Visual Word based Neural Tree for Interpretable Recognition of Images Full article
| Conference |
2nd International Conference “Problems of Informatics, Electronics and Radio Engineering 11-13 Nov 2022 , Новосибирск |
||||
|---|---|---|---|---|---|
| Source | 2022 IEEE International Multi-Conference on Engineering, Computer and Information Sciences (SIBIRCON) Compilation, IEEE. 2022. 6 c. ISBN 9781665464802. |
||||
| Output data | Year: 2023, Pages: 1830-1835 Pages count : 6 DOI: 10.1109/sibircon56155.2022.10017004 | ||||
| Tags | bag of visual words, computer tomography, convolutional network, decision tree, interpretability | ||||
| Authors |
|
||||
| Affiliations |
|
Funding (2)
| 1 | Sobolev Institute of Mathematics | FWNF-2022-0015 |
| 2 | Russian Foundation for Basic Research | 19-29-01175 |
Abstract:
It is necessary to have an explanation of the model prediction to increase confidence in the decision making in a broad range of image recognition tasks, especially medical image recognition.In this paper, we proposed a new method of interpretable image recognition. The basic idea was to use a combination of convolutional neural network, similarity based decision tree, and a trainable bag of visual words. During recognition, the model compared parts of the image with trained templates and made a decision based on the similarity between them. The recognition process was presented as a sequence of logical decision rules which can be easily understood by specialists in the applied area. This technique is similar to the human way of visual recognition. Testing on two datasets showed a competitive recognition quality of the proposed method, compared to a classical convolutional network ResNet50. At the same time, the method provided a possibility of interpreting the prediction.
Cite:
Kozinets R.
, Berikov V.
Visual Word based Neural Tree for Interpretable Recognition of Images
In compilation 2022 IEEE International Multi-Conference on Engineering, Computer and Information Sciences (SIBIRCON). – IEEE., 2023. – C.1830-1835. – ISBN 9781665464802. DOI: 10.1109/sibircon56155.2022.10017004 Scopus OpenAlex
Visual Word based Neural Tree for Interpretable Recognition of Images
In compilation 2022 IEEE International Multi-Conference on Engineering, Computer and Information Sciences (SIBIRCON). – IEEE., 2023. – C.1830-1835. – ISBN 9781665464802. DOI: 10.1109/sibircon56155.2022.10017004 Scopus OpenAlex
Dates:
| Accepted: | Nov 11, 2022 |
| Published print: | Jan 26, 2023 |
| Published online: | Jan 26, 2023 |
Identifiers:
| Scopus: | 2-s2.0-85147505671 |
| OpenAlex: | W4317826546 |
Citing:
Пока нет цитирований