D2Conv3D: Dynamic Dilated Convolutions for Object Segmentation in Videos
Despite receiving significant attention from the research community, the task of segmenting and tracking objects in monocular videos still has much room for improvement. Existing works have simultaneously justified the efficacy of dilated and deformable convolutions for various image-level segmentation tasks. This gives reason to believe that 3D extensions of such convolutions should also yield performance improvements for video-level segmentation tasks. However, this aspect has not yet been explored thoroughly in existing literature. In this paper, we propose Dynamic Dilated Convolutions (D2Conv3D): a novel type of convolution which draws inspiration from dilated and deformable convolutions and extends them to the 3D (spatio-temporal) domain. We experimentally show that D2Conv3D can be used to improve the performance of multiple 3D CNN architectures across multiple video segmentation related benchmarks by simply employing D2Conv3D as a drop-in replacement for standard convolutions. We further show that D2Conv3D out-performs trivial extensions of existing dilated and deformable convolutions to 3D. Lastly, we set a new state-of-the-art on the DAVIS 2016 Unsupervised Video Object Segmentation benchmark. Code is made publicly available at https://github.com/Schmiddo/d2conv3d.
Code (2)
Tasks
Multi-Object Tracking and SegmentationSegmentationSemantic SegmentationUnsupervised Video Object SegmentationVideo Instance SegmentationVideo Object SegmentationVideo SegmentationVideo Semantic SegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
D^2Conv3D: Dynamic Dilated Convolutions for Object Segmentation in Videos
Despite receiving significant attention from the research community, the task of segmenting and tracking objects in monocular videos still has much room for improvement. Existing works have simultaneously justified the e…
SegmentationSemantic SegmentationUnsupervised Video Object SegmentationVideo Object Segmentation+2Efficient Smoothing of Dilated Convolutions for Image Segmentation
Dilated Convolutions have been shown to be highly useful for the task of image segmentation. By introducing gaps into convolutional filters, they enable the use of larger receptive fields without increasing the original …
Image SegmentationSegmentationSemantic SegmentationDilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds
In this work, we propose Dilated Point Convolutions (DPC). In a thorough ablation study, we show that the receptive field size is directly related to the performance of 3D point cloud processing tasks, including semantic…
3D Semantic SegmentationSemantic SegmentationU-Net Using Stacked Dilated Convolutions for Medical Image Segmentation
This paper proposes a novel U-Net variant using stacked dilated convolutions for medical image segmentation (SDU-Net). SDU-Net adopts the architecture of vanilla U-Net with modifications in the encoder and decoder operat…
AllDecoderImage SegmentationMedical Image Segmentation+2CASSOD-Net: Cascaded and Separable Structures of Dilated Convolution for Embedded Vision Systems and Applications
The field of view (FOV) of convolutional neural networks is highly related to the accuracy of inference. Dilated convolutions are known as an effective solution to the problems which require large FOVs. However, for gene…
Face DetectionImage SegmentationSemantic Segmentation