Deeply supervised salient object detection with short connections

Abstract

Recent progress on saliency detection is substantial, benefiting mostly from the explosive development of Convolutional Neural Networks (CNNs). Semantic segmentation and saliency detection algorithms developed lately have been mostly based on Fully Convolutional Neural Networks (FCNs). There is still a large room for improvement over the generic FCN models that do not explicitly deal with the scale-space problem. Holistically-Nested Edge Detector (HED) provides a skip-layer structure with deep supervision for edge and boundary detection, but the performance gain of HED on salience detection is not obvious. In this paper, we propose a new method for saliency detection by introducing short connections to the skip-layer structures within the HED architecture. Our framework provides rich multi-scale feature maps at each layer, a property that is critically needed to perform segment detection. Our method produces state-of-the-art results on 5 widely tested salient object detection benchmarks, with advantages in terms of efficiency (0.15 seconds per image), effectiveness, and simplicity over the existing algorithms.

IEEE TPAMI 2018 (IEEE CVPR 2017)

References in corpus (5)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
• Fully Convolutional Networks for Semantic Segmentation
• Richer Convolutional Features for Edge Detection

Cited by in corpus (90)

• Res2Net: A New Multi-scale Backbone Architecture
• Concealed Object Detection
• Artificial Intelligence in the Creative Industries: A Review
• Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks
• JCS: An Explainable COVID-19 Diagnosis System by Joint Classification and Segmentation
• Dense Attention Fluid Network for Salient Object Detection in Optical Remote Sensing Images
• EDN: Salient Object Detection via Extremely-Downsampled Network
• DPANet: Depth Potentiality-Aware Gated Attention Network for RGB-D Salient Object Detection
• CIR-Net: Cross-modality Interaction and Refinement for RGB-D Salient Object Detection
• Deep Hough Transform for Semantic Line Detection
• Bilateral Attention Network for RGB-D Salient Object Detection
• MobileSal: Extremely Efficient RGB-D Salient Object Detection
• Dynamic Feature Integration for Simultaneous Detection of Salient Object, Edge and Skeleton
• Advances in Deep Concealed Scene Understanding
• Enhanced-alignment Measure for Binary Foreground Map Evaluation
• F3Net: Fusion, Feedback and Focus for Salient Object Detection
• Depth Quality Aware Salient Object Detection
• Cascaded Partial Decoder for Fast and Accurate Salient Object Detection
• RobustTAD: Robust Time Series Anomaly Detection via Decomposition and Convolutional Neural Networks
• Object Detection with Deep Learning: A Review
• SAC-Net: Spatial Attenuation Context for Salient Object Detection
• SCGAN: Saliency Map-guided Colorization with Generative Adversarial Network
• Controlling generative models with continuous factors of variations
• ConnNet: A Long-Range Relation-Aware Pixel-Connectivity Network for Salient Segmentation
• EGNet:Edge Guidance Network for Salient Object Detection
• PU-Net: Point Cloud Upsampling Network
• Middle-level Fusion for Lightweight RGB-D Salient Object Detection
• VST++: Efficient and Stronger Visual Saliency Transformer
• Salient Objects in Clutter
• Progressive Glass Segmentation
• Hierarchical Convolutional Neural Network with Feature Preservation and Autotuned Thresholding for Crack Detection
• Salient Object Detection via Dynamic Scale Routing
• Salient Objects in Clutter: Bringing Salient Object Detection to the Foreground
• Efficiently utilizing complex-valued PolSAR image data via a multi-task deep learning framework
• Regularized Densely-connected Pyramid Network for Salient Instance Segmentation
• Semantic Edge Detection with Diverse Deep Supervision
• Salient Object Detection in Video using Deep Non-Local Neural Networks
• Camouflaged Object Segmentation with Distraction Mining
• Bio-Inspired Representation Learning for Visual Attention Prediction
• JL-DCF: Joint Learning and Densely-Cooperative Fusion Framework for RGB-D Salient Object Detection
• Siamese Network for RGB-D Salient Object Detection and Beyond
• Large-Field Contextual Feature Learning for Glass Detection
• Towards Stable Co-saliency Detection and Object Co-segmentation
• Anchor Diffusion for Unsupervised Video Object Segmentation
• Selectivity or Invariance: Boundary-aware Salient Object Detection
• Finding an Unsupervised Image Segmenter in Each of Your Deep Generative Models
• DNA: Deeply-supervised Nonlinear Aggregation for Salient Object Detection
• Deep Floor Plan Recognition Using a Multi-Task Network with Room-Boundary-Guided Attention
• Disentangled High Quality Salient Object Detection
• Richer and Deeper Supervision Network for Salient Object Detection
• Saliency Integration: An Arbitrator Model
• Self-Erasing Network for Integral Object Attention
• Implicit Motion-Compensated Network for Unsupervised Video Object Segmentation
• Highly Efficient Salient Object Detection with 100K Parameters
• Optimizing the F-measure for Threshold-free Salient Object Detection
• RGB-D Salient Object Detection with Cross-Modality Modulation and Selection
• Exploring Image Enhancement for Salient Object Detection in Low Light Images
• Structured Modeling of Joint Deep Feature and Prediction Refinement for Salient Object Detection
• Progressively Guided Alternate Refinement Network for RGB-D Salient Object Detection
• Centralized Information Interaction for Salient Object Detection
• Instance-Level Relative Saliency Ranking with Graph Reasoning
• A Simple Pooling-Based Design for Real-Time Salient Object Detection
• Boosting Salient Object Detection with Transformer-based Asymmetric Bilateral U-Net
• Deep Green Function Convolution for Improving Saliency in Convolutional Neural Networks
• BiconNet: An Edge-preserved Connectivity-based Approach for Salient Object Detection
• An Integrated Image Filter for Enhancing Change Detection Results
• Learning Discriminative Feature with CRF for Unsupervised Video Object Segmentation
• Data Priming Network for Automatic Check-Out
• A Unified Framework for Shot Type Classification Based on Subject Centric Lens
• CLASS: Cross-Level Attention and Supervision for Salient Objects Detection
• Triple-cooperative Video Shadow Detection
• A Plug-and-play Scheme to Adapt Image Saliency Deep Model for Video Data
• A Novel Video Salient Object Detection Method via Semi-supervised Motion Quality Perception
• Boosting Object Recognition in Point Clouds by Saliency Detection
• Boundary-Aware Salient Object Detection via Recurrent Two-Stream Guided Refinement Network
• Improving Convolutional Neural Networks Via Conservative Field Regularisation and Integration
• Exploring Driving-aware Salient Object Detection via Knowledge Transfer
• Saliency Detection With Fully Convolutional Neural Network
• Saliency Enhancement using Gradient Domain Edges Merging
• Perception-and-Regulation Network for Salient Object Detection
• Label Decoupling Framework for Salient Object Detection
• ROSA: Robust Salient Object Detection against Adversarial Attacks
• Region Refinement Network for Salient Object Detection
• Rethinking of the Image Salient Object Detection: Object-level Semantic Saliency Re-ranking First, Pixel-wise Saliency Refinement Latter
• Deep Image Compositing
• Weakly-Supervised Saliency Detection via Salient Object Subitizing
• Detecting and Segmenting Adversarial Graphics Patterns from Images
• Depthwise Non-local Module for Fast Salient Object Detection Using a Single Thread
• Salient Object Detection with Purificatory Mechanism and Structural Similarity Loss
• Distortion-adaptive Salient Object Detection in 360${}^{\circ }$ Omnidirectional Images