Joint Neural Networks for One-shot Object Recognition and Detection

TL;DR

This paper introduces a joint neural network model inspired by Siamese networks and multi-box detection techniques, capable of recognizing and detecting unseen object categories in one-shot learning scenarios, demonstrating promising accuracy and detection performance.

Contribution

The paper proposes a novel joint neural network architecture for one-shot object recognition and detection that works on unseen categories without prior training on those specific classes.

Findings

Achieves 61.41% accuracy on MiniImageNet for recognition

Attains 47.1% mAP on Pascal VOC for detection

Effective comparison of image pairs for recognizing unseen categories

Abstract

This paper presents a novel joint neural networks approach to address the challenging one-shot object recognition and detection tasks. Inspired by Siamese neural networks and state-of-art multi-box detection approaches, the joint neural networks are able to perform object recognition and detection for categories that remain unseen during the training process. Following the one-shot object recognition/detection constraints, the training and testing datasets do not contain overlapped classes, in other words, all the test classes remain unseen during training. The joint networks architecture is able to effectively compare pairs of images via stacked convolutional layers of the query and target inputs, recognising patterns of the same input query category without relying on previous training around this category. The proposed approach achieves 61.41% accuracy for one-shot object recognition on the MiniImageNet dataset and 47.1% mAP for one-shot object detection when trained on the COCO dataset and tested using the Pascal VOC dataset. Code available at https://github.com/cjvargasc/JNN recog and https://github.com/cjvargasc/JNN detection/