2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022
DOI: 10.1109/cvpr52688.2022.01222
|View full text |Cite
|
Sign up to set email alerts
|

TVConv: Efficient Translation Variant Convolution for Layout-aware Visual Processing

Abstract: As convolution has empowered many smart applications, dynamic convolution further equips it with the ability to adapt to diverse inputs. However, the static and dynamic convolutions are either layout-agnostic or computationheavy, making it inappropriate for layout-specific applications, e.g., face recognition and medical image segmentation. We observe that these applications naturally exhibit the characteristics of large intra-image (spatial) variance and small cross-image variance. This observation motivates … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
34
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
4
3
1

Relationship

0
8

Authors

Journals

citations
Cited by 70 publications
(74 citation statements)
references
References 43 publications
0
34
0
Order By: Relevance
“…Chen et al [26] proposed a dynamic region-aware convolution based on the characteristics of face recognition tasks. Furthermore, in reference [27], a more comprehensive pixel-level dynamic convolution is proposed.…”
Section: Deep Learning-based Metodsmentioning
confidence: 99%
“…Chen et al [26] proposed a dynamic region-aware convolution based on the characteristics of face recognition tasks. Furthermore, in reference [27], a more comprehensive pixel-level dynamic convolution is proposed.…”
Section: Deep Learning-based Metodsmentioning
confidence: 99%
“…These methods utilize depthwise convolution (DWConv) [26] and group convolution (GConv) [27] to extract spatial features. While this approach helps reduce the number of floating-point operations (FLOPs), it does not effectively address the issue of memory access reduction [28]. Previous works [28,29] have suggested minimizing redundancy in the feature maps.…”
Section: Rsconvmentioning
confidence: 99%
“…While this approach helps reduce the number of floating-point operations (FLOPs), it does not effectively address the issue of memory access reduction [28]. Previous works [28,29] have suggested minimizing redundancy in the feature maps. Inspired by this observation, we designed the segmentation-based RSConv method, illustrated in Figure 4.…”
Section: Rsconvmentioning
confidence: 99%
“…At the same time, we found that as the number of channels increased, as shown in Figure 5, feature maps have high similarity between different channels. Based on the idea of partial convolution proposed by Chen [49], we illustrate the design of partial convolution in Figure 6. Partial convolution exploits redundancy in the feature map and systematically applies regular convolution only on a subset of input channels without affecting the remaining channels.…”
Section: Imporoved Csp Structurementioning
confidence: 99%