What is a salient object? A dataset and a baseline model for salient object detection

Abstract

Salient object detection or salient region detection models, diverging from fixation prediction models, have traditionally been dealing with locating and segmenting the most salient object or region in a scene. While the notion of most salient object is sensible when multiple objects exist in a scene, current datasets for evaluation of saliency detection approaches often have scenes with only one single object. We introduce three main contributions in this paper: First, we take an indepth look at the problem of salient object detection by studying the relationship between where people look in scenes and what they choose as the most salient object when they are explicitly asked. Based on the agreement between fixations and saliency judgments, we then suggest that the most salient object is the one that attracts the highest fraction of fixations. Second, we provide two new less biased benchmark datasets containing scenes with multiple objects that challenge existing saliency models. Indeed, we observed a severe drop in performance of 8 state-of-the-art models on our datasets (40% to 70%). Third, we propose a very simple yet powerful model based on superpixels to be used as a baseline for model evaluation and comparison. While on par with the best models on MSRA-5K dataset, our model wins over other models on our data highlighting a serious drawback of existing models, which is convoluting the processes of locating the most salient object and its segmentation. We also provide a review and statistical analysis of some labeled scene datasets that can be used for evaluating salient object detection models. We believe that our work can greatly help remedy the over-fitting of models to existing biased datasets and opens new venues for future research in this fast-evolving field.

arXiv commentIEEE Transactions on Image Processing, 2014

References in corpus (1)

• Visual Saliency Based on Scale-Space Analysis in the Frequency Domain

Cited by in corpus (27)

• Salient Object Detection: A Benchmark
• DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detection
• Salient Object Detection: A Survey
• Edge Preserving and Multi-Scale Contextual Neural Network for Salient Object Detection
• Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection
• Structure-measure: A New Way to Evaluate Foreground Maps
• Supervised Saliency Map Driven Segmentation of the Lesions in Dermoscopic Images
• Salient Object Detection with Lossless Feature Reflection and Weighted Structural Loss
• DFNet: Discriminative feature extraction and integration network for salient object detection
• Revisiting Video Saliency: A Large-scale Benchmark and a New Model
• Boundary-guided Feature Aggregation Network for Salient Object Detection
• Spectrum-driven Mixed-frequency Network for Hyperspectral Salient Object Detection
• Learning Uncertain Convolutional Features for Accurate Saliency Detection
• Probabilistic Saliency Estimation
• Agile Amulet: Real-Time Salient Object Detection with Contextual Attention
• Deep Edge-Aware Saliency Detection
• Non-rigid Object Tracking via Deep Multi-scale Spatial-temporal Discriminative Saliency Maps
• Salient Object Detection by Lossless Feature Reflection
• Automatic Salient Object Detection for Panoramic Images Using Region Growing and Fixation Prediction Model
• Progressive Self-Guided Loss for Salient Object Detection
• Analyzing Periodicity and Saliency for Adult Video Detection
• HyperFusion-Net: Densely Reflective Fusion for Salient Object Detection
• A Benchmark Dataset and Saliency-guided Stacked Autoencoders for Video-based Salient Object Detection
• Weakly Supervised Learning for Salient Object Detection
• A Fixation-based 360° Benchmark Dataset for Salient Object Detection
• Towards Accurate RGB-D Saliency Detection with Complementary Attention and Adaptive Integration
• SalSi: A new seismic attribute for salt dome detection