CBIR using Pre-Trained Neural Networks

Alappat, Agnel Lazar; Nakhate, Prajwal; Suman, Sagar; Chandurkar, Ambarish; Pimpalkhute, Varad; Jain, Tapan K.

doi:10.48550/arxiv.2110.14455

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DALG, presented by Y.Song et al, uses a cross-attention module to hierarchically (instead of heuristically) fuse the features [28]. Furthermore, Alappat et al present a model that uses an Inception V3 backbone network and extracts the MS-RMAC feature matrix to retrieve images [29]. Global-local attention module (GLAM), proposed by C.Song, combines both local and global attention as well as spatial and channel attention and then computes a new feature tensor [30].…”

Section: Related Workmentioning

confidence: 99%

Glocal Retriever: Glocal Image Retrieval Using the Combination of Global and Local Descriptors

Kim¹,

Kim²,

Suh³

2023

Electronics

View full text Add to dashboard Cite

Development of deep learning has led to progress in computer vision, including metric learning tasks such as image retrieval, through convolutional neural networks. In image retrieval, the metric distance (i.e., the similarity) between the images needs to be computed and then compared to return similar images. Global descriptors are good at extracting holistic features of an image, such as the overall shape of the main object and the silhouette. On the other hand, the local features extract the detailed features which the model uses to help classify similar images together. This paper proposes a descriptor mixer which takes advantage of both local and global descriptors (group of features combined into one) as well as different types of global descriptors for an effect of a lighter version of an ensemble of models (i.e., fewer parameters and smaller model size than those of actual ensemble of networks). As a result, the model’s performance improved about 1.36% (recall @ 32) when the combination of the descriptors were used. We empirically found out that the combination of GeM and MAC achieved the highest performance.

show abstract

Section: Related Workmentioning

confidence: 99%

Glocal Retriever: Glocal Image Retrieval Using the Combination of Global and Local Descriptors

Kim¹,

Kim²,

Suh³

2023

Electronics

View full text Add to dashboard Cite

show abstract

“…According to the authors in [32], their MS-RMAC method gives better results than the RMAC proposed in [27]. The authors in [33] propose another variant of MS-RMAC with the InceptionV3 architecture and a post-processing of the vector descriptor before calculating the ranking loss.…”

Section: Ms-rmacmentioning

confidence: 99%

A Comparative Study of Reduction Methods Applied on a Convolutional Neural Network

2022

View full text Add to dashboard Cite

With the emergence of smartphones, video surveillance cameras, social networks, and multimedia engines, as well as the development of the internet and connected objects (the Internet of Things—IoT), the number of available images is increasing very quickly. This leads to the necessity of managing a huge amount of data using Big Data technologies. In this context, several sectors, such as security and medicine, need to extract image features (index) in order to quickly and efficiently find these data with high precision. To reach this first goal, two main approaches exist in the literature. The first one uses classical methods based on the extraction of visual features, such as color, texture, and shape for indexation. The accuracy of these methods was acceptable until the early 2010s. The second approach is based on convolutional neuronal networks (CNN), which offer better precision due to the largeness of the descriptors, but they can cause an increase in research time and storage space. To decrease the research time, one needs to reduce the size of these vectors (descriptors) by using dimensionality reduction methods. In this paper, we propose an approach that allows the problem of the “curse of dimensionality” to be solved thanks to an efficient combination of convolutional neural networks and dimensionality reduction methods. Our contribution consists of defining the best combination approach between the CNN layers and the regional maximum activation of convolutions (RMAC) method and its variants. With our combined approach, we propose providing reduced descriptors that will accelerate the research time and reduce the storage space while maintaining precision. We conclude by proposing the best position of an RMAC layer with an increase in accuracy ranging from 4.03% to 27.34%, a decrease in research time ranging from 89.66% to 98.14% in the function of CNN architecture, and a reduction in the size of the descriptor vector by 97.96% on the GHIM-10K benchmark database.

show abstract

CBIR using Pre-Trained Neural Networks

Cited by 2 publications

References 0 publications

Glocal Retriever: Glocal Image Retrieval Using the Combination of Global and Local Descriptors

Glocal Retriever: Glocal Image Retrieval Using the Combination of Global and Local Descriptors

A Comparative Study of Reduction Methods Applied on a Convolutional Neural Network

Contact Info

Product

Resources

About