Deep Learning—A New Era in Bridging the Semantic Gap

Markowska–Kaczmar, Urszula; Kwaśnicka, Halina

doi:10.1007/978-3-319-73891-8_7

Cited by 8 publications

(5 citation statements)

References 105 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Early on, for a certain feature dimension, direct activation utilizing commercially available pre-trained models [9] surpassed conventional image retrieval algorithms. In order to increase accuracy at the expense of longer running times, it was therefore suggested that better image features are extracted by convolutional networks and then sent to supervised or unsupervised machine learning algorithms to improve accuracy at the cost of increased running time [10]. Additionally, they focused on developing more effective goal functions, enhancing data, and developing sampling techniques.…”

Section: Introductionmentioning

confidence: 99%

SE‐Swin: An improved Swin‐Transfomer network of self‐ensemble feature extraction framework for image retrieval

Xu,

Wang,

Zhang

et al. 2023

IET Image Processing

View full text Add to dashboard Cite

The Swin‐Transformer is a variant of the Vision Transformer, which constructs a hierarchical Transformer that computes representations with shifted windows and window multi‐head self‐attention. This method can handle the scale invariance problem and performs well in many computer vision tasks. In image retrieval, high‐quality feature descriptors are necessary to improve retrieval accuracy. This paper proposes a self‐ensemble Swin‐Transformer network structure to fuse the features of different layers of the Swin‐Transformer network, eliminating noise points present in a single layer, and improving the retrieval effect. Two experiments were conducted, one on the In‐shop Clothes Retrieval dataset and another on the Stanford Online Product dataset. The experiments showed that the proposed method significantly increased the retrieval effect of features extracted using Vision Transformer, surpassing previous state‐of‐the‐art image retrieval methods. In the second experiment, the feature map of the trained model was visualized, revealing that the improved network significantly reduces focus on some noise points and enhances focus on image features compared to the original network.

show abstract

Section: Introductionmentioning

confidence: 99%

SE‐Swin: An improved Swin‐Transfomer network of self‐ensemble feature extraction framework for image retrieval

Xu,

Wang,

Zhang

et al. 2023

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…Multi-dimensional vector space is in relatively lower level than human recognition, and the gap between vector feature and human recognition is called the "semantic gap". In other words, the ultimate objective is to reduce the semantic gap of recognition between human and computer vision [4].…”

Section: Introductionmentioning

confidence: 99%

A Study on the Channel Expansion VAE for Content-Based Image Retrieval

Lee

et al. 2022

Applied Sciences

View full text Add to dashboard Cite

Content-based image retrieval (CBIR) focuses on video searching with fine-tuning of pre-trained off-the-shelf features. CBIR is an intuitive method for image retrieval, although it still requires labeled datasets for fine-tuning due to the inefficiency caused by annotation. Therefore, we explored an unsupervised model for feature extraction of image contents. We used a variational auto-encoder (VAE) expanding channel of neural networks and studied the activation of layer outputs. In this study, the channel expansion method boosted the capability of image retrieval by exploring more kernels and selecting a layer of comparatively activated object region. The experiment included a comparison of channel expansion and visualization of each layer in the encoder network. The proposed model achieved (52.7%) mAP, which outperformed (36.5%) the existing VAE on the MNIST dataset.

show abstract

“…Feeding extracted features to machine learning algorithms (supervised or unsupervised) can improve the CBIR performance (D. Zhang et al, 2012). The trends of recent image retrieval research concentrate on the use of deep learning to improve accuracy at the cost of increasing running time (Markowska-Kaczmar & Kwaśnicka, 2018). Another problem that has a negative effect on CBIR performance (i.e., memory usage, scalability, speed, accuracy) is the high-dimensional features that are usually generated when trying to translate visual image content to a numerical feature form.…”

Section: Introductionmentioning

confidence: 99%

Content-based image retrieval: A review of recent trends

2021

View full text Add to dashboard Cite

With the availability of internet technology and the low-cost of digital image sensor, enormous amount of image databases have been created in different kind of applications. These image databases increase the demand to develop efficient image retrieval search methods that meet user requirements. Great attention and efforts have been devoted to improve content-based image retrieval method with a particular focus on reducing the semantic gap between low-level features and human visual perceptions. Due to the increasing research in this field, this paper surveys, analyses and compares the current state-of-the-art methodologies over the last six years in the CBIR field. This paper also provides an overview of CBIR framework, recent low-level feature extraction methods, machine learning algorithms, similarity measures, and a performance evaluation to inspire further research efforts.

show abstract

Deep Learning—A New Era in Bridging the Semantic Gap

Cited by 8 publications

References 105 publications

SE‐Swin: An improved Swin‐Transfomer network of self‐ensemble feature extraction framework for image retrieval

SE‐Swin: An improved Swin‐Transfomer network of self‐ensemble feature extraction framework for image retrieval

A Study on the Channel Expansion VAE for Content-Based Image Retrieval

Content-based image retrieval: A review of recent trends

Contact Info

Product

Resources

About