Search Results for author: Pau Rodríguez

Found 13 papers, 8 papers with code

Robust multimodal models have outlier features and encode more concepts

no code implementations19 Oct 2023 Jonathan Crabbé, Pau Rodríguez, Vaishaal Shankar, Luca Zappella, Arno Blaas

In this work, we bridge this gap by probing the representation spaces of 12 robust multimodal models with various backbones (ResNets and ViTs) and pretraining sets (OpenAI, LAION-400M, LAION-2B, YFCC15M, CC12M and DataComp).

The Role of Entropy and Reconstruction in Multi-View Self-Supervised Learning

1 code implementation20 Jul 2023 Borja Rodríguez-Gálvez, Arno Blaas, Pau Rodríguez, Adam Goliński, Xavier Suau, Jason Ramapuram, Dan Busbridge, Luca Zappella

We consider a different lower bound on the MI consisting of an entropy and a reconstruction term (ER), and analyze the main MVSSL families through its lens.

Self-Supervised Learning

Challenging Common Assumptions about Catastrophic Forgetting

no code implementations10 Jul 2022 Timothée Lesort, Oleksiy Ostapenko, Diganta Misra, Md Rifat Arefin, Pau Rodríguez, Laurent Charlin, Irina Rish

In this paper, we study the progressive knowledge accumulation (KA) in DNNs trained with gradient-based algorithms in long sequences of tasks with data re-occurrence.

Continual Learning Memorization

Continual Learning with Foundation Models: An Empirical Study of Latent Replay

1 code implementation30 Apr 2022 Oleksiy Ostapenko, Timothee Lesort, Pau Rodríguez, Md Rifat Arefin, Arthur Douillard, Irina Rish, Laurent Charlin

Motivated by this, we study the efficacy of pre-trained vision models as a foundation for downstream continual learning (CL) scenarios.

Benchmarking Continual Learning

SSR: Semi-supervised Soft Rasterizer for single-view 2D to 3D Reconstruction

1 code implementation21 Aug 2021 Issam Laradji, Pau Rodríguez, David Vazquez, Derek Nowrouzezahrai

In order to obtain the viewpoints for these unlabeled images, we propose to use a Siamese network that takes two images as input and outputs whether they correspond to the same viewpoint.

3D Reconstruction

Beyond One-hot Encoding: lower dimensional target embedding

no code implementations28 Jun 2018 Pau Rodríguez, Miguel A. Bautista, Jordi Gonzàlez, Sergio Escalera

Following this observation, we embed the targets into a low-dimensional space, drastically improving convergence speed while preserving accuracy.


Deep Inference of Personality Traits by Integrating Image and Word Use in Social Networks

no code implementations6 Feb 2018 Guillem Cucurull, Pau Rodríguez, V. Oguz Yazici, Josep M. Gonfaus, F. Xavier Roca, Jordi Gonzàlez

Following this trend on visual-based social analysis, we present a novel methodology based on Deep Learning to build a combined image-and-text based personality trait model, trained with images posted together with words found highly correlated to specific personality traits.

A Painless Attention Mechanism for Convolutional Neural Networks

no code implementations ICLR 2018 Pau Rodríguez, Guillem Cucurull, Jordi Gonzàlez, Josep M. Gonfaus, Xavier Roca

We propose a novel attention mechanism to enhance Convolutional Neural Networks for fine-grained recognition.

Regularizing CNNs with Locally Constrained Decorrelations

1 code implementation7 Nov 2016 Pau Rodríguez, Jordi Gonzàlez, Guillem Cucurull, Josep M. Gonfaus, Xavier Roca

In this paper, we show that regularizing negatively correlated features is an obstacle for effective decorrelation and present OrthoReg, a novel regularization technique that locally enforces feature orthogonality.

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