499 citations · 1.1k across the 62 of their papers we have counts for
8 papers · 1 filter
Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks
Jie Hu, Li Shen, Samuel Albanie +2
While the use of bottom-up local operators in convolutional neural networks (CNNs) matches well some of the statistics of natural images, it may also prevent such models from captu…
Emotion Recognition in Speech using Cross-Modal Transfer in the Wild
Samuel Albanie, Arsha Nagrani, Andrea Vedaldi +1
Obtaining large, human labelled speech datasets to train models for emotion recognition is a notoriously challenging task, hindered by annotation cost and label ambiguity. In this…
Semi-convolutional Operators for Instance Segmentation
David Novotny, Samuel Albanie, Diane Larlus +1
Object detection and instance segmentation are dominated by region-based methods such as Mask RCNN. However, there is a growing interest in reducing these problems to pixel labelin…
Small steps and giant leaps: Minimal Newton solvers for Deep Learning
João F. Henriques, Sebastien Ehrhardt, Samuel Albanie +1
We propose a fast second-order method that can be used as a drop-in replacement for current deep learning solvers. Compared to stochastic gradient descent (SGD), it only requires t…
Learnable PINs: Cross-Modal Embeddings for Person Identity
Arsha Nagrani, Samuel Albanie, Andrew Zisserman
We propose and investigate an identity sensitive joint embedding of face and voice. Such an embedding enables cross-modal retrieval from voice to face and from face to voice. We ma…
Self-supervised Learning of Geometrically Stable Features Through Probabilistic Introspection
David Novotny, Samuel Albanie, Diane Larlus +1
Self-supervision can dramatically cut back the amount of manually-labelled data required to train deep neural networks. While self-supervision has usually been considered for tasks…
Seeing Voices and Hearing Faces: Cross-modal biometric matching
Arsha Nagrani, Samuel Albanie, Andrew Zisserman
We introduce a seemingly impossible task: given only an audio clip of someone speaking, decide which of two face images is the speaker. In this paper we study this, and a number of…
Substitute Teacher Networks: Learning with Almost No Supervision
Samuel Albanie, James Thewlis, Joao F. Henriques
Learning through experience is time-consuming, inefficient and often bad for your cortisol levels. To address this problem, a number of recently proposed teacher-student methods ha…