An Adversarial Domain Adaptation Network For Cross-Domain Fine-Grained Recognition

Wang, Yimu; Song, Ren‐Jie; Wei, Xiu-Shen; Zhang, Lijun

doi:10.1109/wacv45572.2020.9093306

Cited by 13 publications

(4 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, these settings are not representative of many real-world applications, e.g., recognizing retail products in storage racks by models trained with images collected in controlled environments [5] or recognizing/detecting tends of thousands of natural species in the wild [2]. More research is needed in areas such as domain adaptation [207], [208], [209], long-tailed distributions [210], [211], open world settings [212], scale variations [2], fine-grained video understanding [213], [214], knowledge transfer, and resource constrained embedded deployment, to name a few.…”

Section: Future Directionsmentioning

confidence: 99%

Fine-Grained Image Analysis With Deep Learning: A Survey

Wei

Song

Aodha

et al. 2022

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

172

View full text Add to dashboard Cite

Fine-grained image analysis (FGIA) is a longstanding and fundamental problem in computer vision and pattern recognition, and underpins a diverse set of real-world applications. The task of FGIA targets analyzing visual objects from subordinate categories, e.g., species of birds or models of cars. The small inter-class and large intra-class variation inherent to fine-grained image analysis makes it a challenging problem. Capitalizing on advances in deep learning, in recent years we have witnessed remarkable progress in deep learning powered FGIA. In this paper we present a systematic survey of these advances, where we attempt to re-define and broaden the field of FGIA by consolidating two fundamental fine-grained research areas -fine-grained image recognition and fine-grained image retrieval. In addition, we also review other key issues of FGIA, such as publicly available benchmark datasets and related domain-specific applications. We conclude by highlighting several research directions and open problems which need further exploration from the community.

show abstract

Section: Future Directionsmentioning

confidence: 99%

Fine-Grained Image Analysis With Deep Learning: A Survey

Wei

Song

Aodha

et al. 2022

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

172

View full text Add to dashboard Cite

show abstract

“…Their work shows the superior performance of using discriminative patches in the fine-grained product classification. In the recent study from [ 144 ], a self-attention module is proposed for capturing the most informative parts in images. The authors compared the activation response of a position with the mean value of features to locate the crucial parts of the fine-grained objects.…”

Section: Techniquesmentioning

confidence: 99%

“…The authors compared the activation response of a position with the mean value of features to locate the crucial parts of the fine-grained objects. The experimental results in [ 144 ] show that the fine-grained recognition performance has been improved in cross-domain scenarios.…”

Section: Techniquesmentioning

confidence: 99%

Deep Learning for Retail Product Recognition: Challenges and Techniques

Wei

Tran

et al. 2020

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Taking time to identify expected products and waiting for the checkout in a retail store are common scenes we all encounter in our daily lives. The realization of automatic product recognition has great significance for both economic and social progress because it is more reliable than manual operation and time-saving. Product recognition via images is a challenging task in the field of computer vision. It receives increasing consideration due to the great application prospect, such as automatic checkout, stock tracking, planogram compliance, and visually impaired assistance. In recent years, deep learning enjoys a flourishing evolution with tremendous achievements in image classification and object detection. This article aims to present a comprehensive literature review of recent research on deep learning-based retail product recognition. More specifically, this paper reviews the key challenges of deep learning for retail product recognition and discusses potential techniques that can be helpful for the research of the topic. Next, we provide the details of public datasets which could be used for deep learning. Finally, we conclude the current progress and point new perspectives to the research of related fields.

show abstract

“…To improve the quality of hash codes, supervised hashing methods such as KSH [33], utilize supervised information (e.g., similarity matrix or label information). Inspired by the progress of deep neural networks [21,50], deep supervised hashing [5,20,24,30,46,53,54] has been proposed, which leverages the power of deep learning to generate high-level semantic features.…”

Section: Introductionmentioning

confidence: 99%

Searching Privately by Imperceptible Lying: A Novel Private Hashing Method with Differential Privacy

Wang

Zhang

2020

Proceedings of the 28th ACM International Conference on Multimedia

Self Cite

View full text Add to dashboard Cite

In the big data era, with the increasing amount of multi-media data, approximate nearest neighbor (ANN) search has been an important but challenging problem. As a widely applied large-scale ANN search method, hashing has made great progress, and achieved sublinear search time with low memory space. However, the advances in hashing are based on the availability of large and representative datasets, which often contain sensitive information. Typically, the privacy of this individually sensitive information is compromised. In this paper, we tackle this valuable yet challenging problem and formulate a task termed as private hashing, which takes into account both searching performance and privacy protection. Specifically, we propose a novel noise mechanism, i.e., Random Flipping, and two private hashing algorithms, i.e., PHashing and PITQ, with the refined analysis within the framework of differential privacy, since differential privacy is a well-established technique to measure the privacy leakage of an algorithm. Random Flipping targets binary scenarios and leverages the "Imperceptible Lying" idea to guarantee ϵ-differential privacy by flipping each datum of the binary matrix (noise addition). To preserve ϵ-differential privacy, PHashing perturbs and adds noise to the hash codes learned by non-private hashing algorithms using Random Flipping. However, the noise addition for privacy in PHashing will cause severe performance drops. To alleviate this problem, PITQ leverages the power of alternative learning to distribute the noise generated by Random Flipping into each iteration while preserving ϵ-differential privacy. Furthermore, to empirically evaluate our algorithms, we conduct comprehensive experiments on the image search task and demonstrate that proposed algorithms achieve equal performance compared with non-private hashing methods.

show abstract

An Adversarial Domain Adaptation Network For Cross-Domain Fine-Grained Recognition

Cited by 13 publications

References 19 publications

Fine-Grained Image Analysis With Deep Learning: A Survey

Fine-Grained Image Analysis With Deep Learning: A Survey

Deep Learning for Retail Product Recognition: Challenges and Techniques

Searching Privately by Imperceptible Lying: A Novel Private Hashing Method with Differential Privacy

Contact Info

Product

Resources

About