ALMN: Deep Embedding Learning with Geometrical Virtual Point Generating
This work addresses the problem of efficient discriminative feature learning for computer vision practitioners, offering an incremental improvement over existing methods.
The paper tackles the computational complexity and performance sensitivity of hard-class mining in deep embedding learning by proposing the Adaptive Large Margin N-Pair loss (ALMN) with a geometrical Virtual Point Generating method, achieving improved intraclass compactness and interclass separability on image retrieval and clustering datasets.
Deep embedding learning becomes more attractive for discriminative feature learning, but many methods still require hard-class mining, which is computationally complex and performance-sensitive. To this end, we propose Adaptive Large Margin N-Pair loss (ALMN) to address the aforementioned issues. Instead of exploring hard example-mining strategy, we introduce the concept of large margin constraint. This constraint aims at encouraging local-adaptive large angular decision margin among dissimilar samples in multimodal feature space so as to significantly encourage intraclass compactness and interclass separability. And it is mainly achieved by a simple yet novel geometrical Virtual Point Generating (VPG) method, which converts artificially setting a fixed margin into automatically generating a boundary training sample in feature space and is an open question. We demonstrate the effectiveness of our method on several popular datasets for image retrieval and clustering tasks.