Supervised Learning Methods for Diversification of Image Search Results

Goynuk, Burak; Altıngövde, İsmail Sengör

doi:10.1007/978-3-030-45442-5_20

Cited by 2 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tables 5 and 6 provide the findings for the approaches based on the supervised R‐LTR method (to facilitate comparisons, the results for the art_xQuAD is repeated). Our results reveal that (a) our multidimensional R‐LTR exp approach (using Adaptive instantiation) with explicit aspects outperforms the baseline R‐LTR imp (which is an implicit diversification method), (b) our implementation of the multidimensional R‐LTR approach using a two‐layer neural network (as in Goynuk and Altingovde [2020]) further improves the performance (since R‐LTR expNN outperforms R‐LTR exp ), and (c) multidimensional R‐LTR expNN yields the best performance only for the ST‐Recall metric, while multidimensional art_xQuAD performs better for the remaining metrics.…”

Section: Experimental Evaluationmentioning

confidence: 99%

“…Finally, in Goynuk and Altingovde (2020), R‐LTR was implemented using a neural network framework, which allows a nonlinear formulation and the training of more complex models (i.e., via multiple hidden layers). Similarly, we apply this approach for training a model based on the same input as Equation ) (denoted by R‐LTR expNN ).…”

Section: Diversification Across Dimensionsmentioning

confidence: 99%

See 1 more Smart Citation

Explicit diversification of search results across multiple dimensions for educational search

Yigit-Sert

Altıngövde

Macdonald

et al. 2020

Asso for Info Science & Tech

Self Cite

View full text Add to dashboard Cite

Making use of search systems to foster learning is an emerging research trend known as search as learning. Earlier works identified result diversification as a useful technique to support learning‐oriented search, since diversification ensures a comprehensive coverage of various aspects of the queried topic in the result list. Inspired by this finding, first we define a new research problem, multidimensional result diversification, in the context of educational search. We argue that in a search engine for the education domain, it is necessary to diversify results across multiple dimensions, that is, not only for the topical aspects covered by the retrieved documents, but also for other dimensions, such as the type of the document (e.g., text, video, etc.) or its intellectual level (say, for beginners/experts). Second, we propose a framework that extends the probabilistic and supervised diversification methods to take into account the coverage of such multiple dimensions. We demonstrate its effectiveness upon a newly developed test collection based on a real‐life educational search engine. Thorough experiments based on gathered relevance annotations reveal that the proposed framework outperforms the baseline by up to 2.4%. An alternative evaluation utilizing user clicks also yields improvements of up to 2% w.r.t. various metrics.

show abstract

Section: Experimental Evaluationmentioning

confidence: 99%

Section: Diversification Across Dimensionsmentioning

confidence: 99%

Explicit diversification of search results across multiple dimensions for educational search

Yigit-Sert

Altıngövde

Macdonald

et al. 2020

Asso for Info Science & Tech

Self Cite

View full text Add to dashboard Cite

show abstract

Boosting Diversity in Visual Search with Pareto Non-Dominated Re-Ranking

Lei,

Gong,

Xiao

et al. 2023

ACM Trans. Multimedia Comput. Commun. Appl.

View full text Add to dashboard Cite

The field of visual search has gained significant attention recently, particularly in the context of web search engines and e-commerce product search platforms. However, the abundance of web images presents a challenge for modern image retrieval systems, as they need to find both relevant and diverse images that maximize users’ satisfaction. In response to this challenge, we propose a non-dominated visual diversity re-ranking (NDVDR) method based on the concept of Pareto Optimality. To begin with, we employ a fast binary hashing method as a coarse-grained retrieval procedure. This allows us to efficiently obtain a subset of candidate images for subsequent re-ranking. Fed with this initial retrieved image results, the NDVDR performs a fine-grained re-ranking procedure for boosting both relevance and visual diversity among the top-ranked images. Recognizing the inherent conflict nature between the objectives of relevance and diversity, the re-ranking procedure is simulated as the analytical stage of a multi-criteria decision-making process, seeking the optimal trade-off between the two conflicting objectives within the initial retrieved images. In particular, a non-dominated sorting mechanism is devised that produces Pareto non-dominated hierarchies among images based on the Pareto dominance relation. Additionally, two novel measures are introduced for the effective characterization of the relevance and diversity scores among different images. We conduct experiments on three popular real-world image datasets and compare our re-ranking method with several state-of-the-art image search re-ranking methods. The experimental results validate that our re-ranking approach guarantees retrieval accuracy while simultaneously boosting diversity among the top-ranked images.

show abstract

Supervised Learning Methods for Diversification of Image Search Results

Abstract: We adopt a supervised learning framework, namely R-LTR [17], to diversify image search results, and extend it in various ways. Our experiments show that the adopted and proposed variants are superior to two well-known baselines, with relative gains up to 11.4%.

Cited by 2 publications

References 13 publications

Explicit diversification of search results across multiple dimensions for educational search

Explicit diversification of search results across multiple dimensions for educational search

Boosting Diversity in Visual Search with Pareto Non-Dominated Re-Ranking

Contact Info

Product

Resources

About