Publications (40)
Counting Cows: Tracking Illegal Cattle Ranching From High-Resolution Satellite Imagery
Issam Laradji, Pau Rodriguez, Freddie Kalaitzis +4
Cattle farming is responsible for 8.8\% of greenhouse gas emissions worldwide. In addition to the methane emitted due to their digestive process, the growing need for grazing areas…
ParaRNN: Unlocking Parallel Training of Nonlinear RNNs for Large Language Models
Federico Danieli, Pau Rodriguez, Miguel Sarabia +2
Recurrent Neural Networks (RNNs) laid the foundation for sequence modeling, but their intrinsic sequential nature restricts parallel computation, creating a fundamental barrier to…
Understanding Input Selectivity in Mamba: Impact on Approximation Power, Memorization, and Associative Recall Capacity
Ningyuan Huang, Miguel Sarabia, Abhinav Moudgil +3
State-Space Models (SSMs), and particularly Mamba, have recently emerged as a promising alternative to Transformers. Mamba introduces input selectivity to its SSM layer (S6) and in…
StarVector: Generating Scalable Vector Graphics Code from Images and Text
Juan A. Rodriguez, Abhay Puri, Shubham Agarwal +6
Scalable Vector Graphics (SVGs) are vital for modern image rendering due to their scalability and versatility. Previous SVG generation methods have focused on curve-based vectoriza…
Constraining Representations Yields Models That Know What They Don't Know
Joao Monteiro, Pau Rodriguez, Pierre-Andre Noel +2
A well-known failure mode of neural networks is that they may confidently return erroneous predictions. Such unsafe behaviour is particularly frequent when the use case slightly di…
LOOC: Localize Overlapping Objects with Count Supervision
Issam H. Laradji, Rafael Pardinas, Pau Rodriguez +1
Acquiring count annotations generally requires less human effort than point-level and bounding box annotations. Thus, we propose the novel problem setup of localizing objects in de…
3rd Continual Learning Workshop Challenge on Egocentric Category and Instance Level Object Understanding
Lorenzo Pellegrini, Chenchen Zhu, Fanyi Xiao +7
Continual Learning, also known as Lifelong or Incremental Learning, has recently gained renewed interest among the Artificial Intelligence research community. Recent research effor…
Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanations
Pau Rodriguez, Massimo Caccia, Alexandre Lacoste +4
Explainability for machine learning models has gained considerable attention within the research community given the importance of deploying more reliable machine-learning systems.…
A Survey of Self-Supervised and Few-Shot Object Detection
Gabriel Huang, Issam Laradji, David Vazquez +2
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. While few-s…
Sparse Autoencoders are Capable LLM Jailbreak Mitigators
Yannick Assogba, Jacopo Cortellazzi, Javier Abad +3
Jailbreak attacks remain a persistent threat to large language model safety. We propose Context-Conditioned Delta Steering (CC-Delta), an SAE-based defense that identifies jailbrea…
GEO-Bench: Toward Foundation Models for Earth Monitoring
Alexandre Lacoste, Nils Lehmann, Pau Rodriguez +14
Recent progress in self-supervision has shown that pre-training large neural networks on vast amounts of unsupervised data can lead to substantial increases in generalization to do…
Multi-label Iterated Learning for Image Classification with Label Ambiguity
Sai Rajeswar, Pau Rodriguez, Soumye Singhal +2
Transfer learning from large-scale pre-trained models has become essential for many computer vision tasks. Recent studies have shown that datasets like ImageNet are weakly labeled…
LinEAS: End-to-end Learning of Activation Steering with a Distributional Loss
Pau Rodriguez, Michal Klein, Eleonora Gualdoni +5
The growing use of generative models in daily life calls for efficient mechanisms to control their generation, to e.g., produce safe content or provide users with tools to explore…
A Weakly Supervised Consistency-based Learning Method for COVID-19 Segmentation in CT Images
Issam Laradji, Pau Rodriguez, Oscar Mañas +6
Coronavirus Disease 2019 (COVID-19) has spread aggressively across the world causing an existential health crisis. Thus, having a system that automatically detects COVID-19 in tomo…
OC-NMN: Object-centric Compositional Neural Module Network for Generative Visual Analogical Reasoning
Rim Assouel, Pau Rodriguez, Perouz Taslakian +2
A key aspect of human intelligence is the ability to imagine -- composing learned concepts in novel ways -- to make sense of new scenarios. Such capacity is not yet attained for ma…
Group Robust Classification Without Any Group Information
Christos Tsirigotis, Joao Monteiro, Pau Rodriguez +2
Empirical risk minimization (ERM) is sensitive to spurious correlations in the training data, which poses a significant risk when deploying systems trained under this paradigm in h…
CVPR 2020 Continual Learning in Computer Vision Competition: Approaches, Results, Current Challenges and Future Directions
Vincenzo Lomonaco, Lorenzo Pellegrini, Pau Rodriguez +12
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…
CADet: Fully Self-Supervised Out-Of-Distribution Detection With Contrastive Learning
Charles Guille-Escuret, Pau Rodriguez, David Vazquez +2
Handling out-of-distribution (OOD) samples has become a major stake in the real-world deployment of machine learning systems. This work explores the use of self-supervised contrast…
Hierarchical Residual Attention Network for Single Image Super-Resolution
Parichehr Behjati, Pau Rodriguez, Armin Mehri +3
Convolutional neural networks are the most successful models in single image super-resolution. Deeper networks, residual connections, and attention mechanisms have further improved…
Affinity LCFCN: Learning to Segment Fish with Weak Supervision
Issam Laradji, Alzayat Saleh, Pau Rodriguez +3
Aquaculture industries rely on the availability of accurate fish body measurements, e.g., length, width and mass. Manual methods that rely on physical tools like rulers are time an…
Data Augmentation for Intent Classification with Off-the-shelf Large Language Models
Gaurav Sahu, Pau Rodriguez, Issam H. Laradji +3
Data augmentation is a widely employed technique to alleviate the problem of data scarcity. In this work, we propose a prompting-based approach to generate labelled training data f…
FigGen: Text to Scientific Figure Generation
Juan A Rodriguez, David Vazquez, Issam Laradji +2
The generative modeling landscape has experienced tremendous growth in recent years, particularly in generating natural images and art. Recent techniques have shown impressive pote…
Dynamically Scaled Activation Steering
Alex Ferrando, Xavier Suau, Jordi Gonzà lez +1
Activation steering has emerged as a powerful method for guiding the behavior of generative models towards desired outcomes such as toxicity mitigation. However, most existing meth…
Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Data
Oscar Mañas, Alexandre Lacoste, Xavier Giro-i-Nieto +2
Remote sensing and automatic earth monitoring are key to solve global-scale challenges such as disaster prevention, land use monitoring, or tackling climate change. Although there…
A Weakly Supervised Region-Based Active Learning Method for COVID-19 Segmentation in CT Images
Issam Laradji, Pau Rodriguez, Frederic Branchaud-Charron +5
One of the key challenges in the battle against the Coronavirus (COVID-19) pandemic is to detect and quantify the severity of the disease in a timely manner. Computed tomographies…
ReCap: Lightweight Referential Grounding for Coherent Story Visualization
Aditya Arora, Akshita Gupta, Pau Rodriguez +1
Story Visualization aims to generate a sequence of images that faithfully depicts a textual narrative that preserve character identity, spatial configuration, and stylistic coheren…
Sequoia: A Software Framework to Unify Continual Learning Research
Fabrice Normandin, Florian Golemo, Oleksiy Ostapenko +10
The field of Continual Learning (CL) seeks to develop algorithms that accumulate knowledge and skills over time through interaction with non-stationary environments. In practice, a…
MAPL: Parameter-Efficient Adaptation of Unimodal Pre-Trained Models for Vision-Language Few-Shot Prompting
Oscar Mañas, Pau Rodriguez, Saba Ahmadi +3
Large pre-trained models have proved to be remarkable zero- and (prompt-based) few-shot learners in unimodal vision and language tasks. We propose MAPL, a simple and parameter-effi…
Workflow Discovery from Dialogues in the Low Data Regime
Amine El Hattami, Stefania Raimondo, Issam Laradji +3
Text-based dialogues are now widely used to solve real-world problems. In cases where solution strategies are already known, they can sometimes be codified into workflows and used…
Overcoming challenges in leveraging GANs for few-shot data augmentation
Christopher Beckham, Issam Laradji, Pau Rodriguez +3
In this paper, we explore the use of GAN-based few-shot data augmentation as a method to improve few-shot classification performance. We perform an exploration into how a GAN can b…
Toward Foundation Models for Earth Monitoring: Proposal for a Climate Change Benchmark
Alexandre Lacoste, Evan David Sherwin, Hannah Kerner +9
Recent progress in self-supervision shows that pre-training large neural networks on vast amounts of unsupervised data can lead to impressive increases in generalisation for downst…
Continual Learning of Diffusion Models with Generative Distillation
Sergi Masip, Pau Rodriguez, Tinne Tuytelaars +1
Diffusion models are powerful generative models that achieve state-of-the-art performance in image synthesis. However, training them demands substantial amounts of data and computa…
Language Decision Transformers with Exponential Tilt for Interactive Text Environments
Nicolas Gontier, Pau Rodriguez, Issam Laradji +2
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. We addres…
OverNet: Lightweight Multi-Scale Super-Resolution with Overscaling Network
Parichehr Behjati, Pau Rodriguez, Armin Mehri +3
Super-resolution (SR) has achieved great success due to the development of deep convolutional neural networks (CNNs). However, as the depth and width of the networks increase, CNN-…
TADAM: Task dependent adaptive metric for improved few-shot learning
Boris N. Oreshkin, Pau Rodriguez, Alexandre Lacoste
Few-shot learning has become essential for producing models that generalize from few examples. In this work, we identify that metric scaling and metric task conditioning are import…
Continual Learning via Local Module Composition
Oleksiy Ostapenko, Pau Rodriguez, Massimo Caccia +1
Modularity is a compelling solution to continual learning (CL), the problem of modeling sequences of related tasks. Learning and then composing modules to solve different tasks pro…
Online Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning
Massimo Caccia, Pau Rodriguez, Oleksiy Ostapenko +8
Continual learning studies agents that learn from streams of tasks without forgetting previous ones while adapting to new ones. Two recent continual-learning scenarios have opened…
GenCtrl -- A Formal Controllability Toolkit for Generative Models
Emily Cheng, Carmen Amo Alonso, Federico Danieli +4
As generative models become ubiquitous, there is a critical need for fine-grained control over the generation process. Yet, while controlled generation methods from prompting to fi…
OCR-VQGAN: Taming Text-within-Image Generation
Juan A. Rodriguez, David Vazquez, Issam Laradji +2
Synthetic image generation has recently experienced significant improvements in domains such as natural image or art generation. However, the problem of figure and diagram generati…
Controlling Language and Diffusion Models by Transporting Activations
Pau Rodriguez, Arno Blaas, Michal Klein +4
The increasing capabilities of large generative models and their ever more widespread deployment have raised concerns about their reliability, safety, and potential misuse. To addr…