CamoFA: A Learnable Fourier-based Augmentation for Camouflage Segmentation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Le, Minh-Quan, Tran, Minh-Triet, Le, Trung-Nghia, Nguyen, Tam V., Do, Thanh-Toan
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929610846896128
author Le, Minh-Quan
Tran, Minh-Triet
Le, Trung-Nghia
Nguyen, Tam V.
Do, Thanh-Toan
author_facet Le, Minh-Quan
Tran, Minh-Triet
Le, Trung-Nghia
Nguyen, Tam V.
Do, Thanh-Toan
contents Camouflaged object detection (COD) and camouflaged instance segmentation (CIS) aim to recognize and segment objects that are blended into their surroundings, respectively. While several deep neural network models have been proposed to tackle those tasks, augmentation methods for COD and CIS have not been thoroughly explored. Augmentation strategies can help improve models' performance by increasing the size and diversity of the training data and exposing the model to a wider range of variations in the data. Besides, we aim to automatically learn transformations that help to reveal the underlying structure of camouflaged objects and allow the model to learn to better identify and segment camouflaged objects. To achieve this, we propose a learnable augmentation method in the frequency domain for COD and CIS via the Fourier transform approach, dubbed CamoFA. Our method leverages a conditional generative adversarial network and cross-attention mechanism to generate a reference image and an adaptive hybrid swapping with parameters to mix the low-frequency component of the reference image and the high-frequency component of the input image. This approach aims to make camouflaged objects more visible for detection and segmentation models. Without bells and whistles, our proposed augmentation method boosts the performance of camouflaged object detectors and instance segmenters by large margins.
format Preprint
id arxiv_https___arxiv_org_abs_2308_15660
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle CamoFA: A Learnable Fourier-based Augmentation for Camouflage Segmentation
Le, Minh-Quan
Tran, Minh-Triet
Le, Trung-Nghia
Nguyen, Tam V.
Do, Thanh-Toan
Computer Vision and Pattern Recognition
Camouflaged object detection (COD) and camouflaged instance segmentation (CIS) aim to recognize and segment objects that are blended into their surroundings, respectively. While several deep neural network models have been proposed to tackle those tasks, augmentation methods for COD and CIS have not been thoroughly explored. Augmentation strategies can help improve models' performance by increasing the size and diversity of the training data and exposing the model to a wider range of variations in the data. Besides, we aim to automatically learn transformations that help to reveal the underlying structure of camouflaged objects and allow the model to learn to better identify and segment camouflaged objects. To achieve this, we propose a learnable augmentation method in the frequency domain for COD and CIS via the Fourier transform approach, dubbed CamoFA. Our method leverages a conditional generative adversarial network and cross-attention mechanism to generate a reference image and an adaptive hybrid swapping with parameters to mix the low-frequency component of the reference image and the high-frequency component of the input image. This approach aims to make camouflaged objects more visible for detection and segmentation models. Without bells and whistles, our proposed augmentation method boosts the performance of camouflaged object detectors and instance segmenters by large margins.
title CamoFA: A Learnable Fourier-based Augmentation for Camouflage Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2308.15660