The effect of low-level image features on pseudo relevance feedback

Vocabulary mismatch in Information retrieval can be solved by Query Expansion (QE) techniques. Relevance feedback is a prominent solution to improve recall of retrieval system. Sometimes user may be reluctant and novice in providing feedback to improve the retrieval performance. Pseudo Relevance Feedback (PRF) automates the process. PRF treats top ranked resultant items are relevant and uses them to expand the query, which is not always correct. PRF by local analysis does not give guarantee to feedback positive terms to the system. Use of global analysis to capture the positive feedback is a regular practice in information retrieval process. This paper addresses the limitations of local analysis and global analysis alone by a novel approach that integrates both PRF and WordNet to select good expansion terms. The proposed solution filters the expansion terms and optimizes the expanded query. The proposed work is carried out on a huge Telugu text corpus collected from Wikipedia and other Telugu daily news portals.

Relevance Feedback (RF) is an important technique to improve information retrieval and has emerged as one of the hottest topics for both the industry and academic researchers. The performance of RF depends on feedback information. As the volume of feedback information gradually increases, Explicit Relevance Feedback (ERF) is attractive. In this paper, we focus on the ERF in which Feedback information is given. With regards to the lack of information in ERF, we apply Pseudo Relevance Feedback (PRF) to enhance retrieval effectiveness. However, the instability of PRF can result in a negative impact on retrieval performance. We use feedback information to define features and propose a classification model to predict which query can benefit from PRF. Then, we form relevance feedback fusion by the prediction of PRF performance. This method is designed to exploit the strengths of PRF and ERF while avoiding some weaknesses of these approaches. Experiment results show that our approach is feasible and effective.

Query-document vocabulary mismatch, the lack of query expressiveness for user needs and the phenomenon of short queries are the main issues associated with information retrieval systems. Query Expansion (QE) is one of the well-known alternative for overcoming these problems. It mainly involves finding synonyms or related words for the query terms. There are several approaches in the query expansion field such as statistical and semantic approaches; they focus on expanding the individual query terms rather than the entire query during the expansion process. An other category of approaches deals with the whole query by using a neural approach based on Pseudo Relevance feedback (PRF) documents. In this work, we carried out an ablation study to measure the impact of the classical and semantic (word embedding, order, context) based query expansion on the retrieval performance. The experiments conducted on the Arabic EveTAR dataset reveal that our hybrid proposed approach combining classical (PRF) and transformer (AraBERT) is competitive with the state-of-the-art methods. In fact, the obtained result in terms of the Mean Average Precision (MAP) is up to 0.72.

Latent Semantic Indexing (LSI) and Relevance Feedback (RF) have been shown to be extremely useful in information retrieval respectively. But at the context of Web image retrieval, LSI is limited for the Single Value Decomposition (SVD) computation cost to large dataset while RF is confused with the reluctance of interaction for most Web users. In this paper, a Pseudo Relevance Feedback approach based on Local Latent Semantic Indexing (PRF-LLSI) is proposed, which integrating the LSI and RF, and making use of the benefit of them while solving the limitation of them. The Local LSI (LLSI) method performs a low-dimensional SVD on the local region of initial retrieved results. Both keywords and image contents of the Web images are computed by LLSI to re-rank the initial retrieval results automatically. The PRF-LLSI contribute to the following: 1) Local LSI resolves the heavy computation cost of LSI; 2) Pseudo Relevance Feedback doesn’t need the user’s interaction; 3) LLSI combine the textual and visual features, which improves the precision of the system. The experiments are done in our VAST (VisuAl & SemanTic image search) system, and the results show the effectiveness of the proposed method.

Query Expansion using Pseudo Relevance Feedback is a useful and a popular technique for reformulating the query. In our proposed query expansion method, we assume that relevant information can be found within a document near the central idea. The document is normally divided into sections, paragraphs and lines. The proposed method tries to extract keywords that are closer to the central theme of the document. The expansion terms are obtained by equi-frequency partition of the documents obtained from pseudo relevance feedback and by using tf-idf scores. The idf factor is calculated for number of partitions in documents. The group of words for query expansion is selected using the following approaches: the highest score, average score and a group of words that has maximum number of keywords. As each query behaved differently for different methods, the effect of these methods in selecting the words for query expansion is investigated. From this initial study, we extend the experiment to develop a rule-based statistical model that automatically selects the best group of words incorporating the tf-idf scoring and the 3 approaches explained here, in the future. The experiments were performed on FIRE 2011 Adhoc Hindi and English test collections on 50 queries each, using Terrier as retrieval engine.

This paper introduced a LDA-based pseudo relevance feedback (PRF) model for cross language information retrieval. To validate the performance of PRF techniques in CLIR task, we conducted cross language query expansion experiments based on a self-constructed CLIR system, the LDA-based PRF model was applied before or after the query translating process, namely the pre-translation-PRF, the post-translation-PRF, and the combined-PRF strategy. We also compared this model with the classical VSM-based PRF algorithm. Experiment results showed that the proposed LDA-based PRF method was effective for improving the performance of CLIR.

Microblog retrieval has received much attention in recent years due to the wide spread of social microblogging platforms such as Twitter. Many research studies investigated different approaches for microblog retrieval. Query expansion is one of the approaches that showed stable performance for improving microblog retrieval effectiveness. In this paper we comprehensively investigate query expansion for microblog retrieval using pseudo relevance feedback (PRF) with different configurations. In addition, we propose a hyperlink-extended PRF by expanding queries using embedded hyperlinks in retrieved microblogs. Our experimental results on TREC microblog data showed that PRF alone could outperform many retrieval approaches if configured properly. Results also showed that utilizing hyperlinked documents in tweets for query expansion improves results over traditional PRF. Our best results achieved using hyperlink-extended PRF outperformed most of the reported results using other approaches.

Pseudo-relevance feedback (PRF) is an effective approach in Information Retrieval but unfortunately many experiments have shown that PRF is ineffective in patent retrieval. This is because the quality of initial results in the patent retrieval is poor and therefore estimating a relevance model via PRF often hurts the retrieval performance due to off-topic terms. We propose a learning to rank framework for estimating the effectiveness of a patent document in terms of its performance in PRF. Specifically, the knowledge of effective feedback documents on past queries is used to estimate effective feedback documents for new queries. This is achieved by introducing features correlated with feedback document effectiveness. We use patent-specific contents to define such features. We then apply regression to predict document effectiveness given the proposed features. We evaluated the effectiveness of the proposed method on the patent prior art search collection CLEF-IP 2010. Our experimental results show significantly improved retrieval accuracy over a PRF baseline which expands the query using all top-ranked documents.

Geographic Information Retrieval (GIR) is a specialized Information Retrieval (IR) branch that deals with information related to geographical locations. Traditional IR engines are perfectly able to retrieve the majority of the relevant documents for most geographical queries, but they have severe difficulties generating a pertinent ranking of the retrieved results, which leads to poor performance. A key reason for this ranking problem has been a lack of information. Therefore, previous GIR research has tried to fill this gap using robust geographical resources (i.e. a geographical ontology), while other research with the same aim has used relevant feedback techniques instead. This paper explores the use of Bag of Concepts (BoC; a representation where documents are considered as the union of the meanings of its terms) and Holographic Reduced Representation (HRR; a novel representation for textual structure) as re-ranking mechanisms for GIR. Our results reveal an improvement in mean average precision (MAP) when compared to the traditional vector space model, even if Pseudo Relevance Feedback is employed.

Pseudo-relevance feedback (PRF) has been proven to be an effective query expansion strategy to improve retrieval performance. Several PRF methods have so far been proposed for many retrieval models. Recent theoretical studies of PRF methods show that most of the PRF methods do not satisfy all necessary constraints. Among all, the log-logistic model has been shown to be an effective method that satisfies most of the PRF constraints. In this paper, we first introduce two new PRF constraints. We further analyze the log-logistic feedback model and show that it does not satisfy these two constraints as well as the previously proposed "relevance effect" constraint. We then modify the log-logistic formulation to satisfy all these constraints. Experiments on three TREC newswire and web collections demonstrate that the proposed modification significantly outperforms the original log-logistic model, in all collections.

Computer vision based road detection is an indispensable and challenging task in many real-world applications such as obstacle detection in autonomous driving. Low-level image features (e.g., color and texture) and pre-trained models are commonly used for this task. In this paper, we propose a simple yet effective approach to detect roads from a single image, which avoids the supervised model training that typically relies on a considerable number of labeled images. The key idea is to leverage unsupervised feature learning to obtain good road representations. Specifically, we first represent an input road image as a set of image patches. The K-means clustering algorithm is then applied to these image patches (after pre-processing) to generate K cluster centroids. Thus obtained centroids will be used together with a nonlinear mapping function and a bag-of-words projection to derive the image's feature representation in pixel and region levels respectively. All pixels (of the input image) using the former mapping will be clustered by Density Peaks algorithm into several regions, and the regions represented by the latter feature will be grouped by a graph cut method into two classes: road and non-road. Experimental results on several complicated road images demonstrate the effectiveness of our proposed method.

It is shown in [4] that Rocchio's similarity-based relevance feedback algorithm makes Ωn mistakes in searching for a collection of documents represented by a monotone disjunction of at most k relevant features or terms over the n-dimensional binary vector space {0, 1}n. In practice, Rocchio's algorithm often uses a fixed query updating factor and a fixed classification threshold. When this is the case, we strengthen the work in [4] in this paper and prove that Rocchio's algorithm makes Ωkn---k mistakes in searching for the same collection of documents over the binary vector space {0, 1}n. A quadratic lower bound is obtained when k is proportional to n. An Okn---k2 upper bound is also obtained.

Relevance feedback (RF) approaches are use to improve the performance of content-based image retrieval (CBIR) systems. In this paper, a RF approach based on modification of similarity measure using particle swarm optimization (PSO) in a medical X-ray image retrieval system is proposed. In this algorithm, using PSO, the significance of each feature in the similarity measure is modified to image retrieval. This modification causes that good features have major effect in relevant image retrieval. The defined fitness function in PSO uses relevant and irrelevant retrieved images with different strategies, simultaneously. The relevant and irrelevant images are used to exhort and penalize similarity measure, respectively. To evaluate, the proposed RF is integrated to a CBIR system based on semantic classification. In this system, using merging scheme in a hierarchical structure, the overlapped classes are merged together and determined search space for each query image. The proposed RF evaluated on a database consisting of 10000 medical X-ray images of 57 classes. The proposed algorithm provides the improvement, effectiveness more than the literature.

Medical image retrieval can assist physicians in finding information supporting their diagnosis and fulfilling information needs. Systems that allow searching for medical images need to provide tools for quick and easy navigation and query refinement as the time available for information search is often short. Relevance feedback is a powerful tool in information retrieval. This study evaluates relevance feedback techniques with regard to the content they use. A novel relevance feedback technique that uses both text and visual information of the results is proposed. The two information modalities from the image examples are fused either at the feature level using the Rocchio algorithm or at the query list fusion step using a common late fusion rule. Results using the ImageCLEF 2012 benchmark database for medical image retrieval show the potential of relevance feedback techniques in medical image retrieval. The mean average precision (mAP) is used as the evaluation metric and the proposed method outperforms commonly-used methods. The baseline without feedback reached 16 % whereas the relevance feedback with 20 images reached up to 26.35 % with three steps and when using 100 images up to 34.87 % in four steps. Most improvements occur in the first two steps of relevance feedback and then results start to become relatively flat. This might also be due to only using positive feedback as negative feeback often also improves results after more steps. The effect of relevance feedback in automatically spelling corrected and translated queries is investigated as well. Results without mistakes were better than spell-corrected results but the spelling correction more than double results over non-corrected retrieval. Multimodal relevance feedback has shown to be able to help visual medical information retrieval. Next steps include integrating semantics into relevance feedback techniques to benefit from the structured knowledge of ontologies and experimenting on the fusion of text and visual information.

An approach using many intermediate semantic concepts is proposed with the potential to bridge the semantic gap between what a color, shape, and texture-based ldquolow-levelrdquo image analysis can extract from video and what users really want to find, most likely using text descriptions of their information needs. Semantic concepts such as cars, planes, roads, people, animals, and different types of scenes (outdoor, night time, etc.) can be automatically detected in the video with reasonable accuracy. This leads us to ask how can they be used automatically and how does a user (or a retrieval system) translate the user's information need into a selection of related concepts that would help find the relevant video clips, from the large list of available concepts. We illustrate how semantic concept retrieval can be automatically exploited by mapping queries into query classes and through pseudo-relevance feedback. We also provide evidence how a semantic concept can be utilized by users in interactive retrieval, through interfaces that provide affordances of explicit concept selection and search, concept filtering, and relevance feedback. How many concepts we actually need and how accurately they need to be detected and linked through various relationships is specified in the ontology structure.