Deep Unsupervised Saliency Detection: A Multiple Noisy Labeling Perspective

Abstract

The success of current deep saliency detection methods heavily depends on the availability of large-scale supervision in the form of per-pixel labeling. Such supervision, while labor-intensive and not always possible, tends to hinder the generalization ability of the learned models. By contrast, traditional handcrafted features based unsupervised saliency detection methods, even though have been surpassed by the deep supervised methods, are generally dataset-independent and could be applied in the wild. This raises a natural question that "Is it possible to learn saliency maps without using labeled data while improving the generalization ability?". To this end, we present a novel perspective to unsupervised saliency detection through learning from multiple noisy labeling generated by "weak" and "noisy" unsupervised handcrafted saliency methods. Our end-to-end deep learning framework for unsupervised saliency detection consists of a latent saliency prediction module and a noise modeling module that work collaboratively and are optimized jointly. Explicit noise modeling enables us to deal with noisy saliency maps in a probabilistic way. Extensive experimental results on various benchmarking datasets show that our model not only outperforms all the unsupervised saliency methods with a large margin but also achieves comparable performance with the recent state-of-the-art supervised deep saliency methods.

Accepted by IEEE/CVF CVPR 2018 as Spotlight

References in corpus (5)

• Caffe: Convolutional Architecture for Fast Feature Embedding
• Visual Saliency Based on Multiscale Deep Features
• Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection
• Learning Deep Networks from Noisy Labels with Dropout Regularization
• Integrated Deep and Shallow Networks for Salient Object Detection

Cited by in corpus (19)

• Advances in Deep Concealed Scene Understanding
• Self-supervising Action Recognition by Statistical Moment and Subspace Descriptors
• UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders
• Few-Shot Learning via Saliency-guided Hallucination of Samples
• Finding an Unsupervised Image Segmenter in Each of Your Deep Generative Models
• Weakly-Supervised Salient Object Detection via Scribble Annotations
• Structure-Consistent Weakly Supervised Salient Object Detection with Local Saliency Coherence
• SEIGAN: Towards Compositional Image Generation by Simultaneously Learning to Segment, Enhance, and Inpaint
• Visual Saliency Maps Can Apply to Facial Expression Recognition
• DeepUSPS: Deep Robust Unsupervised Saliency Prediction With Self-Supervision
• Distilling Localization for Self-Supervised Representation Learning
• Unsupervised Single Image Deraining with Self-supervised Constraints
• Uncertainty Inspired RGB-D Saliency Detection
• Learning Noise-Aware Encoder-Decoder from Noisy Labels by Alternating Back-Propagation for Saliency Detection
• Uncertainty-Aware Deep Calibrated Salient Object Detection
• Multi-Class Classification from Noisy-Similarity-Labeled Data
• What I See Is What You See: Joint Attention Learning for First and Third Person Video Co-analysis
• Deep Robust Subjective Visual Property Prediction in Crowdsourcing
• Region Refinement Network for Salient Object Detection