Abstract | ||
---|---|---|
Selecting the most appropriate data examples to present a deep neural network (DNN) at different stages of training is an unsolved challenge. Though practitioners typically ignore this problem, a non-trivial data scheduling method may result in a significant improvement in both convergence and generalization performance. In this paper, we introduce Self-Paced Learning with Adaptive Deep Visual Embeddings (SPL-ADVisE), a novel end-to-end training protocol that unites self-paced learning (SPL) and deep metric learning (DML). We leverage the Magnet Loss to train an embedding convolutional neural network (CNN) to learn a salient representation space. The student CNN classifier dynamically selects similar instance-level training examples to form a mini-batch, where the easiness from the cross-entropy loss and the true diverseness of examples from the learned metric space serve as sample importance priors. To demonstrate the effectiveness of SPL-ADVisE, we use deep CNN architectures for the task of supervised image classification on several coarse- and fine-grained visual recognition datasets. Results show that, across all datasets, the proposed method converges faster and reaches a higher final accuracy than other SPL variants, particularly on fine-grained classes. |
Year | Venue | DocType |
---|---|---|
2018 | BMVC | Conference |
Volume | Citations | PageRank |
abs/1807.09200 | 0 | 0.34 |
References | Authors | |
0 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Vithursan Thangarasa | 1 | 0 | 0.34 |
Graham W. Taylor | 2 | 1523 | 127.22 |