# Self-Paced Learning with Adaptive Deep Visual Embeddings

Source: [Self-Paced Learning with Adaptive Deep Visual Embeddings](<https://www.sota2.com/research/paper/68fa649a1e209131cea0578c>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:56:36.364Z

Authors: Vithursan Thangarasa, Graham W. Taylor

Published: 2018-07-24T16:01:00.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1807.09200>)

[PDF](<https://arxiv.org/pdf/1807.09200.pdf>)
