.png){kind=icon}
返回
Salient Object Detection via Dynamic Scale Routing
.png){kind=icon}
OA
AI
DOI：10.1109/TIP.2022.3214332.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Recent research advances in salient object detection (SOD) could largely be attributed to ever-stronger multi-scale feature representation empowered by the deep learning technologies. The existing SOD deep models extract multi-scale features via the off-the-shelf encoders and combine them smartly via various delicate decoders. However, the kernel sizes in this commonly-used thread are usually fixed. In our new experiments, we have observed that kernels of small size are preferable in scenarios containing tiny salient objects. In contrast, large kernel sizes could perform better for images with large salient objects. Inspired by this observation, we advocate the dynamic scale routing (as a brand-new idea) in this paper. It will result in a generic plug-in that could directly fit the existing feature backbone. This paper's key technical innovations are two-fold. First, instead of using the vanilla convolution with fixed kernel sizes for the encoder design, we propose the dynamic pyramid convolution (DPConv), which dynamically selects the best-suited kernel sizes w.r.t. the given input. Second, we provide a self-adaptive bidirectional decoder design to accommodate the DPConv-based encoder best. The most significant highlight is its capability of routing between feature scales and their dynamic collection, making the inference process scale-aware. As a result, this paper continues to enhance the current SOTA performance. Both the code and dataset are publicly available at https://github.com/wuzhenyubuaa/DPNet.
Keyword:
Kernel
Decoding
Feature extraction
Routing
Deep learning
Object detection
Technological innovation
Dynamic scale routing
scale-aware feature aggregation
salient object detection
期刊
IF:
13.7
论文数:
1.0W
被引数:
8.4W
机构
引用论文
LID, LEED, and Alternative Rating Systems—Integrating Low Impact Development Techniques with Green Building DesignLID，LEED和替代评级系统-将低影响开发技术与绿色建筑设计相结合
PREAI
分享收藏Recursive multi-model complementary deep fusion for robust salient object detection via parallel sub-networks.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏
查看更多内容