Towards High-Resolution Salient Object Detection

Abstract

Deep neural network based methods have made a significant breakthrough in salient object detection. However, they are typically limited to input images with low resolutions ($400\times 400$ pixels or less). Little effort has been made to train deep neural networks to directly handle salient object detection in very high-resolution images. This paper pushes forward high-resolution saliency detection, and contributes a new dataset, named High-Resolution Salient Object Detection (HRSOD). To our best knowledge, HRSOD is the first high-resolution saliency detection dataset to date. As another contribution, we also propose a novel approach, which incorporates both global semantic information and local high-resolution details, to address this challenging task. More specifically, our approach consists of a Global Semantic Network (GSN), a Local Refinement Network (LRN) and a Global-Local Fusion Network (GLFN). GSN extracts the global semantic information based on down-sampled entire image. Guided by the results of GSN, LRN focuses on some local regions and progressively produces high-resolution predictions. GLFN is further proposed to enforce spatial consistency and boost performance. Experiments illustrate that our method outperforms existing state-of-the-art methods on high-resolution saliency datasets by a large margin, and achieves comparable or even better performance than them on widely-used saliency benchmarks. The HRSOD dataset is available at https://github.com/yi94code/HRSOD.

arXiv commentAccepted by ICCV2019. The HRSOD dataset is available at https://github.com/yi94code/HRSOD

References in corpus (5)

• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
• Salient Object Detection with Lossless Feature Reflection and Weighted Structural Loss
• Agile Amulet: Real-Time Salient Object Detection with Contextual Attention
• Non-rigid Object Tracking via Deep Multi-scale Spatial-temporal Discriminative Saliency Maps
• Auto-Retoucher(ART) - A framework for Background Replacement and Image Editing

Cited by in corpus (9)

• Suppress and Balance: A Simple Gated Network for Salient Object Detection
• A Single Stream Network for Robust and Real-time RGB-D Salient Object Detection
• Highly Efficient Salient Object Detection with 100K Parameters
• Progressively Guided Alternate Refinement Network for RGB-D Salient Object Detection
• Multi-scale Interactive Network for Salient Object Detection
• Local Context Attention for Salient Object Segmentation
• Attention-guided Image Compression by Deep Reconstruction of Compressive Sensed Saliency Skeleton
• Defocus Blur Detection via Salient Region Detection Prior
• Cascade Graph Neural Networks for RGB-D Salient Object Detection