Multi-granularity sequence generation for hierarchical image classification
Abstract Hierarchical multi-granularity image classification is a challenging task that aims to tag each given image with multiple granularity labels simultaneously. Existing methods tend to overlook that different image regions contribute differently to label prediction at different granularities,...
| Main Authors: | , |
|---|---|
| 格式: | Article |
| 語言: | English |
| 出版: |
SpringerOpen
2024-01-01
|
| 叢編: | Computational Visual Media |
| 主題: | |
| 在線閱讀: | https://doi.org/10.1007/s41095-022-0332-2 |
| _version_ | 1827388253154574336 |
|---|---|
| author | Xinda Liu Lili Wang |
| author_facet | Xinda Liu Lili Wang |
| author_sort | Xinda Liu |
| collection | DOAJ |
| description | Abstract Hierarchical multi-granularity image classification is a challenging task that aims to tag each given image with multiple granularity labels simultaneously. Existing methods tend to overlook that different image regions contribute differently to label prediction at different granularities, and also insufficiently consider relationships between the hierarchical multi-granularity labels. We introduce a sequence-to-sequence mechanism to overcome these two problems and propose a multi-granularity sequence generation (MGSG) approach for the hierarchical multi-granularity image classification task. Specifically, we introduce a transformer architecture to encode the image into visual representation sequences. Next, we traverse the taxonomic tree and organize the multi-granularity labels into sequences, and vectorize them and add positional information. The proposed multi-granularity sequence generation method builds a decoder that takes visual representation sequences and semantic label embedding as inputs, and outputs the predicted multi-granularity label sequence. The decoder models dependencies and correlations between multi-granularity labels through a masked multi-head self-attention mechanism, and relates visual information to the semantic label information through a cross-modality attention mechanism. In this way, the proposed method preserves the relationships between labels at different granularity levels and takes into account the influence of different image regions on labels with different granularities. Evaluations on six public benchmarks qualitatively and quantitatively demonstrate the advantages of the proposed method. Our project is available at https://github.com/liuxindazz/mgsg . |
| first_indexed | 2024-03-08T16:15:01Z |
| format | Article |
| id | doaj.art-1f9ddbe7a6d34778be7b51a074acbfc8 |
| institution | Directory Open Access Journal |
| issn | 2096-0433 2096-0662 |
| language | English |
| last_indexed | 2024-03-08T16:15:01Z |
| publishDate | 2024-01-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Computational Visual Media |
| spelling | doaj.art-1f9ddbe7a6d34778be7b51a074acbfc82024-01-07T12:39:08ZengSpringerOpenComputational Visual Media2096-04332096-06622024-01-0110224326010.1007/s41095-022-0332-2Multi-granularity sequence generation for hierarchical image classificationXinda Liu0Lili Wang1State Key Laboratory of Virtual Reality Technology and Systems, Beihang UniversityState Key Laboratory of Virtual Reality Technology and Systems, Beihang UniversityAbstract Hierarchical multi-granularity image classification is a challenging task that aims to tag each given image with multiple granularity labels simultaneously. Existing methods tend to overlook that different image regions contribute differently to label prediction at different granularities, and also insufficiently consider relationships between the hierarchical multi-granularity labels. We introduce a sequence-to-sequence mechanism to overcome these two problems and propose a multi-granularity sequence generation (MGSG) approach for the hierarchical multi-granularity image classification task. Specifically, we introduce a transformer architecture to encode the image into visual representation sequences. Next, we traverse the taxonomic tree and organize the multi-granularity labels into sequences, and vectorize them and add positional information. The proposed multi-granularity sequence generation method builds a decoder that takes visual representation sequences and semantic label embedding as inputs, and outputs the predicted multi-granularity label sequence. The decoder models dependencies and correlations between multi-granularity labels through a masked multi-head self-attention mechanism, and relates visual information to the semantic label information through a cross-modality attention mechanism. In this way, the proposed method preserves the relationships between labels at different granularity levels and takes into account the influence of different image regions on labels with different granularities. Evaluations on six public benchmarks qualitatively and quantitatively demonstrate the advantages of the proposed method. Our project is available at https://github.com/liuxindazz/mgsg .https://doi.org/10.1007/s41095-022-0332-2hierarchical multi-granularity classificationvision and text transformersequence generationfine-grained image recognitioncross-modality attention |
| spellingShingle | Xinda Liu Lili Wang Multi-granularity sequence generation for hierarchical image classification Computational Visual Media hierarchical multi-granularity classification vision and text transformer sequence generation fine-grained image recognition cross-modality attention |
| title | Multi-granularity sequence generation for hierarchical image classification |
| title_full | Multi-granularity sequence generation for hierarchical image classification |
| title_fullStr | Multi-granularity sequence generation for hierarchical image classification |
| title_full_unstemmed | Multi-granularity sequence generation for hierarchical image classification |
| title_short | Multi-granularity sequence generation for hierarchical image classification |
| title_sort | multi granularity sequence generation for hierarchical image classification |
| topic | hierarchical multi-granularity classification vision and text transformer sequence generation fine-grained image recognition cross-modality attention |
| url | https://doi.org/10.1007/s41095-022-0332-2 |
| work_keys_str_mv | AT xindaliu multigranularitysequencegenerationforhierarchicalimageclassification AT liliwang multigranularitysequencegenerationforhierarchicalimageclassification |