Fusing Adaptive Meta Feature Weighting for Few-shot Object Detection

Zhou Peng, Liu Anzhan
Proceedings of 2024 International Conference on Machine Learning and Intelligent Computing, PMLR 245:129-137, 2024.

Abstract

Few-shot object detection models often lack the perceptual ability to detect the target objects and fine-tuning the model on base class images to quickly adapt to new tasks can lead to feature shift issues. We propose an Adaptive Meta-Feature Weighting (AMFW-YOLO) object detection model for solving these problems. This model introduces an attention mechanism based on spatial and channel-wise squeeze-and-excitation (scSE) blocks, which helps the model focus on the regions of interest in the target samples and suppresses interference from background regions. Additionally, to compensate for the feature shift caused during the fine-tuning stage, we design an Adaptive Meta-Feature Weighting module (AMFW), This module embeds positional information into spatial features, captures long-range dependencies along two directions, and adaptively compensates for the weights of deep global features, effectively improving the accuracy of the model.

Cite this Paper

BibTeX
@InProceedings{pmlr-v245-peng24a, title = {Fusing Adaptive Meta Feature Weighting for Few-shot Object Detection}, author = {Peng, Zhou and Anzhan, Liu}, booktitle = {Proceedings of 2024 International Conference on Machine Learning and Intelligent Computing}, pages = {129--137}, year = {2024}, editor = {Nianyin, Zeng and Pachori, Ram Bilas}, volume = {245}, series = {Proceedings of Machine Learning Research}, month = {26--28 Apr}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v245/main/assets/peng24a/peng24a.pdf}, url = {https://proceedings.mlr.press/v245/peng24a.html}, abstract = {Few-shot object detection models often lack the perceptual ability to detect the target objects and fine-tuning the model on base class images to quickly adapt to new tasks can lead to feature shift issues. We propose an Adaptive Meta-Feature Weighting (AMFW-YOLO) object detection model for solving these problems. This model introduces an attention mechanism based on spatial and channel-wise squeeze-and-excitation (scSE) blocks, which helps the model focus on the regions of interest in the target samples and suppresses interference from background regions. Additionally, to compensate for the feature shift caused during the fine-tuning stage, we design an Adaptive Meta-Feature Weighting module (AMFW), This module embeds positional information into spatial features, captures long-range dependencies along two directions, and adaptively compensates for the weights of deep global features, effectively improving the accuracy of the model. } }
Endnote
%0 Conference Paper %T Fusing Adaptive Meta Feature Weighting for Few-shot Object Detection %A Zhou Peng %A Liu Anzhan %B Proceedings of 2024 International Conference on Machine Learning and Intelligent Computing %C Proceedings of Machine Learning Research %D 2024 %E Zeng Nianyin %E Ram Bilas Pachori %F pmlr-v245-peng24a %I PMLR %P 129--137 %U https://proceedings.mlr.press/v245/peng24a.html %V 245 %X Few-shot object detection models often lack the perceptual ability to detect the target objects and fine-tuning the model on base class images to quickly adapt to new tasks can lead to feature shift issues. We propose an Adaptive Meta-Feature Weighting (AMFW-YOLO) object detection model for solving these problems. This model introduces an attention mechanism based on spatial and channel-wise squeeze-and-excitation (scSE) blocks, which helps the model focus on the regions of interest in the target samples and suppresses interference from background regions. Additionally, to compensate for the feature shift caused during the fine-tuning stage, we design an Adaptive Meta-Feature Weighting module (AMFW), This module embeds positional information into spatial features, captures long-range dependencies along two directions, and adaptively compensates for the weights of deep global features, effectively improving the accuracy of the model.
APA
Peng, Z. & Anzhan, L.. (2024). Fusing Adaptive Meta Feature Weighting for Few-shot Object Detection. Proceedings of 2024 International Conference on Machine Learning and Intelligent Computing, in Proceedings of Machine Learning Research 245:129-137 Available from https://proceedings.mlr.press/v245/peng24a.html.

Related Material