Unsupervised Semantic-based Aggregation of Deep Convolutional Features

Abstract

In this paper, we propose a simple but effective semantic-based aggregation (SBA) method. The proposed SBA utilizes the discriminative filters of deep convolutional layers as semantic detectors. Moreover, we propose the effective unsupervised strategy to select some semantic detectors to generate the "probabilistic proposals", which highlight certain discriminative pattern of objects and suppress the noise of background. The final global SBA representation could then be acquired by aggregating the regional representations weighted by the selected "probabilistic proposals" corresponding to various semantic content. Our unsupervised SBA is easy to generalize and achieves excellent performance on various tasks. We conduct comprehensive experiments and show that our unsupervised SBA outperforms the state-of-the-art unsupervised and supervised aggregation methods on image retrieval, place recognition and cloud classification.

arXiv comment10 pages. arXiv admin note: text overlap with arXiv:1705.01247

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
• Fully Convolutional Networks for Semantic Segmentation
• A Discriminatively Learned CNN Embedding for Person Re-identification
• Particular object retrieval with integral max-pooling of CNN activations
• CNN Features off-the-shelf: an Astounding Baseline for Recognition
• Weakly Supervised Fine-Grained Image Categorization
• Deep Image Retrieval: Learning global representations for image search
• Neural Activation Constellations: Unsupervised Part Model Discovery with Convolutional Networks
• Unsupervised Part-based Weighting Aggregation of Deep Convolutional Features for Image Retrieval
• Iterative Manifold Embedding Layer Learned by Incomplete Data for Large-scale Image Retrieval

Cited by in corpus (3)

• DASGIL: Domain Adaptation for Semantic and Geometric-aware Image-based Localization
• UR2KiD: Unifying Retrieval, Keypoint Detection, and Keypoint Description without Local Correspondence Supervision
• Adversarial Soft-detection-based Aggregation Network for Image Retrieval