Iterative Active Classification of Large Image Collection

Song, Mofei; Sun, Zhengxing; Li, Bo; Hu, Jiagao

doi:10.1007/978-3-319-73603-7_24

Cited by 3 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we perform the use study to compare with the following two works: interactive streaming image classification (ISIC) [ 6 ] and PicMarker [ 5 ]. Meanwhile, we also compare the performance of our method with the conference version of this work (2018active) [ 11 ]. To compare the efficiency, we select the two image sets from Scene8 as the evaluation sets, which are used for the evaluation of ISIC and PicMarker, respectively.…”

Section: Resultsmentioning

confidence: 99%

“…Figure 8 a shows that the average of the user effort required by our method is less than that of the conference version—i.e., the curve of our system is lower. Meanwhile, the average timing of our method is 328.3 s. ISIC [ 6 ] reports the average timing of finishing the classification of the same 400 images, which is 656.3 s. In the user study of the conference version [ 11 ], the average timing is 385.8 s. Thus, for the first user study, our method is 2.0 times faster than ISIC, and 1.2 times faster than the conference version. For the second image set, we ask 6 users to classify 538 images by our system and our preliminary version.…”

Section: Resultsmentioning

confidence: 99%

“…The work is an extension of our preliminary research [11]. The extensions are summarized as follows: first, we introduce the idea of semantic embedding for feature learning, which improves the flexibility of image representation.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Personalized Image Classification by Semantic Embedding and Active Learning

Song

2020

Entropy

Self Cite

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: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Personalized Image Classification by Semantic Embedding and Active Learning

Song

2020

Entropy

Self Cite

View full text Add to dashboard Cite

show abstract

“…This work also builds on our previous work of classifying 2D images [27], extending and implementing it to support the classification of 3D shapes. The specific contributions of the current paper are as follows.…”

Section: Contributionmentioning

confidence: 99%

A personalized active method for 3D shape classification

Song

2020

Vis Comput

Self Cite

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

Oracle or Teacher? A Systematic Overview of Research on Interactive Labeling for Machine Learning

Knaeble¹,

Nadj²,

Maedche³

2020

WI2020 Zentrale Tracks

View full text Add to dashboard Cite

Machine learning is steadily growing in popularityas is its demand for labeled training data. However, these datasets often need to be labeled by human domain experts in a labor-intensive process. Recently, a new area of research has formed around this process, called interactive labeling. While much research exists in this young and rapidly growing area, it lacks a systematic overview. In this paper, we strive to provide such overview, along with a cluster analysis and an outlook on five avenues for future research. Hereby, we identified 57 relevant articles, most of them investigating approaches for labeling images or text. Further, our findings indicate that there exist two competing views how the user could be treated: (a) oracle, where users are queried whether a label is right or wrong versus (b) teacher, where users can offer deeper explanations in the interactive labeling process.

show abstract

Iterative Active Classification of Large Image Collection

Cited by 3 publications

References 14 publications

Personalized Image Classification by Semantic Embedding and Active Learning

Personalized Image Classification by Semantic Embedding and Active Learning

A personalized active method for 3D shape classification

Oracle or Teacher? A Systematic Overview of Research on Interactive Labeling for Machine Learning

Contact Info

Product

Resources

About