Hashing-based cross-modal search which aims to map multiple modality features into binary codes has attracted increasingly attention due to its storage and search efficiency especially in largescale database retrieval. Recent unsupervised deep cross-modal hashing methods have shown promising results. However, existing approaches typically suffer from two limitations: (1) They usually learn cross-modal similarity information separately or in a redundant fusion manner, which may fail to capture semantic correlations among instances from different modalities sufficiently and effectively. (2) They seldom consider the sampling and weighting schemes for unsupervised cross-modal hashing, resulting in the lack of satisfactory discriminative ability in hash codes. To overcome these limitations, we propose a novel unsupervised deep cross-modal hashing method called Joint-modal Distributionbased Similarity Hashing (JDSH) for large-scale cross-modal retrieval. First, we propose a novel cross-modal joint-training method by constructing a joint-modal similarity matrix to fully preserve the cross-modal semantic correlations among instances. Second, we propose a sampling and weighting scheme termed the Distributionbased Similarity Decision and Weighting (DSDW) method for unsupervised cross-modal hashing, which is able to generate more discriminative hash codes by pushing semantic similar instance pairs closer and pulling semantic dissimilar instance pairs apart. The experimental results demonstrate the superiority of JDSH compared with several unsupervised cross-modal hashing methods on two public datasets NUS-WIDE and MIRFlickr.
We study instancewise feature importance scoring as a method for model interpretation. Any such method yields, for each predicted instance, a vector of importance scores associated with the feature vector. Methods based on the Shapley score have been proposed as a fair way of computing feature attributions of this kind, but incur an exponential complexity in the number of features. This combinatorial explosion arises from the definition of the Shapley value and prevents these methods from being scalable to large data sets and complex models. We focus on settings in which the data have a graph structure, and the contribution of features to the target variable is well-approximated by a graph-structured factorization. In such settings, we develop two algorithms with linear complexity for instancewise feature importance scoring. We establish the relationship of our methods to the Shapley value and another closely related concept known as the Myerson value from cooperative game theory. We demonstrate on both language and image data that our algorithms compare favorably with other methods for model interpretation.
We propose a new method for detecting changes in Markov network structure between two sets of samples. Instead of naively fitting two Markov network models separately to the two data sets and figuring out their difference, we directly learn the network structure change by estimating the ratio of Markov network models. This density-ratio formulation naturally allows us to introduce sparsity in the network structure change, which highly contributes to enhancing interpretability. Furthermore, computation of the normalization term, a critical bottleneck of the naive approach, can be remarkably mitigated. We also give the dual formulation of the optimization problem, which further reduces the computation cost for large-scale Markov networks. Through experiments, we demonstrate the usefulness of our method.
In recent years, unmanned aerial vehicles (UAVs) for plant protection have achieved rapid development in China. In order to test and evaluate the performances of pesticides application and development status of UAVs in China, four typical UAV models were selected to test the spraying coverage, penetrability, droplets density and the work efficiency. The results showed that the deposition and spraying liquid coverage were inconsistent both in lateral and longitudinal direction. Under the condition of the similar amount of spray volume and operation parameters, the volume median diameter (VMD) of the droplet was negatively correlated with the coverage density. The failure of the UAVs for plant protection mainly took up on the blockage of nozzle, transfusion tube and the liquid pump. The failure rate of UAVs took up 3.73%-4.36% of the total working time. The operation of UAVs during ground service took up 50% of the total working time, the preparation work took up 10%, and the route planning took up around 10%, while net operation time only took up around 30%. On the whole, the high efficiency of UAV was not fully achieved; the daily operated area was not in a satisfactory level now. The spraying performances of UAVs still need further improvement.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.