Few-shot Adaptive Object Detection with Cross-Domain CutMix
- URL: http://arxiv.org/abs/2208.14586v1
- Date: Wed, 31 Aug 2022 01:26:10 GMT
- Title: Few-shot Adaptive Object Detection with Cross-Domain CutMix
- Authors: Yuzuru Nakamura, Yasunori Ishii, Yuki Maruyama, Takayoshi Yamashita
- Abstract summary: In object detection, data amount and cost are a trade-off, and collecting a large amount of data in a specific domain is labor intensive.
We propose a data synthesis method that can solve the large domain gap problem.
The proposed method achieves higher accuracy than conventional methods in a very different domain problem setting.
- Score: 5.432990262699911
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: In object detection, data amount and cost are a trade-off, and collecting a
large amount of data in a specific domain is labor intensive. Therefore,
existing large-scale datasets are used for pre-training. However, conventional
transfer learning and domain adaptation cannot bridge the domain gap when the
target domain differs significantly from the source domain. We propose a data
synthesis method that can solve the large domain gap problem. In this method, a
part of the target image is pasted onto the source image, and the position of
the pasted region is aligned by utilizing the information of the object
bounding box. In addition, we introduce adversarial learning to discriminate
whether the original or the pasted regions. The proposed method trains on a
large number of source images and a few target domain images. The proposed
method achieves higher accuracy than conventional methods in a very different
domain problem setting, where RGB images are the source domain, and thermal
infrared images are the target domain. Similarly, the proposed method achieves
higher accuracy in the cases of simulation images to real images.
Related papers
- Source-free Domain Adaptive Object Detection in Remote Sensing Images [11.19538606490404]
We propose a source-free object detection (SFOD) setting for RS images.
It aims to perform target domain adaptation using only the source pre-trained model.
Our method does not require access to source domain RS images.
arXiv Detail & Related papers (2024-01-31T15:32:44Z) - DARC: Distribution-Aware Re-Coloring Model for Generalizable Nucleus
Segmentation [68.43628183890007]
We argue that domain gaps can also be caused by different foreground (nucleus)-background ratios.
First, we introduce a re-coloring method that relieves dramatic image color variations between different domains.
Second, we propose a new instance normalization method that is robust to the variation in the foreground-background ratios.
arXiv Detail & Related papers (2023-09-01T01:01:13Z) - Domain Agnostic Image-to-image Translation using Low-Resolution
Conditioning [6.470760375991825]
We propose a domain-agnostic i2i method for fine-grained problems, where the domains are related.
We present a novel approach that relies on training the generative model to produce images that both share distinctive information of the associated source image.
We validate our method on the CelebA-HQ and AFHQ datasets by demonstrating improvements in terms of visual quality.
arXiv Detail & Related papers (2023-05-08T19:58:49Z) - Ranking Distance Calibration for Cross-Domain Few-Shot Learning [91.22458739205766]
Recent progress in few-shot learning promotes a more realistic cross-domain setting.
Due to the domain gap and disjoint label spaces between source and target datasets, their shared knowledge is extremely limited.
We employ a re-ranking process for calibrating a target distance matrix by discovering the reciprocal k-nearest neighbours within the task.
arXiv Detail & Related papers (2021-12-01T03:36:58Z) - Disentangled Unsupervised Image Translation via Restricted Information
Flow [61.44666983942965]
Many state-of-art methods hard-code the desired shared-vs-specific split into their architecture.
We propose a new method that does not rely on inductive architectural biases.
We show that the proposed method achieves consistently high manipulation accuracy across two synthetic and one natural dataset.
arXiv Detail & Related papers (2021-11-26T00:27:54Z) - Multilevel Knowledge Transfer for Cross-Domain Object Detection [26.105283273950942]
Domain shift is a well known problem where a model trained on a particular domain (source) does not perform well when exposed to samples from a different domain (target)
In this work, we address the domain shift problem for the object detection task.
Our approach relies on gradually removing the domain shift between the source and the target domains.
arXiv Detail & Related papers (2021-08-02T15:24:40Z) - Few-shot Image Generation via Cross-domain Correspondence [98.2263458153041]
Training generative models, such as GANs, on a target domain containing limited examples can easily result in overfitting.
In this work, we seek to utilize a large source domain for pretraining and transfer the diversity information from source to target.
To further reduce overfitting, we present an anchor-based strategy to encourage different levels of realism over different regions in the latent space.
arXiv Detail & Related papers (2021-04-13T17:59:35Z) - Six-channel Image Representation for Cross-domain Object Detection [17.854940064699985]
Deep learning models are data-driven and the excellent performance is highly dependent on the abundant and diverse datasets.
Some image-to-image translation techniques are employed to generate some fake data of some specific scenes to train the models.
We propose to inspire the original 3-channel images and their corresponding GAN-generated fake images to form 6-channel representations of the dataset.
arXiv Detail & Related papers (2021-01-03T04:50:03Z) - Discriminative Cross-Domain Feature Learning for Partial Domain
Adaptation [70.45936509510528]
Partial domain adaptation aims to adapt knowledge from a larger and more diverse source domain to a smaller target domain with less number of classes.
Recent practice on domain adaptation manages to extract effective features by incorporating the pseudo labels for the target domain.
It is essential to align target data with only a small set of source data.
arXiv Detail & Related papers (2020-08-26T03:18:53Z) - TriGAN: Image-to-Image Translation for Multi-Source Domain Adaptation [82.52514546441247]
We propose the first approach for Multi-Source Domain Adaptation (MSDA) based on Generative Adversarial Networks.
Our method is inspired by the observation that the appearance of a given image depends on three factors: the domain, the style and the content.
We test our approach using common MSDA benchmarks, showing that it outperforms state-of-the-art methods.
arXiv Detail & Related papers (2020-04-19T05:07:22Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.