Unsupervised Attention Regularization Based Domain Adaptation for Oracle Character Recognition
- URL: http://arxiv.org/abs/2409.15893v1
- Date: Tue, 24 Sep 2024 09:07:05 GMT
- Title: Unsupervised Attention Regularization Based Domain Adaptation for Oracle Character Recognition
- Authors: Mei Wang, Weihong Deng, Jiani Hu, Sen Su,
- Abstract summary: The study of oracle characters plays an important role in Chinese archaeology and philology.
The difficulty of collecting and annotating real-world scanned oracle characters hinders the development of oracle character recognition.
We develop a novel unsupervised domain adaptation (UDA) method to transfer recognition knowledge from labeled handprinted oracle characters to unlabeled scanned data.
- Score: 59.05212866862219
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: The study of oracle characters plays an important role in Chinese archaeology and philology. However, the difficulty of collecting and annotating real-world scanned oracle characters hinders the development of oracle character recognition. In this paper, we develop a novel unsupervised domain adaptation (UDA) method, i.e., unsupervised attention regularization net?work (UARN), to transfer recognition knowledge from labeled handprinted oracle characters to unlabeled scanned data. First, we experimentally prove that existing UDA methods are not always consistent with human priors and cannot achieve optimal performance on the target domain. For these oracle characters with flip-insensitivity and high inter-class similarity, model interpretations are not flip-consistent and class-separable. To tackle this challenge, we take into consideration visual perceptual plausibility when adapting. Specifically, our method enforces attention consistency between the original and flipped images to achieve the model robustness to flipping. Simultaneously, we constrain attention separability between the pseudo class and the most confusing class to improve the model discriminability. Extensive experiments demonstrate that UARN shows better interpretability and achieves state-of-the-art performance on Oracle-241 dataset, substantially outperforming the previously structure-texture separation network by 8.5%.
Related papers
- DPA: Dual Prototypes Alignment for Unsupervised Adaptation of Vision-Language Models [7.649900082537232]
This study introduces DPA, an unsupervised domain adaptation method for vision-textual models.
It introduces the concept of dual prototypes, acting as distinct classifiers, along with the convex combination of their outputs.
It ranks pseudo-labels to facilitate robust self-training, particularly during early training.
Experiments on 13 downstream vision tasks demonstrate that DPA significantly outperforms zero-shot CLIP and the state-of-the-art unsupervised adaptation baselines.
arXiv Detail & Related papers (2024-08-16T17:30:27Z) - Oracle Character Recognition using Unsupervised Discriminative
Consistency Network [65.64172835624206]
We propose a novel unsupervised domain adaptation method for oracle character recognition (OrCR)
We leverage pseudo-labeling to incorporate the semantic information into adaptation and constrain augmentation consistency.
Our approach achieves state-of-the-art result on Oracle-241 dataset and substantially outperforms the recently proposed structure-texture separation network by 15.1%.
arXiv Detail & Related papers (2023-12-11T02:52:27Z) - Enhancing Visual Perception in Novel Environments via Incremental Data
Augmentation Based on Style Transfer [2.516855334706386]
"unknown unknowns" challenge autonomous agent deployment in real-world scenarios.
Our approach enhances visual perception by leveraging the Variational Prototyping (VPE) to adeptly identify and handle novel inputs.
Our findings suggest the potential benefits of incorporating generative models for domain-specific augmentation strategies.
arXiv Detail & Related papers (2023-09-16T03:06:31Z) - Learning Objective-Specific Active Learning Strategies with Attentive
Neural Processes [72.75421975804132]
Learning Active Learning (LAL) suggests to learn the active learning strategy itself, allowing it to adapt to the given setting.
We propose a novel LAL method for classification that exploits symmetry and independence properties of the active learning problem.
Our approach is based on learning from a myopic oracle, which gives our model the ability to adapt to non-standard objectives.
arXiv Detail & Related papers (2023-09-11T14:16:37Z) - UIA-ViT: Unsupervised Inconsistency-Aware Method based on Vision
Transformer for Face Forgery Detection [52.91782218300844]
We propose a novel Unsupervised Inconsistency-Aware method based on Vision Transformer, called UIA-ViT.
Due to the self-attention mechanism, the attention map among patch embeddings naturally represents the consistency relation, making the vision Transformer suitable for the consistency representation learning.
arXiv Detail & Related papers (2022-10-23T15:24:47Z) - Cluster-level pseudo-labelling for source-free cross-domain facial
expression recognition [94.56304526014875]
We propose the first Source-Free Unsupervised Domain Adaptation (SFUDA) method for Facial Expression Recognition (FER)
Our method exploits self-supervised pretraining to learn good feature representations from the target data.
We validate the effectiveness of our method in four adaptation setups, proving that it consistently outperforms existing SFUDA methods when applied to FER.
arXiv Detail & Related papers (2022-10-11T08:24:50Z) - Unsupervised Structure-Texture Separation Network for Oracle Character
Recognition [70.29024469395608]
Oracle bone script is the earliest-known Chinese writing system of the Shang dynasty and is precious to archeology and philology.
We propose a structure-texture separation network (STSN), which is an end-to-end learning framework for joint disentanglement, transformation, adaptation and recognition.
arXiv Detail & Related papers (2022-05-13T10:27:02Z) - Feature Diversity Learning with Sample Dropout for Unsupervised Domain
Adaptive Person Re-identification [0.0]
This paper proposes a new approach to learn the feature representation with better generalization ability through limiting noisy pseudo labels.
We put forward a brand-new method referred as to Feature Diversity Learning (FDL) under the classic mutual-teaching architecture.
Experimental results show that our proposed FDL-SD achieves the state-of-the-art performance on multiple benchmark datasets.
arXiv Detail & Related papers (2022-01-25T10:10:48Z)
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.