A Streamlined Attention Mechanism for Image Classification and Fine-Grained Visual Recognition
In the recent advancements attention mechanism in deep learning had played a vital role in proving better results in tasks under computer vision. There exists multiple kinds of works under attention mechanism which includes under image classification, fine-grained visual recognition, image captionin...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Brno University of Technology
2021-12-01
|
| Series: | Mendel |
| Subjects: | |
| Online Access: | http://46.28.109.63/index.php/mendel/article/view/159 |
| _version_ | 1818890076842622976 |
|---|---|
| author | Dakshayani Himabindu D Praveen Kumar S |
| author_facet | Dakshayani Himabindu D Praveen Kumar S |
| author_sort | Dakshayani Himabindu D |
| collection | DOAJ |
| description | In the recent advancements attention mechanism in deep learning had played a
vital role in proving better results in tasks under computer vision. There exists multiple
kinds of works under attention mechanism which includes under image classification,
fine-grained visual recognition, image captioning, video captioning, object
detection and recognition tasks. Global and local attention are the two attention
based mechanisms which helps in interpreting the attentive partial. Considering
this criteria, there exists channel and spatial attention where in channel attention
considers the most attentive channel among the produced block of channels and
spatial attention considers which region among the space needs to be focused on.
We have proposed a streamlined attention block module which helps in enhancing
the feature based learning with less number of additional layers i.e., a GAP layer
followed by a linear layer with an incorporation of second order pooling(GSoP)
after every layer in the utilized encoder. This mechanism has produced better
range dependencies by the conducted experimentation. We have experimented
our model on CIFAR-10, CIFAR-100 and FGVC-Aircrafts datasets considering finegrained
visual recognition. We were successful in achieving state-of-the-result for
FGVC-Aircrafts with an accuracy of 97%. |
| first_indexed | 2024-12-19T17:19:10Z |
| format | Article |
| id | doaj.art-960abea1ee3b49c9bdf23a1bf95feb16 |
| institution | Directory Open Access Journal |
| issn | 1803-3814 2571-3701 |
| language | English |
| last_indexed | 2024-12-19T17:19:10Z |
| publishDate | 2021-12-01 |
| publisher | Brno University of Technology |
| record_format | Article |
| series | Mendel |
| spelling | doaj.art-960abea1ee3b49c9bdf23a1bf95feb162022-12-21T20:12:43ZengBrno University of TechnologyMendel1803-38142571-37012021-12-01272A Streamlined Attention Mechanism for Image Classification and Fine-Grained Visual RecognitionDakshayani Himabindu D0Praveen Kumar S1Department of CSE, GIT, GITAM UniversityDepartment of CSE, GIT, GITAM UniversityIn the recent advancements attention mechanism in deep learning had played a vital role in proving better results in tasks under computer vision. There exists multiple kinds of works under attention mechanism which includes under image classification, fine-grained visual recognition, image captioning, video captioning, object detection and recognition tasks. Global and local attention are the two attention based mechanisms which helps in interpreting the attentive partial. Considering this criteria, there exists channel and spatial attention where in channel attention considers the most attentive channel among the produced block of channels and spatial attention considers which region among the space needs to be focused on. We have proposed a streamlined attention block module which helps in enhancing the feature based learning with less number of additional layers i.e., a GAP layer followed by a linear layer with an incorporation of second order pooling(GSoP) after every layer in the utilized encoder. This mechanism has produced better range dependencies by the conducted experimentation. We have experimented our model on CIFAR-10, CIFAR-100 and FGVC-Aircrafts datasets considering finegrained visual recognition. We were successful in achieving state-of-the-result for FGVC-Aircrafts with an accuracy of 97%.http://46.28.109.63/index.php/mendel/article/view/159Visual attention, spatial attention, channel attention, fine-grained visual recognition, image classification, deep learning. |
| spellingShingle | Dakshayani Himabindu D Praveen Kumar S A Streamlined Attention Mechanism for Image Classification and Fine-Grained Visual Recognition Mendel Visual attention, spatial attention, channel attention, fine-grained visual recognition, image classification, deep learning. |
| title | A Streamlined Attention Mechanism for Image Classification and Fine-Grained Visual Recognition |
| title_full | A Streamlined Attention Mechanism for Image Classification and Fine-Grained Visual Recognition |
| title_fullStr | A Streamlined Attention Mechanism for Image Classification and Fine-Grained Visual Recognition |
| title_full_unstemmed | A Streamlined Attention Mechanism for Image Classification and Fine-Grained Visual Recognition |
| title_short | A Streamlined Attention Mechanism for Image Classification and Fine-Grained Visual Recognition |
| title_sort | streamlined attention mechanism for image classification and fine grained visual recognition |
| topic | Visual attention, spatial attention, channel attention, fine-grained visual recognition, image classification, deep learning. |
| url | http://46.28.109.63/index.php/mendel/article/view/159 |
| work_keys_str_mv | AT dakshayanihimabindud astreamlinedattentionmechanismforimageclassificationandfinegrainedvisualrecognition AT praveenkumars astreamlinedattentionmechanismforimageclassificationandfinegrainedvisualrecognition AT dakshayanihimabindud streamlinedattentionmechanismforimageclassificationandfinegrainedvisualrecognition AT praveenkumars streamlinedattentionmechanismforimageclassificationandfinegrainedvisualrecognition |