This paper presents a visual attention based convolutional neural network (CNN) to solve the image classification problem in the real complex world scene. The presented method can simulate the process of recognizing objects and find the area of interest which is related with the task. Compared with the CNN method in image classification, the model is proficient in fine-grained classification problem and has a better robustness due to its mechanism of multi-glance and visual attention. We evaluate the model on vehicle dataset, where its performance exceeds CNN baseline on image classification.

A visual attention based convolutional neural network for image classification

With advances in multimedia technologies and the proliferation of smart phone, digital cameras, storage devices, there are a rapidly growing massive amount of multimedia data collected in many applications such as multimedia retrieval and management system, in which the data element is composed of text, image, video and audio. Consequently, the study of multimedia near duplicate detection has attracted significant concern from research organizations and commercial communities. Traditional solution minwish hashing (MinWise) faces two challenges: expensive preprocessing time and lower comparison speed. Thus, this work first introduce a hashing method called one permutation hashing (OPH) to shun the costly preprocessing time. Based on OPH, a more efficient strategy group based one permutation hashing (GOPH) is developed to deal with the high comparison time. Based on the fact that the similarity of most multimedia data is not very high, this work design an new hashing method namely hierarchical one permutation hashing (HOPH) to further improve the performance. Comprehensive experiments on real multimedia datasets clearly show that with similar accuracy HOPH is five to seven times faster than MinWise.

Hierarchical one permutation hashing: efficient multimedia near duplicate detection

With advances in multimedia technologies and the proliferation of smart phone, digital cameras, storage devices, there are a rapidly growing massive amount of multimedia data collected in many applications such as multimedia retrieval and management system, in which the data element is composed of text, image, video and audio. Consequently, the study of multimedia near duplicate detection has attracted significant concern from research organizations and commercial communities. Traditional solution minwish hashing (\minwise) faces two challenges: expensive preprocessing time and lower comparison speed. Thus, this work first introduce a hashing method called one permutation hashing (\oph) to shun the costly preprocessing time. Based on \oph, a more efficient strategy group based one permutation hashing (\goph) is developed to deal with the high comparison time. Based on the fact that the similarity of most multimedia data is not very high, this work design an new hashing method namely hierarchical one permutation hashing (\hoph) to further improve the performance. Comprehensive experiments on real multimedia datasets clearly show that with similar accuracy \hoph is five to seven times faster than

Hierarchical One Permutation Hashing: Efficient Multimedia Near Duplicate Detection

Image similarity measures play an important role in nearest neighbor search and duplicate detection for large-scale image datasets. Recently, Minwise Hashing (or Minhash) and its related hashing algorithms have achieved great performances in large-scale image retrieval systems. However, there are a large number of comparisons for image pairs in these applications, which may spend a lot of computation time and affect the performance. In order to quickly obtain the pairwise images that theirs similarities are higher than the specific threshold T (e.g., 0.5), we propose a dynamic threshold filter of Minwise Hashing for image similarity measures. It greatly reduces the calculation time by terminating the unnecessary comparisons in advance. We also find that the filter can be extended to other hashing algorithms, on when the estimator satisfies the binomial distribution, such as b-Bit Minwise Hashing, One Permutation Hashing, etc. In this pager, we use the Bag-of-Visual-Words (BoVW) model based on the Scale Invariant Feature Transform (SIFT) to represent the image features. We have proved that the filter is correct and effective through the experiment on real image datasets.

A Filter of Minhash for Image Similarity Measures

We propose a spatial min-Hash algorithm that groups the minimal hashing functions into an s-tuples called a sketch depending on the spatial context. We use the bag-of-words technology to represent an image in a spatial pyramid way, and generate a minimal hashing function for each spatial location of the corresponding level. These minimal hashing functions are bundled to form a sketch. Furthermore, we implement the proposed algorithm to similar image searching. We use the binary SIFT combined with Hamming distance to verify the candidate images obtained by the spatial min-Hash in order to improve the retrieval performance. There are two advantages of our method: 1) the spatial min-Hash is more discriminative than the standard min-Hash in term of image representation; 2) the feature matching based on the binary SIFT in the verification stage improves the performance of image retrieval with a low computational cost. We implement our method on Oxford building dataset, and the experimental results demonstrate that the spatial min-Hash is a stronger representation method than the standard min-Hash, and the spatial min-Hash is superior to the standard min-Hash in term of retrieval performance.

Shuyang Song

Papers

Spatial min-Hash for similar image search