TY - GEN
T1 - COFENET
T2 - 29th IEEE International Conference on Image Processing, ICIP 2022
AU - Wang, Bor Shiun
AU - Hsieh, Jun Wei
AU - Hsieh, Yi Kuan
AU - Chen, Ping Yang
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - It is challenging to classify patterns with small inter-class variations but large intra-class variations especially for textured objects with relatively small sizes and blurry boundaries. We propose the Co-Feature Network (COFENet), a novel deep learning network for fine-grained texture-based image classification. State-of-the-art (SoTA) methods on this mostly rely on feature concatenation by merging convolutional features into fully connected layers. Some existing work explored the variation between pair-wise features during learning, they only considered the relations in the feature channels, and did not explore the spatial or structural relations among the image regions where the features are extracted from. We propose to leverage such information among the features and their relative spatial layouts to capture richer pairwise, orientationwise, and distancewise relations among feature channels for end-to-end learning of intra-class and inter-class variations.
AB - It is challenging to classify patterns with small inter-class variations but large intra-class variations especially for textured objects with relatively small sizes and blurry boundaries. We propose the Co-Feature Network (COFENet), a novel deep learning network for fine-grained texture-based image classification. State-of-the-art (SoTA) methods on this mostly rely on feature concatenation by merging convolutional features into fully connected layers. Some existing work explored the variation between pair-wise features during learning, they only considered the relations in the feature channels, and did not explore the spatial or structural relations among the image regions where the features are extracted from. We propose to leverage such information among the features and their relative spatial layouts to capture richer pairwise, orientationwise, and distancewise relations among feature channels for end-to-end learning of intra-class and inter-class variations.
KW - Fine-grained classification
KW - Image classification
KW - medical image analysis
KW - Texture classification
UR - http://www.scopus.com/inward/record.url?scp=85146734348&partnerID=8YFLogxK
U2 - 10.1109/ICIP46576.2022.9897463
DO - 10.1109/ICIP46576.2022.9897463
M3 - Conference contribution
AN - SCOPUS:85146734348
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - 3928
EP - 3932
BT - 2022 IEEE International Conference on Image Processing, ICIP 2022 - Proceedings
PB - IEEE Computer Society
Y2 - 16 October 2022 through 19 October 2022
ER -