Dynamic Region-Aware Convolution

Chen, Jin; Wang, Xijun; Guo, Zichao; Zhang, Xiangyu; Sun, Jian

doi:10.48550/arxiv.2003.12243

Cited by 10 publications

(6 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most existing arts [141], [142], [143], [144] generate an H × W × k 2 kernel map to produce spatially dynamic weights (H, W are the spatial size of the output feature and k is the kernel size). Considering the pixels belonging to the same object may share identical weights, dynamic region-aware convolution (DRConv) [145] generates a segmentation mask for an input image, dividing it into m regions, for each of which a weight generation network is responsible for producing a data-dependant kernel.…”

Section: Pixel-wise Dynamic Parametersmentioning

confidence: 99%

Dynamic Neural Networks: A Survey

Han

Huang

Song

et al. 2021

Preprint

View full text Add to dashboard Cite

Dynamic neural network is an emerging research topic in deep learning. Compared to static models which have fixed computational graphs and parameters at the inference stage, dynamic networks can adapt their structures or parameters to different inputs, leading to notable advantages in terms of accuracy, computational efficiency, adaptiveness, etc. In this survey, we comprehensively review this rapidly developing area by dividing dynamic networks into three main categories: 1) instance-wise dynamic models that process each instance with data-dependent architectures or parameters; 2) spatial-wise dynamic networks that conduct adaptive computation with respect to different spatial locations of image data and 3) temporal-wise dynamic models that perform adaptive inference along the temporal dimension for sequential data such as videos and texts. The important research problems of dynamic networks, e.g., architecture design, decision making scheme, optimization technique and applications, are reviewed systematically. Finally, we discuss the open problems in this field together with interesting future research directions.

show abstract

Section: Pixel-wise Dynamic Parametersmentioning

confidence: 99%

Dynamic Neural Networks: A Survey

Han

Huang

Song

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…It generates dynamic weights conditioned on the input or input-related features for parameterizing some operators (mostly fully-connected layers or convolutions). This has been applied to many tasks [39,25,12,2,24,21,17].…”

Section: Dynamic Computationmentioning

confidence: 99%

Image Synthesis via Semantic Composition

Wang¹,

Qi²,

Chen³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

In this paper, we present a novel approach to synthesize realistic images based on their semantic layouts. It hypothesizes that for objects with similar appearance, they share similar representation. Our method establishes dependencies between regions according to their appearance correlation, yielding both spatially variant and associated representations. Conditioning on these features, we propose a dynamic weighted network constructed by spatially conditional computation (with both convolution and normalization). More than preserving semantic distinctions, the given dynamic network strengthens semantic relevance, benefiting global structure and detail synthesis. We demonstrate that our method gives the compelling generation performance qualitatively and quantitatively with extensive experiments on benchmarks 1 .

show abstract

“…Some methods use dynamic mechanism to adjust the network configurations. DRConv (Chen et al 2020a) assigned filters to learning appointed spatial areas that achieved better performance through obtaining rich and diverse spatial information. Other methods dynamically learn to set the hyperparameters.…”

Section: Related Workmentioning

confidence: 99%

DSIC: Dynamic Sample-Individualized Connector for Multi-Scale Object Detection

Li¹,

Liu²,

Li³

et al. 2020

Preprint

View full text Add to dashboard Cite

Although object detection has reached a milestone thanks to the great success of deep learning, the scale variation is still the key challenge. Integrating multi-level features is presented to alleviate the problems, like the classic Feature Pyramid Network (FPN) and its improvements. However, the specifically designed feature integration modules of these methods may not have the optimal architecture for feature fusion. Moreover, these models have fixed architectures and data flow paths, when fed with various samples. They cannot adjust and be compatible with each kind of data. To overcome the above limitations, we propose a Dynamic Sample-Individualized Connector (DSIC) for multi-scale object detection. It dynamically adjusts network connections to fit different samples. In particular, DSIC consists of two components: Intra-scale Selection Gate (ISG) and Cross-scale Selection Gate (CSG). ISG adaptively extracts multi-level features from backbone as the input of feature integration. CSG automatically activate informative data flow paths based on the multi-level features. Furthermore, these two components are both plug-and-play and can be embedded in any backbone. Experimental results demonstrate that the proposed method outperforms the state-of-the-arts.

show abstract

Dynamic Region-Aware Convolution

Cited by 10 publications

References 32 publications

Dynamic Neural Networks: A Survey

Dynamic Neural Networks: A Survey

Image Synthesis via Semantic Composition

DSIC: Dynamic Sample-Individualized Connector for Multi-Scale Object Detection

Contact Info

Product

Resources

About