Search Results for author: Joao F. Henriques

Found 9 papers, 2 papers with code

Small Steps and Giant Leaps: Minimal Newton Solvers for Deep Learning

1 code implementation ICCV 2019 Joao F. Henriques, Sebastien Ehrhardt, Samuel Albanie, Andrea Vedaldi

We first validate our method, called CurveBall, on small problems with known solutions (noisy Rosenbrock function and degenerate 2-layer linear networks), where current deep learning solvers struggle.

Substitute Teacher Networks: Learning with Almost No Supervision

1 code implementation1 Apr 2018 Samuel Albanie, James Thewlis, Joao F. Henriques

Learning through experience is time-consuming, inefficient and often bad for your cortisol levels.

Rolling Riemannian Manifolds to Solve the Multi-class Classification Problem

no code implementations CVPR 2013 Rui Caseiro, Pedro Martins, Joao F. Henriques, Fatima Silva Leite, Jorge Batista

In the past few years there has been a growing interest on geometric frameworks to learn supervised classification models on Riemannian manifolds [31, 27].

Binary Classification Classification +3

On the Origin of Species of Self-Supervised Learning

no code implementations31 Mar 2021 Samuel Albanie, Erika Lu, Joao F. Henriques

In the quiet backwaters of cs. CV, cs. LG and stat. ML, a cornucopia of new learning systems is emerging from a primordial soup of mathematics-learning systems with no need for external supervision.

Self-Supervised Learning

Moving SLAM: Fully Unsupervised Deep Learning in Non-Rigid Scenes

no code implementations5 May 2021 Dan Xu, Andrea Vedaldi, Joao F. Henriques

We build on the idea of view synthesis, which uses classical camera geometry to re-render a source image from a different point-of-view, specified by a predicted relative pose and depth map.

Depth Estimation Depth Prediction +1

Multi-modal Self-Supervision from Generalized Data Transformations

no code implementations28 Sep 2020 Mandela Patrick, Yuki Asano, Polina Kuznetsova, Ruth Fong, Joao F. Henriques, Geoffrey Zweig, Andrea Vedaldi

In this paper, we show that, for videos, the answer is more complex, and that better results can be obtained by accounting for the interplay between invariance, distinctiveness, multiple modalities and time.

Audio Classification Retrieval +1

A Light Touch Approach to Teaching Transformers Multi-view Geometry

no code implementations CVPR 2023 Yash Bhalgat, Joao F. Henriques, Andrew Zisserman

Transformers are powerful visual learners, in large part due to their conspicuous lack of manually-specified priors.

Retrieval

Cannot find the paper you are looking for? You can Submit a new open access paper.