• Corpus ID: 226307119

SVAM: Saliency-guided Visual Attention Modeling by Autonomous Underwater Robots

  title={SVAM: Saliency-guided Visual Attention Modeling by Autonomous Underwater Robots},
  author={Md. Jahidul Islam and Ruobing Wang and Karin de Langis and Junaed Sattar},
This paper presents a holistic approach to saliency-guided visual attention modeling (SVAM) for use by autonomous underwater robots. Our proposed model, named SVAM-Net, integrates deep visual features at various scales and semantics for effective salient object detection (SOD) in natural underwater images. The SVAM-Net architecture is configured in a unique way to jointly accommodate bottom-up and top-down learning within two separate branches of the network while sharing the same encoding… 
Salient Objects in Clutter
It is argued that improving the dataset can yield higher performance gains than focusing only on the decoder design, and several dataset-enhancement strategies are investigated, including label smoothing to implicitly emphasize salient boundaries, random image augmentation to adapt saliency models to various scenarios, and self-supervised learning as a regularization strategy to learn from small datasets.


Simultaneous Enhancement and Super-Resolution of Underwater Imagery for Improved Visual Perception
Deep SESR is presented, a residual-in-residual network-based generative model that can learn to restore perceptual image qualities at 2x, 3x, or 4x higher spatial resolution and formulating a multi-modal objective function that addresses the chrominance-specific underwater color degradation, lack of image sharpness, and loss in high-level feature representation.
Fast Underwater Image Enhancement for Improved Visual Perception
The proposed conditional generative adversarial network-based model is suitable for real-time preprocessing in the autonomy pipeline by visually-guided underwater robots and provides improved performances of standard models for underwater object detection, human pose estimation, and saliency prediction.
One-Shot Informed Robotic Visual Search in the Wild
A method that enables informed visual navigation via a learned visual similarity operator that guides the robot’s visual search towards parts of the scene that look like an exemplar image, which is given by the user as a high-level specification for data collection.
BASNet: Boundary-Aware Salient Object Detection
Experimental results on six public datasets show that the proposed predict-refine architecture, BASNet, outperforms the state-of-the-art methods both in terms of regional and boundary evaluation measures.
Real-Time Visual SLAM for Autonomous Underwater Hull Inspection Using Visual Saliency
A novel online bag-of-words measure for intra and interimage saliency are introduced and are shown to be useful for image key-frame selection, information-gain-based link hypothesis, and novelty detection.
Enhancing Underwater Imagery Using Generative Adversarial Networks
A method to improve the quality of visual underwater scenes using Generative Adversarial Networks (GANs), with the goal of improving input to vision-driven behaviors further down the autonomy pipeline is proposed.
Underwater Image Super-Resolution using Deep Residual Multipliers
A deep residual network-based generative model for single image super-resolution (SISR) of underwater imagery for use by autonomous underwater robots and an adversarial training pipeline for learning SISR from paired data is provided.
DHSNet: Deep Hierarchical Saliency Network for Salient Object Detection
  • Nian Liu, Junwei Han
  • Computer Science
    2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
Evaluations on four benchmark datasets and comparisons with other 11 state-of-the-art algorithms demonstrate that DHSNet not only shows its significant superiority in terms of performance, but also achieves a real-time speed of 23 FPS on modern GPUs.
Toward a Generic Diver-Following Algorithm: Balancing Robustness and Efficiency in Deep Visual Detection
This letter designs an architecturally simple convolutional neural network based diver detection model that is much faster than the state-of-the-art deep models yet provides comparable detection performances.
Cascaded Partial Decoder for Fast and Accurate Salient Object Detection
A novel Cascaded Partial Decoder (CPD) framework for fast and accurate salient object detection and applies the proposed framework to optimize existing multi-level feature aggregation models and significantly improve their efficiency and accuracy.