Bridging Saliency Detection to Weakly Supervised Object Detection Based on Self-paced Curriculum Learning

Abstract

Weakly-supervised object detection (WOD) is a challenging problems in computer vision. The key problem is to simultaneously infer the exact object locations in the training images and train the object detectors, given only the training images with weak image-level labels. Intuitively, by simulating the selective attention mechanism of human visual system, saliency detection technique can select attractive objects in scenes and thus is a potential way to provide useful priors for WOD. However, the way to adopt saliency detection in WOD is not trivial since the detected saliency region might be possibly highly ambiguous in complex cases. To this end, this paper first comprehensively analyzes the challenges in applying saliency detection to WOD. Then, we make one of the earliest efforts to bridge saliency detection to WOD via the self-paced curriculum learning, which can guide the learning procedure to gradually achieve faithful knowledge of multi-class objects from easy to hard. The experimental results demonstrate that the proposed approach can successfully bridge saliency detection and WOD tasks and achieve the state-of-the-art object detection results under the weak supervision.

Has published in IJCAI 16

References in corpus (1)

• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition

Cited by in corpus (18)

• RGB-D Salient Object Detection: A Survey
• Few-Example Object Detection with Model Communication
• Self Paced Deep Learning for Weakly Supervised Object Detection
• Light Field Salient Object Detection: A Review and Benchmark
• Saliency Guided End-to-End Learning for Weakly Supervised Object Detection
• Generalized Multi-Task Learning from Substantially Unlabeled Multi-Source Medical Image Data
• Deep Descriptor Transforming for Image Co-Localization
• Self-Paced Contrastive Learning for Semi-supervised Medical Image Segmentation with Meta-labels
• Unsupervised Object Discovery and Co-Localization by Deep Descriptor Transforming
• Progressive Self-Guided Loss for Salient Object Detection
• One-Click Annotation with Guided Hierarchical Object Detection
• Distributed Self-Paced Learning in Alternating Direction Method of Multipliers
• Self-Paced Probabilistic Principal Component Analysis for Data with Outliers
• Low-Shot Learning from Imaginary 3D Model
• Salient Object Detection Combining a Self-attention Module and a Feature Pyramid Network
• Graph-Theoretic Spatiotemporal Context Modeling for Video Saliency Detection
• Cascade Graph Neural Networks for RGB-D Salient Object Detection
• Weakly Supervised Object Localization and Detection: A Survey