Weakly Supervised One-Shot Detection with Attention Similarity Networks

TL;DR

This paper introduces a novel neural network architecture that combines Siamese similarity and attention mechanisms to improve weakly supervised one-shot detection, effectively identifying and localizing unseen class instances in images and audio.

Contribution

The paper presents a new neural network model that integrates attention with Siamese similarity for weakly supervised one-shot detection of unseen classes.

Findings

Significantly outperforms baseline methods in computer vision tasks.

Effective in localizing unseen class instances.

Applicable to both visual and audio data domains.

Abstract

Neural network models that are not conditioned on class identities were shown to facilitate knowledge transfer between classes and to be well-suited for one-shot learning tasks. Following this motivation, we further explore and establish such models and present a novel neural network architecture for the task of weakly supervised one-shot detection. Our model is only conditioned on a single exemplar of an unseen class and a larger target example that may or may not contain an instance of the same class as the exemplar. By pairing a Siamese similarity network with an attention mechanism, we design a model that manages to simultaneously identify and localise instances of classes unseen at training time. In experiments with datasets from the computer vision and audio domains, the proposed method considerably outperforms the baseline methods for the weakly supervised one-shot detection task.