Enhanced-alignment Measure for Binary Foreground Map Evaluation

Abstract

The existing binary foreground map (FM) measures to address various types of errors in either pixel-wise or structural ways. These measures consider pixel-level match or image-level information independently, while cognitive vision studies have shown that human vision is highly sensitive to both global information and local details in scenes. In this paper, we take a detailed look at current binary FM evaluation measures and propose a novel and effective E-measure (Enhanced-alignment measure). Our measure combines local pixel values with the image-level mean value in one term, jointly capturing image-level statistics and local pixel matching information. We demonstrate the superiority of our measure over the available measures on 4 popular datasets via 5 meta-measures, including ranking models for applications, demoting generic, random Gaussian noise maps, ground-truth switch, as well as human judgments. We find large improvements in almost all the meta-measures. For instance, in terms of application ranking, we observe improvementrangingfrom9.08% to 19.65% compared with other popular measures.

8pages, 10 figures, IJCAI 2018 (oral)

References in corpus (1)

• Deeply supervised salient object detection with short connections

Cited by in corpus (21)

• Fast Camouflaged Object Detection via Edge-based Reversible Re-calibration Network
• CAGNet: Content-Aware Guidance for Salient Object Detection
• Advances in Deep Concealed Scene Understanding
• Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network
• A Survey on Deep Learning for Polyp Segmentation: Techniques, Challenges and Future Trends
• Salient Objects in Clutter: Bringing Salient Object Detection to the Foreground
• Suppress and Balance: A Simple Gated Network for Salient Object Detection
• Deep Co-supervision and Attention Fusion Strategy for Automatic COVID-19 Lung Infection Segmentation on CT Images
• Contrast-weighted Dictionary Learning Based Saliency Detection for Remote Sensing Images
• Automatic Polyp Segmentation via Multi-scale Subtraction Network
• Uncertainty-aware Joint Salient Object and Camouflaged Object Detection
• A Single Stream Network for Robust and Real-time RGB-D Salient Object Detection
• Structure-Consistent Weakly Supervised Salient Object Detection with Local Saliency Coherence
• Confidence-Aware Learning for Camouflaged Object Detection
• Learning Synergistic Attention for Light Field Salient Object Detection
• An End-to-End Network for Co-Saliency Detection in One Single Image
• Deep RGB-D Saliency Detection with Depth-Sensitive Attention and Automatic Multi-Modal Fusion
• Synergistic saliency and depth prediction for RGB-D saliency detection
• Light Field Saliency Detection with Dual Local Graph Learning andReciprocative Guidance
• Salient Object Detection with Purificatory Mechanism and Structural Similarity Loss
• Cascade Graph Neural Networks for RGB-D Salient Object Detection