Search Results for author: Issam Laradji

Found 32 papers, 26 papers with code

TK-KNN: A Balanced Distance-Based Pseudo Labeling Approach for Semi-Supervised Intent Classification

1 code implementation17 Oct 2023 Nicholas Botzer, David Vasquez, Tim Weninger, Issam Laradji

In the present work, we describe Top-K K-Nearest Neighbor (TK-KNN), which uses a more robust pseudo-labeling approach based on distance in the embedding space while maintaining a balanced set of pseudo-labeled examples across classes through a ranking-based approach.

intent-classification Intent Classification

Automatic Data Augmentation Learning using Bilevel Optimization for Histopathological Images

1 code implementation21 Jul 2023 Saypraseuth Mounsaveng, Issam Laradji, David Vázquez, Marco Perdersoli, Ismail Ben Ayed

Experimental results show that our model can learn color and affine transformations that are more helpful to train an image classifier than predefined DA transformations, which are also more expensive as they need to be selected before the training by grid search on a validation set.

Bilevel Optimization Data Augmentation

FigGen: Text to Scientific Figure Generation

1 code implementation1 Jun 2023 Juan A Rodriguez, David Vazquez, Issam Laradji, Marco Pedersoli, Pau Rodriguez

The generative modeling landscape has experienced tremendous growth in recent years, particularly in generating natural images and art.

Language Decision Transformers with Exponential Tilt for Interactive Text Environments

no code implementations10 Feb 2023 Nicolas Gontier, Pau Rodriguez, Issam Laradji, David Vazquez, Christopher Pal

Text-based game environments are challenging because agents must deal with long sequences of text, execute compositional actions using text and learn from sparse rewards.

Offline RL

OCR-VQGAN: Taming Text-within-Image Generation

2 code implementations19 Oct 2022 Juan A. Rodriguez, David Vazquez, Issam Laradji, Marco Pedersoli, Pau Rodriguez

To alleviate this problem, we present OCR-VQGAN, an image encoder, and decoder that leverages OCR pre-trained features to optimize a text perceptual loss, encouraging the architecture to preserve high-fidelity text and diagram structure.

Image Generation Optical Character Recognition (OCR)

Constraining Representations Yields Models That Know What They Don't Know

no code implementations30 Aug 2022 Joao Monteiro, Pau Rodriguez, Pierre-Andre Noel, Issam Laradji, David Vazquez

In the add-on case, the original neural network's inference head is completely unaffected (so its accuracy remains the same) but we now have the option to use TAC's own confidence and prediction when determining which course of action to take in an hypothetical production workflow.

Workflow Discovery from Dialogues in the Low Data Regime

1 code implementation24 May 2022 Amine El Hattami, Stefania Raimondo, Issam Laradji, David Vazquez, Pau Rodriguez, Chris Pal

We propose and evaluate an approach that conditions models on the set of possible actions, and we show that using this strategy, we can improve WD performance.

Workflow Discovery

Overcoming challenges in leveraging GANs for few-shot data augmentation

1 code implementation30 Mar 2022 Christopher Beckham, Issam Laradji, Pau Rodriguez, David Vazquez, Derek Nowrouzezahrai, Christopher Pal

In this paper, we explore the use of GAN-based few-shot data augmentation as a method to improve few-shot classification performance.

Classification Data Augmentation +1

Neural Point Light Fields

no code implementations CVPR 2022 Julian Ost, Issam Laradji, Alejandro Newell, Yuval Bahat, Felix Heide

We introduce Neural Point Light Fields that represent scenes implicitly with a light field living on a sparse point cloud.

Novel View Synthesis

Stochastic Mirror Descent: Convergence Analysis and Adaptive Variants via the Mirror Stochastic Polyak Stepsize

no code implementations28 Oct 2021 Ryan D'Orazio, Nicolas Loizou, Issam Laradji, Ioannis Mitliagkas

We investigate the convergence of stochastic mirror descent (SMD) under interpolation in relatively smooth and smooth convex optimization.

A Survey of Self-Supervised and Few-Shot Object Detection

1 code implementation27 Oct 2021 Gabriel Huang, Issam Laradji, David Vazquez, Simon Lacoste-Julien, Pau Rodriguez

Labeling data is often expensive and time-consuming, especially for tasks such as object detection and instance segmentation, which require dense labeling of the image.

Few-Shot Object Detection Instance Segmentation +3

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 Trivial Counterfactual Explanations with Diverse Valuable Explanations

2 code implementations ICCV 2021 Pau Rodriguez, Massimo Caccia, Alexandre Lacoste, Lee Zamparo, Issam Laradji, Laurent Charlin, David Vazquez

Explainability for machine learning models has gained considerable attention within the research community given the importance of deploying more reliable machine-learning systems.

Attribute BIG-bench Machine Learning +2

Affinity LCFCN: Learning to Segment Fish with Weak Supervision

1 code implementation6 Nov 2020 Issam Laradji, Alzayat Saleh, Pau Rodriguez, Derek Nowrouzezahrai, Mostafa Rahimi Azghadi, David Vazquez

Leading automatic approaches rely on fully-supervised segmentation models to acquire these measurements but these require collecting per-pixel labels -- also time consuming and laborious: i. e., it can take up to two minutes per fish to generate accurate segmentation labels, almost always requiring at least some manual intervention.

Segmentation

CVPR 2020 Continual Learning in Computer Vision Competition: Approaches, Results, Current Challenges and Future Directions

1 code implementation14 Sep 2020 Vincenzo Lomonaco, Lorenzo Pellegrini, Pau Rodriguez, Massimo Caccia, Qi She, Yu Chen, Quentin Jodelet, Ruiping Wang, Zheda Mai, David Vazquez, German I. Parisi, Nikhil Churamani, Marc Pickett, Issam Laradji, Davide Maltoni

In the last few years, we have witnessed a renewed and fast-growing interest in continual learning with deep neural networks with the shared objective of making current AI systems more adaptive, efficient and autonomous.

Benchmarking Continual Learning

Segmentation of Pulmonary Opacification in Chest CT Scans of COVID-19 Patients

1 code implementation7 Jul 2020 Keegan Lensink, Issam Laradji, Marco Law, Paolo Emilio Barbano, Savvas Nicolaou, William Parker, Eldad Haber

In this work we provide open source models for the segmentation of patterns of pulmonary opacification on chest Computed Tomography (CT) scans which have been correlated with various stages and severities of infection.

Computed Tomography (CT) Domain Adaptation +1

A Weakly Supervised Consistency-based Learning Method for COVID-19 Segmentation in CT Images

3 code implementations4 Jul 2020 Issam Laradji, Pau Rodriguez, Oscar Mañas, Keegan Lensink, Marco Law, Lironne Kurzman, William Parker, David Vazquez, Derek Nowrouzezahrai

Thus, we propose a consistency-based (CB) loss function that encourages the output predictions to be consistent with spatial transformations of the input images.

Stochastic Polyak Step-size for SGD: An Adaptive Learning Rate for Fast Convergence

1 code implementation24 Feb 2020 Nicolas Loizou, Sharan Vaswani, Issam Laradji, Simon Lacoste-Julien

Consequently, the proposed stochastic Polyak step-size (SPS) is an attractive choice for setting the learning rate for stochastic gradient descent (SGD).

Fast and Furious Convergence: Stochastic Second Order Methods under Interpolation

1 code implementation11 Oct 2019 Si Yi Meng, Sharan Vaswani, Issam Laradji, Mark Schmidt, Simon Lacoste-Julien

Under this condition, we show that the regularized subsampled Newton method (R-SSN) achieves global linear convergence with an adaptive step-size and a constant batch-size.

Binary Classification Second-order methods

Class-Based Styling: Real-time Localized Style Transfer with Semantic Segmentation

1 code implementation30 Aug 2019 Lironne Kurzman, David Vazquez, Issam Laradji

We propose a Class-Based Styling method (CBS) that can map different styles for different object classes in real-time.

Object Segmentation +2

M-ADDA: Unsupervised Domain Adaptation with Deep Metric Learning

1 code implementation6 Jul 2018 Issam Laradji, Reza Babanezhad

Unsupervised domain adaptation techniques have been successful for a wide range of problems where supervised labels are limited.

Metric Learning Unsupervised Domain Adaptation

Let's Make Block Coordinate Descent Converge Faster: Faster Greedy Rules, Message-Passing, Active-Set Complexity, and Superlinear Convergence

1 code implementation23 Dec 2017 Julie Nutini, Issam Laradji, Mark Schmidt

Block coordinate descent (BCD) methods are widely used for large-scale numerical optimization because of their cheap iteration costs, low memory requirements, amenability to parallelization, and ability to exploit problem structure.

Optimization and Control 90C06

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