HELA-VFA: a hellinger distance-attention-based feature aggregation network for few-shot classification
Enabling effective learning using only a few presented examples is a crucial but difficult computer vision objective. Few-shot learning have been proposed to address the challenges, and more recently variational inference-based approaches are incorporated to enhance few-shot classification performa...
Saved in:
Main Authors: | , , , , |
---|---|
Other Authors: | |
Format: | Conference or Workshop Item |
Language: | English |
Published: |
2024
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/173508 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-173508 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1735082024-04-16T15:31:07Z HELA-VFA: a hellinger distance-attention-based feature aggregation network for few-shot classification Lee, Gao Yu Dam, Tanmoy Poenar, Daniel Puiu Duong, Vu N. Ferdaus, Md Meftahul School of Mechanical and Aerospace Engineering School of Electrical and Electronic Engineering 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Air Traffic Management Research Institute Computer and Information Science Feature aggregation Few-shot learning Hellinger distance Image classification Enabling effective learning using only a few presented examples is a crucial but difficult computer vision objective. Few-shot learning have been proposed to address the challenges, and more recently variational inference-based approaches are incorporated to enhance few-shot classification performances. However, the current dominant strategy utilized the Kullback-Leibler (KL) divergences to find the log marginal likelihood of the target class distribution, while neglecting the possibility of other probabilistic comparative measures, as well as the possibility of incorporating attention in the feature extraction stages, which can increase the effectiveness of the few-shot model. To this end, we proposed the HELlinger-Attention Variational Feature Aggregation network (HELA-VFA), which utilized the Hellinger distance along with attention in the encoder to fulfill the aforementioned gaps. We show that our approach enables the derivation of an alternate form of the lower bound commonly presented in prior works, thus making the variational optimization feasible and be trained on the same footing in a given setting. Extensive experiments performed on four benchmarked few-shot classification datasets demonstrated the feasibility and superiority of our approach relative to the State-Of-The-Arts (SOTAs) approaches. Civil Aviation Authority of Singapore (CAAS) Submitted/Accepted version This research/project is supported by the Civil Aviation Authority of Singapore and NTU under their collaboration in the Air Traffic Management Research Institute. 2024-04-12T06:01:41Z 2024-04-12T06:01:41Z 2024 Conference Paper Lee, G. Y., Dam, T., Poenar, D. P., Duong, V. N. & Ferdaus, M. M. (2024). HELA-VFA: a hellinger distance-attention-based feature aggregation network for few-shot classification. 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2162-2172. https://dx.doi.org/10.1109/WACV57701.2024.00217 https://hdl.handle.net/10356/173508 10.1109/WACV57701.2024.00217 2162 2172 en © 2024 IEEE. All rights reserved. This article may be downloaded for personal use only. Any other use requires prior permission of the copyright holder. The Version of Record is available online at http://doi.org/10.1109/WACV57701.2024.00217. application/pdf |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Computer and Information Science Feature aggregation Few-shot learning Hellinger distance Image classification |
spellingShingle |
Computer and Information Science Feature aggregation Few-shot learning Hellinger distance Image classification Lee, Gao Yu Dam, Tanmoy Poenar, Daniel Puiu Duong, Vu N. Ferdaus, Md Meftahul HELA-VFA: a hellinger distance-attention-based feature aggregation network for few-shot classification |
description |
Enabling effective learning using only a few presented
examples is a crucial but difficult computer vision objective. Few-shot learning have been proposed to address the challenges, and more recently variational inference-based approaches are incorporated to enhance few-shot classification performances. However, the current dominant strategy utilized the Kullback-Leibler (KL) divergences to find the log marginal likelihood of the target class distribution, while neglecting the possibility of other probabilistic comparative measures, as well as the possibility of incorporating attention in the feature extraction stages, which can increase the effectiveness of the few-shot model. To this end, we proposed the HELlinger-Attention Variational Feature Aggregation network (HELA-VFA), which utilized the Hellinger distance along with attention in the encoder to fulfill the aforementioned gaps. We show that our approach enables the derivation of an alternate form of the lower bound commonly presented in prior works, thus making the variational optimization feasible and be trained on the same footing in a given setting. Extensive experiments performed on four benchmarked few-shot classification datasets demonstrated the feasibility and superiority of our approach relative to the State-Of-The-Arts (SOTAs) approaches. |
author2 |
School of Mechanical and Aerospace Engineering |
author_facet |
School of Mechanical and Aerospace Engineering Lee, Gao Yu Dam, Tanmoy Poenar, Daniel Puiu Duong, Vu N. Ferdaus, Md Meftahul |
format |
Conference or Workshop Item |
author |
Lee, Gao Yu Dam, Tanmoy Poenar, Daniel Puiu Duong, Vu N. Ferdaus, Md Meftahul |
author_sort |
Lee, Gao Yu |
title |
HELA-VFA: a hellinger distance-attention-based feature aggregation network for few-shot classification |
title_short |
HELA-VFA: a hellinger distance-attention-based feature aggregation network for few-shot classification |
title_full |
HELA-VFA: a hellinger distance-attention-based feature aggregation network for few-shot classification |
title_fullStr |
HELA-VFA: a hellinger distance-attention-based feature aggregation network for few-shot classification |
title_full_unstemmed |
HELA-VFA: a hellinger distance-attention-based feature aggregation network for few-shot classification |
title_sort |
hela-vfa: a hellinger distance-attention-based feature aggregation network for few-shot classification |
publishDate |
2024 |
url |
https://hdl.handle.net/10356/173508 |
_version_ |
1806059759800942592 |