.png){kind=icon}
返回
Improving RGB-D Salient Object Detection via Modality-Aware Decoder
.png){kind=icon}
PRE
AI
DOI：10.1109/TIP.2022.3205747.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Most existing RGB-D salient object detection (SOD) methods are primarily focusing on cross-modal and cross-level saliency fusion, which has been proved to be efficient and effective. However, these methods still have a critical limitation, i.e., their fusion patterns - typically the combination of selective characteristics and its variations, are too highly dependent on the network's non-linear adaptability. In such methods, the balances between RGB and D (Depth) are formulated individually considering the intermediate feature slices, but the relation at the modality level may not be learned properly. The optimal RGB-D combinations differ depending on the RGB-D scenarios, and the exact complementary status is frequently determined by multiple modality-level factors, such as D quality, the complexity of the RGB scene, and degree of harmony between them. Therefore, given the existing approaches, it may be difficult for them to achieve further performance breakthroughs, as their methodologies belong to some methods that are somewhat less modality sensitive. To conquer this problem, this paper presents the Modality-aware Decoder (MaD). The critical technical innovations include a series of feature embedding, modality reasoning, and feature back-projecting and collecting strategies, all of which upgrade the widely-used multi-scale and multi-level decoding process to be modality-aware. Our MaD achieves competitive performance over other state-of-the-art (SOTA) models without using any fancy tricks in the decoder's design. Codes and results will be publicly available at https://github.com/MengkeSong/MaD.
Keyword:
Decoding
Object detection
Training
Task analysis
Saliency detection
Image segmentation
Feature extraction
RGB-D salient object detection
modality-aware fusion
deep learning
期刊
IF:
13.7
论文数:
1.0W
被引数:
8.4W
机构
引用论文
分享收藏Texting and Accessing the Web While Driving: Traffic Citations and Crashes Among Young Adult Drivers
PREAI
分享收藏Urban Green Space and the Pursuit of Health Equity in Parts of the United States美国部分地区的城市绿地与对健康公平的追求
OAAI
OAAI分享收藏Innovation, creativity and governance: Social dynamics of economic performance in city-regions.png)
Innovation
InnovationIF0
PREAI
分享收藏
查看更多内容