Learning Fine-grained Image Similarity with Deep Ranking

Abstract

Learning fine-grained image similarity is a challenging task. It needs to capture between-class and within-class image differences. This paper proposes a deep ranking model that employs deep learning techniques to learn similarity metric directly from images.It has higher learning capability than models based on hand-crafted features. A novel multiscale network structure has been developed to describe the images effectively. An efficient triplet sampling algorithm is proposed to learn the model with distributed asynchronized stochastic gradient. Extensive experiments show that the proposed algorithm outperforms models based on hand-crafted visual features and deep classification models.

CVPR 2014

References in corpus (2)

• Improving neural networks by preventing co-adaptation of feature detectors
• Weighted Random Sampling over Data Streams

Cited by in corpus (22)

• Generalisation and Sharing in Triplet Convnets for Sketch based Visual Search
• Learning Deep Similarity Models with Focus Ranking for Fabric Image Retrieval
• Video2GIF: Automatic Generation of Animated GIFs from Video
• Deep Unsupervised Learning of Visual Similarities
• Fine-grained Categorization and Dataset Bootstrapping using Deep Metric Learning with Humans in the Loop
• Exchangeable deep neural networks for set-to-set matching and learning
• DARI: Distance metric And Representation Integration for Person Verification
• Fast Video Shot Transition Localization with Deep Structured Models
• Generative Model with Coordinate Metric Learning for Object Recognition Based on 3D Models
• Learning Concept Embeddings with Combined Human-Machine Expertise
• Tiny Descriptors for Image Retrieval with Unsupervised Triplet Hashing
• Text Embeddings for Retrieval From a Large Knowledge Base
• Ranked List Loss for Deep Metric Learning
• TransNFCM: Translation-Based Neural Fashion Compatibility Modeling
• Deep Architectures for Learning Context-dependent Ranking Functions
• Channel Interaction Networks for Fine-Grained Image Categorization
• A Multi-Resolution Word Embedding for Document Retrieval from Large Unstructured Knowledge Bases
• Multitask Text-to-Visual Embedding with Titles and Clickthrough Data
• A Neural Embeddings Approach for Detecting Mobile Counterfeit Apps
• Shapes as Product Differentiation: Neural Network Embedding in the Analysis of Markets for Fonts
• Deep learning achieves perfect anomaly detection on 108,308 retinal images including unlearned diseases
• Harvesting Visual Objects from Internet Images via Deep Learning Based Objectness Assessment