dc.contributor.author | Sun, Danyang | |
dc.contributor.author | Dornaika, Fadi | |
dc.contributor.author | Hoang, Vinh Truong | |
dc.contributor.author | Barrena Orueechebarria, Nagore | |
dc.date | 2026-09-27 | |
dc.date.accessioned | 2024-12-30T19:34:26Z | |
dc.date.available | 2024-12-30T19:34:26Z | |
dc.date.issued | 2024-09-27 | |
dc.identifier.citation | 2024 IEEE International Conference on Image Processing (ICIP) : 624-630 (2024) | es_ES |
dc.identifier.isbn | 979-8-3503-4939-9 | |
dc.identifier.uri | http://hdl.handle.net/10810/71075 | |
dc.description.abstract | Data augmentation can mitigate overfitting problems in data
exploration without increasing the size of the model. Existing
cutmix-based data augmentation has been proven to signifi-
cantly enhance deep learning performance. However, many
existing methods overlook the discriminative local context of
the image and rely on ad hoc regions consisting of square or
rectangular local regions, resulting in the loss of complete
semantic object parts. In this work, we propose a superpixel-
wise local-context-aware efficient image mixing approach
for data augmentation, aiming to overcome the limitations
previously mentioned. Our approach only requires one for-
ward propagation using a superpixel attention-based label
mixing with lower computational complexity. The model is
trained using a combination of a global classification of the
mixed (augmented) image loss, a superpixel-wise weighted
local classification loss, and a superpixel-based weighted
contrastive learning loss. The last two losses are based on
the superpixel-aware attentive embeddings. Thus, the result-
ing deep encoder can learn both local and global features of
the images, capturing object-part local context information.
Experiments on diverse benchmarks, such as ImageNet-1K
and CUB-200-2011, indicate that the proposed method out-
performs many augmentation methods for visual recognition.
We have not only demonstrated its effectiveness on CNN
models, but also on transformer models. | es_ES |
dc.description.sponsorship | University of the Basque Country UPV/EHU (Spain), IKERBASQUE Basque Foundation for Science (Spain), Ho Chi Minh City open University (Vietnam) | es_ES |
dc.language.iso | eng | es_ES |
dc.publisher | IEEE | es_ES |
dc.rights | info:eu-repo/semantics/embargoedAccess | es_ES |
dc.subject | Data augmentation, Local context, Super- pixel, Deep visual recognition | es_ES |
dc.subject | data augmentation | es_ES |
dc.subject | local context | es_ES |
dc.subject | super- pixel | es_ES |
dc.subject | deep visual recognition | es_ES |
dc.title | Superpixel Mixing: A Data Augmentation Technique For Robust Deep Visual Recognition Models | es_ES |
dc.type | info:eu-repo/semantics/conferenceObject | es_ES |
dc.rights.holder | (c) 2024 IEEE | es_ES |
dc.relation.publisherversion | https://doi.org/10.1109/ICIP51287.2024.10648078 | es_ES |
dc.identifier.doi | 10.1109/ICIP51287.2024.10648078 | |
dc.departamentoes | Ciencia de la computación e inteligencia artificial | es_ES |
dc.departamentoeu | Konputazio zientziak eta adimen artifiziala | es_ES |