9 papers
Asymmetric metric learning for knowledge transfer
Mateusz Budnik, Yannis Avrithis
Knowledge transfer from large teacher models to smaller student models has recently been studied for metric learning, focusing on fine-grained classification. In this work, focusin…
Few-Shot Few-Shot Learning and the role of Spatial Attention
Yann Lifchitz, Yannis Avrithis, Sylvaine Picard
Few-shot learning is often motivated by the ability of humans to learn new tasks from few examples. However, standard few-shot classification benchmarks assume that the representat…
Rethinking deep active learning: Using unlabeled data at model training
Oriane Siméoni, Mateusz Budnik, Yannis Avrithis +1
Active learning typically focuses on training a model on few labeled examples alone, while unlabeled ones are only used for acquisition. In this work we depart from this setting by…
Graph convolutional networks for learning with few clean and many noisy labels
Ahmet Iscen, Giorgos Tolias, Yannis Avrithis +2
In this work we consider the problem of learning a classifier from noisy labels when a few clean labeled examples are given. The structure of clean and noisy data is modeled by a g…
Local Features and Visual Words Emerge in Activations
Oriane Siméoni, Yannis Avrithis, Ondrej Chum
We propose a novel method of deep spatial matching (DSM) for image retrieval. Initial ranking is based on image descriptors extracted from convolutional neural network activations…
Label Propagation for Deep Semi-supervised Learning
Ahmet Iscen, Giorgos Tolias, Yannis Avrithis +1
Semi-supervised learning is becoming increasingly important because it can combine data carefully labeled by humans with abundant unlabeled data to train deep neural networks. Clas…