpeng; Ju, Qi

doi:10.1109/cvprw50498.2020.00358

Cited by 17 publications

(14 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Maintaining the same level of abstraction, but extending the analysis on Table 1 to the columns that contribute with specific data regarding each of the components that comprise the architecture of the different detection systems considered, we see that there is a marginal number of papers, namely MAOD [92], CornerNet-Squeeze [93], and LightDet [94], that explore the joint application of adjustments on backbone, neck, and head. The remaining majority is evenly split between work that explores enhancements on two of the elements that form the detection system in its different permutations [91,[95][96][97][98][99][100][101][102][103][104][105][106], and approaches that choose to focus on just one component [48,[107][108][109][110][111][112][113][114][115][116][117]. The main object of interest in the latter case is the neck, and, to a lesser extent, the backbone.…”

Section: Lightweight Object Detection Frameworkmentioning

confidence: 99%

“…That divergence becomes even more pronounced if we take into account the size of those spaces: quite even for the two groups when it comes to the neck while significantly uneven when talking about the head. Furthermore, regarding the latter, the subgroup of methods that seek to lower computational and memory cost have an evident prominence (approach embodied by five publications [48,91,93,98,118] referenced in Table 1) compared to the method that encompasses accuracy-centric modifications (with only two representative works [97,101] in the table ).…”

Section: Detection Head Architectural Principlesmentioning

confidence: 99%

“…The second head-specific-category or group (ii) is monopolized by the exploitation of residual blocks as a constituent part of the head's structure [92,94,97,101]. Such an approach is able to both increase the detection accuracy and contribute to reducing the resulting network's memory requirements.…”

Section: Detection Head Architectural Principlesmentioning

confidence: 99%

“…3.1.1, this type of block integrates the so-called shortcut connections to allow the flow of information between shallow and late-stage layers and thus keeps the semantic richness of features [97]. The value of residual connection goes beyond its accuracy-enhancement ability; it has also been adopted as the base structure for conceiving architectural alternatives equally advantageous in terms of detection accuracy, such as the bottleneck residual block [101], capable of fusing high-level multi-scale features, the inverted residuals and linear bottlenecks [92] that enable increasing the representational power of channel-wise nonlinear transformations, and a lighter version [94] that, inspired by group convolutions and comprised of two different branches, leverages channel shuffle to allow information exchange between branches.…”

Section: Detection Head Architectural Principlesmentioning

confidence: 99%

See 3 more Smart Citations

Optimized convolutional neural network architectures for efficient on-device vision-based object detection

Rodriguez-Conde

Campos

Fdez-Riverola

2021

Neural Comput & Applic

View full text Add to dashboard Cite

Convolutional neural networks have pushed forward image analysis research and computer vision over the last decade, constituting a state-of-the-art approach in object detection today. The design of increasingly deeper and wider architectures has made it possible to achieve unprecedented levels of detection accuracy, albeit at the cost of both a dramatic computational burden and a large memory footprint. In such a context, cloud systems have become a mainstream technological solution due to their tremendous scalability, providing researchers and practitioners with virtually unlimited resources. However, these resources are typically made available as remote services, requiring communication over the network to be accessed, thus compromising the speed of response, availability, and security of the implemented solution. In view of these limitations, the on-device paradigm has emerged as a recent yet widely explored alternative, pursuing more compact and efficient networks to ultimately enable the execution of the derived models directly on resource-constrained client devices. This study provides an up-to-date review of the more relevant scientific research carried out in this vein, circumscribed to the object detection problem. In particular, the paper contributes to the field with a comprehensive architectural overview of both the existing lightweight object detection frameworks targeted to mobile and embedded devices, and the underlying convolutional neural networks that make up their internal structure. More specifically, it addresses the main structural-level strategies used for conceiving the various components of a detection pipeline (i.e., backbone, neck, and head), as well as the most salient techniques proposed for adapting such structures and the resulting architectures to more austere deployment environments. Finally, the study concludes with a discussion of the specific challenges and next steps to be taken to move toward a more convenient accuracy–speed trade-off.

show abstract

Section: Lightweight Object Detection Frameworkmentioning

confidence: 99%

Section: Detection Head Architectural Principlesmentioning

confidence: 99%

Section: Detection Head Architectural Principlesmentioning

confidence: 99%

Section: Detection Head Architectural Principlesmentioning

confidence: 99%

See 2 more Smart Citations

Optimized convolutional neural network architectures for efficient on-device vision-based object detection

Rodriguez-Conde

Campos

Fdez-Riverola

2021

Neural Comput & Applic

View full text Add to dashboard Cite

show abstract

“…Considering the fact that low-level features are scarcely associated with high-level semantics, we aim to learn domain-invariant features with shared parameters. Furthermore, with the high resolution, low-level features benefit to improve the localization ability [30,5]. Therefore, we strongly conduct align local features in lower layers using a least-squares loss inspired by [37,55] to train the domain discriminator D l , consisting of 1×1 convolutional layers.…”

Section: Hierarchical Feature Alignmentmentioning

confidence: 99%

Multi-Source Domain Adaptation for Object Detection

Yao

Zhao

et al. 2021

Preprint

View full text Add to dashboard Cite

To reduce annotation labor associated with object detection, an increasing number of studies focus on transferring the learned knowledge from a labeled source domain to another unlabeled target domain. However, existing methods assume that the labeled data are sampled from a single source domain, which ignores a more generalized scenario, where labeled data are from multiple source domains. For the more challenging task, we propose a unified Faster R-CNN based framework, termed Divide-and-Merge Spindle Network (DMSN), which can simultaneously enhance domain invariance and preserve discriminative power. Specifically, the framework contains multiple source subnets and a pseudo target subnet. First, we propose a hierarchical feature alignment strategy to conduct strong and weak alignments for low-and high-level features, respectively, considering their different effects for object detection. Second, we develop a novel pseudo subnet learning algorithm to approximate optimal parameters of pseudo target subset by weighted combination of parameters in different source subnets. Finally, a consistency regularization for region proposal network is proposed to facilitate each subnet to learn more abstract invariances. Extensive experiments on different adaptation scenarios demonstrate the effectiveness of the proposed model.

show abstract