Generalized Local Attention Pooling for Deep Metric Learning
| Autor: | David Varas, Elisenda Bou-Balust, Carlos Roig, Issey Masuda, Juan Carlos Riveiro |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Artificial neural network
Computer science business.industry Dimensionality reduction Feature extraction Pooling Pattern recognition 02 engineering and technology 010501 environmental sciences 01 natural sciences Feature (computer vision) Metric (mathematics) 0202 electrical engineering electronic engineering information engineering Embedding 020201 artificial intelligence & image processing Artificial intelligence business Image retrieval 0105 earth and related environmental sciences |
| Zdroj: | ICPR |
| DOI: | 10.1109/icpr48806.2021.9412479 |
| Popis: | Deep metric learning has been key to recent advances in face verification and image retrieval amongst others. These systems consist on a feature extraction block (extracts feature maps from images) followed by a spatial dimensionality reduction block (generates compact image representations from the feature maps) and an embedding generation module (projects the image representation to the embedding space). While research on deep metric learning has focused on improving the losses for the embedding generation module, the dimensionality reduction block has been overlooked. In this work, we propose a novel method to generate compact image representations which uses local spatial information through an attention mechanism, named Generalized Local Attention Pooling (GLAP). This method, instead of being placed at the end layer of the backbone, is connected at an intermediate level, resulting in lower memory requirements. We assess the performance of the aforementioned method by comparing it with multiple dimensionality reduction techniques, demonstrating the importance of using attention weights to generate robust compact image representations. Moreover, we compare the performance of multiple state-of-the-art losses using the standard deep metric learning system against the same experiment with our GLAP. Experiments showcase that the proposed Generalized Local Attention Pooling mechanism outperforms other pooling methods when compared with current state-of-the-art losses for deep metric learning. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|