Personalized image annotation via class-specific cross-domain learning

Qian, Zhenyu; Zhong, Ping; Wang, Runsheng

doi:10.1016/j.image.2015.03.008

Cited by 5 publications

(7 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to whether user interaction is needed, we divide existing work into two types of methods, automatic methods and semiautomatic methods. The automatic methods achieve personalization by inferring from personal tagging history or personal collections [6,10,24]. These methods exploit the related clues to learn the personalized classifier in a batch way, but they all collect a large amount of data in advance.…”

Section: Personalized Classificationmentioning

confidence: 99%

A personalized active method for 3D shape classification

Song

2020

Vis Comput

View full text Add to dashboard Cite

To efficiently and flexibly classify 3D shape in a user-adaptive way, this paper proposes a novel interactive system by incorporating active learning, online learning and user intervention. Given a shape collection, our system iteratively alternates the interactive annotation and verification until the labels of all the shapes are confirmed explicitly by the users. The main advantage is that it provides faster interactive classification rates than alternative approaches. Our system achieves this goal by a unified active learning algorithm that selects the shapes to be annotated or verified for the next iteration. The shape selection step is solved by maximizing a probability model for simulating the time cost of human input during manual intervention. The selected shapes are then pushed to the users along with their category predictions, which are generated by a proposed weighted blending framework. After manually confirming or refining the automatic predictions, we use an extended soft confidence-weighted learning method to update the classifier incrementally for the subsequent active selection and shape classification in turn. Experimental results demonstrated the effectiveness of the proposed method.

show abstract

Section: Personalized Classificationmentioning

confidence: 99%

A personalized active method for 3D shape classification

Song

2020

Vis Comput

View full text Add to dashboard Cite

show abstract

“…According to whether user intervention is required, existing work can be divided into automatic methods and interactive methods. The automatic methods [ 15 , 16 ] learn the personalized classifier based on personal collections or tagging history in an offline manner. However, a large amount of data are required to be annotated according to a specific user’s preference in advance.…”

Section: Related Workmentioning

confidence: 99%

Personalized Image Classification by Semantic Embedding and Active Learning

Song

2020

Entropy

View full text Add to dashboard Cite

Currently, deep learning has shown state-of-the-art performance in image classification with pre-defined taxonomy. However, in a more real-world scenario, different users usually have different classification intents given an image collection. To satisfactorily personalize the requirement, we propose an interactive image classification system with an offline representation learning stage and an online classification stage. During the offline stage, we learn a deep model to extract the feature with higher flexibility and scalability for different users’ preferences. Instead of training the model only with the inter-class discrimination, we also encode the similarity between the semantic-embedding vectors of the category labels into the model. This makes the extracted feature adapt to multiple taxonomies with different granularities. During the online session, an annotation task iteratively alternates with a high-throughput verification task. When performing the verification task, the users are only required to indicate the incorrect prediction without giving the exact category label. For each iteration, our system chooses the images to be annotated or verified based on interactive efficiency optimization. To provide a high interactive rate, a unified active learning algorithm is used to search the optimal annotation and verification set by minimizing the expected time cost. After interactive annotation and verification, the new classified images are used to train a customized classifier online, which reflects the user-adaptive intent of categorization. The learned classifier is then used for subsequent annotation and verification tasks. Experimental results under several public image datasets show that our method outperforms existing methods.

show abstract

“…Domain adaptation deals with the distribution divergence across domains, which aroused considerable interest in computer vision community [3,4,12]. There are many methods to cope with domain adaptation problems including instance, feature and classifier based approaches.…”

Section: Related Workmentioning

confidence: 99%

“…Visual domain adaptation problem has attracted great attention in computer vision and machine learning areas [1][2][3][4][5]. In real world applications, collecting labeled images or annotating unlabeled images is time-consuming and difficult.…”

Section: Introductionmentioning

confidence: 99%