Deep Contrast Learning for Salient Object Detection

Abstract

Salient object detection has recently witnessed substantial progress due to powerful features extracted using deep convolutional neural networks (CNNs). However, existing CNN-based methods operate at the patch level instead of the pixel level. Resulting saliency maps are typically blurry, especially near the boundary of salient objects. Furthermore, image patches are treated as independent samples even when they are overlapping, giving rise to significant redundancy in computation and storage. In this CVPR 2016 paper, we propose an end-to-end deep contrast network to overcome the aforementioned limitations. Our deep network consists of two complementary components, a pixel-level fully convolutional stream and a segment-wise spatial pooling stream. The first stream directly produces a saliency map with pixel-level accuracy from an input image. The second stream extracts segment-wise features very efficiently, and better models saliency discontinuities along object boundaries. Finally, a fully connected CRF model can be optionally incorporated to improve spatial coherence and contour localization in the fused result from these two streams. Experimental results demonstrate that our deep model significantly improves the state of the art.

To appear in CVPR 2016

References in corpus (12)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
• Fully Convolutional Networks for Semantic Segmentation
• Rich feature hierarchies for accurate object detection and semantic segmentation
• Convolutional Feature Masking for Joint Object and Stuff Segmentation
• Holistically-Nested Edge Detection
• Visual Saliency Based on Multiscale Deep Features
• PISA: Pixelwise Image Saliency by Aggregating Complementary Appearance Contrast Measures with Edge-Preserving Coherence
• Highly Efficient Forward and Backward Propagation of Convolutional Neural Networks for Pixelwise Classification
• HD-CNN: Hierarchical Deep Convolutional Neural Network for Large Scale Visual Recognition

Cited by in corpus (32)

• A Review on Deep Learning Techniques Applied to Semantic Segmentation
• Video Salient Object Detection via Fully Convolutional Networks
• Visual Saliency Detection Based on Multiscale Deep CNN Features
• Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection
• Structure-measure: A New Way to Evaluate Foreground Maps
• Deep Unsupervised Saliency Detection: A Multiple Noisy Labeling Perspective
• PiCANet: Learning Pixel-wise Contextual Attention for Saliency Detection
• Deep Spatial Feature Reconstruction for Partial Person Re-identification: Alignment-Free Approach
• Salient Objects in Clutter: Bringing Salient Object Detection to the Foreground
• Salient Object Detection in Video using Deep Non-Local Neural Networks
• Exploiting saliency for object segmentation from image level labels
• Learning Uncertain Convolutional Features for Accurate Saliency Detection
• Agile Amulet: Real-Time Salient Object Detection with Contextual Attention
• Learning RGB-D Salient Object Detection using background enclosure, depth contrast, and top-down features
• Context Proposals for Saliency Detection
• Semantics Meet Saliency: Exploring Domain Affinity and Models for Dual-Task Prediction
• Saccade Sequence Prediction: Beyond Static Saliency Maps
• A Segmentation-aware Deep Fusion Network for Compressed Sensing MRI
• Context-Aware Semantic Inpainting
• Learning Selective Mutual Attention and Contrast for RGB-D Saliency Detection
• HyperFusion-Net: Densely Reflective Fusion for Salient Object Detection
• Contrast-Oriented Deep Neural Networks for Salient Object Detection
• Learning Discriminative Feature with CRF for Unsupervised Video Object Segmentation
• A Benchmark Dataset and Saliency-guided Stacked Autoencoders for Video-based Salient Object Detection
• Instance-Level Salient Object Segmentation
• Unsupervised Learning of Important Objects from First-Person Videos
• Deep, Dense, and Low-Rank Gaussian Conditional Random Fields
• Integrated Deep and Shallow Networks for Salient Object Detection
• Automatic Image Stylization Using Deep Fully Convolutional Networks
• LSTM-CF: Unifying Context Modeling and Fusion with LSTMs for RGB-D Scene Labeling
• Using Cross-Model EgoSupervision to Learn Cooperative Basketball Intention
• Hierarchical Deep Co-segmentation of Primary Objects in Aerial Videos