SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1807.09200 · 2018

Self-Paced Learning with Adaptive Deep Visual Embeddings

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1807.09200")
get_code_for_paper("1807.09200")
have("1807.09200")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1807.09200.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1807.09200.svg)](https://syntology.ai/paper/1807.09200)

Connect an agent — have() is free.