Retrieving Black-box Optimal Images from External Databases

  title={Retrieving Black-box Optimal Images from External Databases},
  author={R. Sato},
  journal={Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining},
  • R. Sato
  • Published 30 December 2021
  • Computer Science
  • Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining
Suppose we have a black-box function (e.g., deep neural network) that takes an image as input and outputs a value that indicates preference. How can we retrieve optimal images with respect to this function from an external database on the Internet? Standard retrieval problems in the literature (e.g., item recommendations) assume that an algorithm has full access to the set of items. In other words, such algorithms are designed for service providers. In this paper, we consider the retrieval… 

Figures and Tables from this paper

CLEAR: A Fully User-side Image Search System
This demonstration shows the first fully user-side image search system, CLEAR, which realizes a similarimage search engine for Flickr, and the challenge is that Flickr does not provide an official similar image search engine or corresponding API.


Deep Image Retrieval: Learning Global Representations for Image Search
This work proposes a novel approach for instance-level image retrieval that produces a global and compact fixed-length representation for each image by aggregating many region-wise descriptors by leveraging a ranking framework and projection weights to build the region features.
Harvesting visual concepts for image search with complex queries
A scheme to enhance web image reranking for complex queries by fully exploring the information from simple visual concepts is presented and two applications are introduced: photo-based question answering and textual news visualization.
Deep Supervised Hashing for Fast Image Retrieval
A novel Deep Supervised Hashing method to learn compact similarity-preserving binary code for the huge body of image data using pairs/triplets of images as training inputs and encouraging the output of each image to approximate discrete values.
Aggregating Local Deep Features for Image Retrieval
This paper shows that deep features and traditional hand-engineered features have quite different distributions of pairwise similarities, hence existing aggregation methods have to be carefully re-evaluated and reveals that in contrast to shallow features, the simple aggregation method based on sum pooling provides the best performance for deep convolutional features.
Deep Neural Architecture for Multi-Modal Retrieval based on Joint Embedding Space for Text and Images
A gated neural architecture is proposed to project image and keyword queries as well as multi-modal retrieval units into the same low-dimensional embedding space and perform semantic matching in this space and demonstrates superior retrieval accuracy of the proposed architecture in comparison to the state-of-art baselines.
Can Social Tagging Improve Web Image Search?
A method that replaces an abstract query term given by a user with a set of concrete terms and that uses these terms in queries input into Web image search engines to improve the recall ratio of Web image searches.
Improving Web Image Search with Contextual Information
A context-aware re-ranking model, a neural network-based framework to re-rank web image search results for a query based on previous interaction behavior in the search session in which the query was submitted, and the results show that CARM outperforms state-of-the-art baseline models in terms of personalized evaluation metrics.
Query refinement suggestion in multimodal image retrieval with relevance feedback
From the results of an evaluation performed, it can be said that this type of query suggestion is a very good enhancement to the relevance feedback scheme, and can potentially lead to better retrieval performance and less effort from the user.
Simultaneous feature learning and hash coding with deep neural networks
Extensive evaluations on several benchmark image datasets show that the proposed simultaneous feature learning and hash coding pipeline brings substantial improvements over other state-of-the-art supervised or unsupervised hashing methods.
Deep Residual Learning for Image Recognition
This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.