Online User Modeling for Interactive Streaming Image Classification

Hu, Jiagao; Sun, Zhengxing; Li, Bo; Yang, Kewei; Li, Dongyang

doi:10.1007/978-3-319-51814-5_25

Cited by 8 publications

(9 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…When the classifier is updated, we test the accurate rate of the classifier on the test set. To compare with previous methods [ 6 ], we also record the performance of the classifier when the 660 images are trained in a random sequence. As shown in Figure 7 b, our method can achieve a faster growth rate of the accuracy curve.…”

Section: Resultsmentioning

confidence: 99%

“…However, most existing methods are not very efficient, since users are asked to label the examples one by one. The most related works are interactive image classification method [ 5 , 6 ]. Instead of providing one image once, these methods provide a group of images and their category prediction at one time, which allows the user to interactively classify a collection of images in a more high-throughput way.…”

Section: Related Workmentioning

confidence: 99%

“…To address this issue, some methods [ 5 , 6 ] first extract many features from different views to cover diverse requirements, and then use online user intervention to confirm and refine the class label of every image interactively. As a result, the users can control the classification of the given image collection in a user-adaptive way.…”

Section: Introductionmentioning

confidence: 99%

“…The first problem is the adaptability of the image representation. especially, these methods [ 5 , 6 ] directly concatenate the appearance and semantic features into a high-dimensional vector representation, which is very inefficient. Moreover, the semantic feature only covers the discrimination information of one certain taxonomy.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

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

Section: Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Personalized Image Classification by Semantic Embedding and Active Learning

Song

2020

Entropy

View full text Add to dashboard Cite

show abstract

“…For example, Song et al propose an incremental online algorithm to dynamically update the LS-SVM model when a new chunk of samples are incorporated into the SV set [22]. Hu et al use an incremental online variant of the nearest class mean classifier and update the class means incrementally [23]. A novel online universal classifier capable of performing the multi-classification problem is proposed in [24].…”

Section: Related Workmentioning

confidence: 99%

A Noise-Resilient Online Learning Algorithm for Scene Classification

et al. 2018

View full text Add to dashboard Cite

The proliferation of remote sensing imagery motivates a surge of research interest in image processing such as feature extraction and scene recognition, etc. Among them, scene recognition (classification) is a typical learning task that focuses on exploiting annotated images to infer the category of an unlabeled image. Existing scene classification algorithms predominantly focus on static data and are designed to learn discriminant information from clean data. They, however, suffer from two major shortcomings, i.e., the noisy label may negatively affect the learning procedure and learning from scratch may lead to a huge computational burden. Thus, they are not able to handle large-scale remote sensing images, in terms of both recognition accuracy and computational cost. To address this problem, in the paper, we propose a noise-resilient online classification algorithm, which is scalable and robust to noisy labels. Specifically, ramp loss is employed as loss function to alleviate the negative affect of noisy labels, and we iteratively optimize the decision function in Reproducing Kernel Hilbert Space under the framework of Online Gradient Descent (OGD). Experiments on both synthetic and real-world data sets demonstrate that the proposed noise-resilient online classification algorithm is more robust and sparser than state-of-the-art online classification algorithms.

show abstract