Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Domain Generalization for Object Recognition with Multi-task Autoencoders

About

The problem of domain generalization is to take knowledge acquired from a number of related domains where training data is available, and to then successfully apply it to previously unseen domains. We propose a new feature learning algorithm, Multi-Task Autoencoder (MTAE), that provides good generalization performance for cross-domain object recognition. Our algorithm extends the standard denoising autoencoder framework by substituting artificially induced corruption with naturally occurring inter-domain variability in the appearance of objects. Instead of reconstructing images from noisy versions, MTAE learns to transform the original image into analogs in multiple related domains. It thereby learns features that are robust to variations across domains. The learnt features are then used as inputs to a classifier. We evaluated the performance of the algorithm on benchmark image recognition datasets, where the task is to learn features from multiple datasets and to then predict the image label from unseen datasets. We found that (denoising) MTAE outperforms alternative autoencoder-based models as well as the current state-of-the-art algorithms for domain generalization.

Muhammad Ghifary, W. Bastiaan Kleijn, Mengjie Zhang, David Balduzzi• 2015

Related benchmarks

TaskDatasetResultRank
Image ClassificationOffice-31
Average Accuracy79
261
Image ClassificationPACS (test)
Average Accuracy64.45
254
Image ClassificationPACS
Overall Average Accuracy64.5
230
Domain GeneralizationPACS (test)
Average Accuracy51.19
225
Domain GeneralizationPACS
Accuracy (Art)60.3
221
Multi-class classificationVLCS
Acc (Caltech)90.71
139
object recognitionPACS (leave-one-domain-out)
Acc (Art painting)60.27
112
Image ClassificationPACS v1 (test)
Average Accuracy64.5
92
Image ClassificationOffice-10 + Caltech-10
Average Accuracy86.28
77
Multi-class classificationPACS (test)
Accuracy (Art Painting)60.27
76
Showing 10 of 39 rows

Other info

Follow for update