Domain Adaptation and Active Learning for Fine-Grained Recognition in the Field of Biodiversity

by   Bernd Gruner, et al.

Deep-learning methods offer unsurpassed recognition performance in a wide range of domains, including fine-grained recognition tasks. However, in most problem areas there are insufficient annotated training samples. Therefore, the topic of transfer learning respectively domain adaptation is particularly important. In this work, we investigate to what extent unsupervised domain adaptation can be used for fine-grained recognition in a biodiversity context to learn a real-world classifier based on idealized training data, e.g. preserved butterflies and plants. Moreover, we investigate the influence of different normalization layers, such as Group Normalization in combination with Weight Standardization, on the classifier. We discovered that domain adaptation works very well for fine-grained recognition and that the normalization methods have a great influence on the results. Using domain adaptation and Transferable Normalization, the accuracy of the classifier could be increased by up to 12.35 combined with an active learning component to improve the results. We compare different active learning strategies with each other. Surprisingly, we found that more sophisticated strategies provide better results than the random selection baseline for only one of the two datasets. In this case, the distance and diversity strategy performed best. Finally, we present a problem analysis of the datasets.


page 4

page 5

page 6

page 11

page 12


Fine-grained Recognition in the Wild: A Multi-Task Domain Adaptation Approach

While fine-grained object recognition is an important problem in compute...

Active Adversarial Domain Adaptation

We propose an active learning approach for transferring representations ...

Fine-grained Knowledge Fusion for Sequence Labeling Domain Adaptation

In sequence labeling, previous domain adaptation methods focus on the ad...

Divide and Adapt: Active Domain Adaptation via Customized Learning

Active domain adaptation (ADA) aims to improve the model adaptation perf...

Unsupervised Domain Adaptation Learning for Hierarchical Infant Pose Recognition with Synthetic Data

The Alberta Infant Motor Scale (AIMS) is a well-known assessment scheme ...

Adaptive Ensembling: Unsupervised Domain Adaptation for Political Document Analysis

Insightful findings in political science often require researchers to an...

Identifying Products in Online Cybercrime Marketplaces: A Dataset for Fine-grained Domain Adaptation

One weakness of machine-learned NLP models is that they typically perfor...

Please sign up or login with your details

Forgot password? Click here to reset