Overview
BMVC 2020 is the 31st British Machine Vision Virtual Conference. The British Machine Vision Conference (BMVC) is the British Machine Vision Association (BMVA) annual conference on machine vision, image processing, and pattern recognition. It is one of the major international conferences on computer vision and related areas held in the UK. With increasing popularity and quality, it has established itself as a prestigious event on the vision calendar.
🎉 It is an honor that AIOZ is having one publication at BMVC 2020. 🎉
Visit Conference Website at: https://www.bmvc2020-conference.com/
AIOZ research @ MICCAI 2021
✨ Multiple Meta-model Quantifying for Medical Visual Question Answering
Unsupervised Deep Distance Metric Learning (UDML) aims to learn sample similarities in the embedding space from an unlabeled dataset. Traditional UDML methods usually use the triplet loss or pairwise loss which requires the mining of positive and negative samples w.r.t. anchor data points. This is, however, challenging in an unsupervised setting as the label information is not available. In this paper, we propose a new UDML method that overcomes that challenge. In particular, we propose to use a deep clustering loss to learn centroids, i.e., pseudo labels, that represent semantic classes. During learning, these centroids are also used to reconstruct the input samples. It hence ensures the representativeness of centroids — each centroid represents visually similar samples. Therefore, the centroids give information about positive (visually similar) and negative (visually dissimilar) samples. Based on pseudo labels, we propose a novel unsupervised metric loss which enforces the positive concentration and negative separation of samples in the embedding space. Experimental results on benchmarking datasets show that the proposed approach outperforms other UDML methods.
Find out more information at
📜 Our blog post: https://blog.ai.aioz.io/research/deep-metric-learning-cbswr/
🎬 Our presentation: https://www.bmvc2020-conference.com/conference/papers/paper_0328.html
🚀 Github: https://github.com/aioz-ai/BMVC20_CBSwR