Apr 21 2017 cs.CV
The recently proposed stochastic residual networks selectively activate or bypass the layers during training, based on independent stochastic choices, each of which following a probability distribution that is fixed in advance. In this paper we present a first exploration on the use of an epoch-dependent distribution, starting with a higher probability of bypassing deeper layers and then activating them more frequently as training progresses. Preliminary results are mixed, yet they show some potential of adding an epoch-dependent management of distributions, worth of further investigation.
Aug 03 2016 cs.CV
Content-Based Image Retrieval based on local features is computationally expensive because of the complexity of both extraction and matching of local feature. On one hand, the cost for extracting, representing, and comparing local visual descriptors has been dramatically reduced by recently proposed binary local features. On the other hand, aggregation techniques provide a meaningful summarization of all the extracted feature of an image into a single descriptor, allowing us to speed up and scale up the image search. Only a few works have recently mixed together these two research directions, defining aggregation methods for binary local features, in order to leverage on the advantage of both approaches. In this paper, we report an extensive comparison among state-of-the-art aggregation methods applied to binary features. Then, we mathematically formalize the application of Fisher Kernels to Bernoulli Mixture Models. Finally, we investigate the combination of the aggregated binary features with the emerging Convolutional Neural Network (CNN) features. Our results show that aggregation methods on binary features are effective and represent a worthwhile alternative to the direct matching. Moreover, the combination of the CNN with the Fisher Vector (FV) built upon binary features allowed us to obtain a relative improvement over the CNN results that is in line with that recently obtained using the combination of the CNN with the FV built upon SIFTs. The advantage of using the FV built upon binary features is that the extraction process of binary features is about two order of magnitude faster than SIFTs.
In this paper we tackle the problem of image search when the query is a short textual description of the image the user is looking for. We choose to implement the actual search process as a similarity search in a visual feature space, by learning to translate a textual query into a visual representation. Searching in the visual feature space has the advantage that any update to the translation model does not require to reprocess the, typically huge, image collection on which the search is performed. We propose Text2Vis, a neural network that generates a visual representation, in the visual feature space of the fc6-fc7 layers of ImageNet, from a short descriptive text. Text2Vis optimizes two loss functions, using a stochastic loss-selection method. A visual-focused loss is aimed at learning the actual text-to-visual feature mapping, while a text-focused loss is aimed at modeling the higher-level semantic concepts expressed in language and countering the overfit on non-relevant visual components of the visual loss. We report preliminary results on the MS-COCO dataset.
Surrogate Text Representation (STR) is a profitable solution to efficient similarity search on metric space using conventional text search engines, such as Apache Lucene. This technique is based on comparing the permutations of some reference objects in place of the original metric distance. However, the Achilles heel of STR approach is the need to reorder the result set of the search according to the metric distance. This forces to use a support database to store the original objects, which requires efficient random I/O on a fast secondary memory (such as flash-based storages). In this paper, we propose to extend the Surrogate Text Representation to specifically address a class of visual metric objects known as Vector of Locally Aggregated Descriptors (VLAD). This approach is based on representing the individual sub-vectors forming the VLAD vector with the STR, providing a finer representation of the vector and enabling us to get rid of the reordering phase. The experiments on a publicly available dataset show that the extended STR outperforms the baseline STR achieving satisfactory performance near to the one obtained with the original VLAD vectors.
A new class of applications based on visual search engines are emerging, especially on smart-phones that have evolved into powerful tools for processing images and videos. The state-of-the-art algorithms for large visual content recognition and content based similarity search today use the "Bag of Features" (BoF) or "Bag of Words" (BoW) approach. The idea, borrowed from text retrieval, enables the use of inverted files. A very well known issue with this approach is that the query images, as well as the stored data, are described with thousands of words. This poses obvious efficiency problems when using inverted files to perform efficient image matching. In this paper, we propose and compare various techniques to reduce the number of words describing an image to improve efficiency and we study the effects of this reduction on effectiveness in landmark recognition and retrieval scenarios. We show that very relevant improvement in performance are achievable still preserving the advantages of the BoF base approach.
The scalability, as well as the effectiveness, of the different Content-based Image Retrieval (CBIR) approaches proposed in literature, is today an important research issue. Given the wealth of images on the Web, CBIR systems must in fact leap towards Web-scale datasets. In this paper, we report on our experience in building a test collection of 100 million images, with the corresponding descriptive features, to be used in experimenting new scalable techniques for similarity searching, and comparing their results. In the context of the SAPIR (Search on Audio-visual content using Peer-to-peer Information Retrieval) European project, we had to experiment our distributed similarity searching technology on a realistic data set. Therefore, since no large-scale collection was available for research purposes, we had to tackle the non-trivial process of image crawling and descriptive feature extraction (we used five MPEG-7 features) using the European EGEE computer GRID. The result of this effort is CoPhIR, the first CBIR test collection of such scale. CoPhIR is now open to the research community for experiments and comparisons, and access to the collection was already granted to more than 50 research groups worldwide.