Miguel Lagunes-Fortiz — accepted AI-conference papers

2020

Centroids Triplet Network and Temporally-Consistent Embeddings for In-Situ Object Recognition

Miguel Lagunes-Fortiz, Dima Damen, Walterio Mayol-Cuevas

IROS 2020poster

This work proposes learning to recognize objects from a small number of training examples collected and deployed in-situ. That is, from data collected where the objects are commonly placed or being used, perhaps after first encountering them, the learning algorithm immediately is able to recognize t…

Cited by 5 Source ↗Scholar ↗

2019

Learning Discriminative Embeddings for Object Recognition on-the-fly

Miguel Lagunes-Fortiz, Dima Damen, Walterio Mayol-Cuevas

ICRA 2019poster

We address the problem of learning to recognize new objects on-the-fly efficiently. When using CNNs, a typical approach for learning new objects is by fine-tuning the model. However, this approach relies on the assumption that the original training set is available and requires high-end computationa…

Cited by 17 Source ↗Scholar ↗