Search Results for author: Marco Pedersoli

Found 73 papers, 48 papers with code

Unsupervised Object Discovery: A Comprehensive Survey and Unified Taxonomy

no code implementations30 Oct 2024 José-Fabian Villa-Vásquez, Marco Pedersoli

Unsupervised object discovery is commonly interpreted as the task of localizing and/or categorizing objects in visual data without the need for labeled examples.

Navigate Object +3

Spatial Action Unit Cues for Interpretable Deep Facial Expression Recognition

1 code implementation1 Oct 2024 Soufiane Belharbi, Marco Pedersoli, Alessandro Lameiras Koerich, Simon Bacon, Eric Granger

During training, this AU codebook is used, along with the input image expression label, and facial landmarks, to construct a AU heatmap that indicates the most discriminative image regions of interest w. r. t the facial expression.

Facial Expression Recognition Facial Expression Recognition (FER)

Source-Free Domain Adaptation for YOLO Object Detection

1 code implementation25 Sep 2024 Simon Varailhon, Masih Aminbeidokhti, Marco Pedersoli, Eric Granger

Source-free domain adaptation (SFDA) is a challenging problem in object detection, where a pre-trained source model is adapted to a new target domain without using any source domain data for privacy and efficiency reasons.

Model Selection Object +3

Multi Teacher Privileged Knowledge Distillation for Multimodal Expression Recognition

1 code implementation16 Aug 2024 Muhammad Haseeb Aslam, Marco Pedersoli, Alessandro Lameiras Koerich, Eric Granger

However, PKD methods based on structural similarity are primarily confined to learning from a single joint teacher representation, which limits their robustness, accuracy, and ability to learn from diverse multimodal sources.

Knowledge Distillation Multimodal Emotion Recognition

Masked Multi-Query Slot Attention for Unsupervised Object Discovery

1 code implementation30 Apr 2024 Rishav Pramanik, José-Fabian Villa-Vásquez, Marco Pedersoli

Moreover, we extend the slot attention to a multi-query approach, allowing the model to learn multiple sets of slots, producing more stable masks.

Object object-detection +4

MiPa: Mixed Patch Infrared-Visible Modality Agnostic Object Detection

1 code implementation29 Apr 2024 Heitor R. Medeiros, David Latortue, Eric Granger, Marco Pedersoli

Multimodal learning is a common way to leverage these modalities, where multiple modality-specific encoders and a fusion module are used to improve performance.

Autonomous Driving Multispectral Object Detection +3

A Realistic Protocol for Evaluation of Weakly Supervised Object Localization

1 code implementation15 Apr 2024 Shakeeb Murtaza, Soufiane Belharbi, Marco Pedersoli, Eric Granger

These bboxes are also employed to estimate the threshold from LOC maps, circumventing the need for test-set bbox annotations.

Model Selection Object +2

Modality Translation for Object Detection Adaptation Without Forgetting Prior Knowledge

1 code implementation1 Apr 2024 Heitor Rapela Medeiros, Masih Aminbeidokhti, Fidel Guerrero Pena, David Latortue, Eric Granger, Marco Pedersoli

This paper focuses on adapting a large object detection model trained on RGB images to new data extracted from IR images with a substantial modality shift.

object-detection Object Detection +1

Do not trust what you trust: Miscalibration in Semi-supervised Learning

1 code implementation22 Mar 2024 Shambhavi Mishra, Balamurali Murugesan, Ismail Ben Ayed, Marco Pedersoli, Jose Dolz

State-of-the-art semi-supervised learning (SSL) approaches rely on highly confident predictions to serve as pseudo-labels that guide the training on unlabeled samples.

Image Classification

Joint Multimodal Transformer for Emotion Recognition in the Wild

1 code implementation15 Mar 2024 Paul Waligora, Haseeb Aslam, Osama Zeeshan, Soufiane Belharbi, Alessandro Lameiras Koerich, Marco Pedersoli, Simon Bacon, Eric Granger

Multimodal emotion recognition (MMER) systems typically outperform unimodal systems by leveraging the inter- and intra-modal relationships between, e. g., visual, textual, physiological, and auditory modalities.

Multimodal Emotion Recognition

Attention-based Class-Conditioned Alignment for Multi-Source Domain Adaptation of Object Detectors

1 code implementation14 Mar 2024 Atif Belal, Akhil Meethal, Francisco Perdigon Romero, Marco Pedersoli, Eric Granger

Domain adaptation methods for object detection (OD) strive to mitigate the impact of distribution shifts by promoting feature alignment across source and target domains.

Benchmarking Domain Adaptation +3

Guided Interpretable Facial Expression Recognition via Spatial Action Unit Cues

1 code implementation1 Feb 2024 Soufiane Belharbi, Marco Pedersoli, Alessandro Lameiras Koerich, Simon Bacon, Eric Granger

During training, this \au codebook is used, along with the input image expression label, and facial landmarks, to construct a \au heatmap that indicates the most discriminative image regions of interest w. r. t the facial expression.

Facial Expression Recognition Facial Expression Recognition (FER)

StarVector: Generating Scalable Vector Graphics Code from Images

1 code implementation17 Dec 2023 Juan A. Rodriguez, Shubham Agarwal, Issam H. Laradji, Pau Rodriguez, David Vazquez, Christopher Pal, Marco Pedersoli

These visual tokens are pre-pended to the SVG token embeddings, and the sequence is modeled by the StarCoder model using next-token prediction, effectively learning to align the visual and code tokens.

Code Generation Vector Graphics

Subject-Based Domain Adaptation for Facial Expression Recognition

1 code implementation9 Dec 2023 Muhammad Osama Zeeshan, Muhammad Haseeb Aslam, Soufiane Belharbi, Alessandro Lameiras Koerich, Marco Pedersoli, Simon Bacon, Eric Granger

It efficiently leverages information from multiple source subjects (labeled source domain data) to adapt a deep FER model to a single target individual (unlabeled target domain data).

Facial Expression Recognition Facial Expression Recognition (FER) +2

Evaluating Supervision Levels Trade-Offs for Infrared-Based People Counting

1 code implementation20 Nov 2023 David Latortue, Moetez Kdayem, Fidel A Guerrero Peña, Eric Granger, Marco Pedersoli

Object detection models are commonly used for people counting (and localization) in many applications but require a dataset with costly bounding box annotations for training.

Image Classification object-detection +1

DiPS: Discriminative Pseudo-Label Sampling with Self-Supervised Transformers for Weakly Supervised Object Localization

1 code implementation9 Oct 2023 Shakeeb Murtaza, Soufiane Belharbi, Marco Pedersoli, Aydin Sarraf, Eric Granger

Subsequently, these proposals are used as pseudo-labels to train our new transformer-based WSOL model designed to perform classification and localization tasks.

Object Pseudo Label +1

Bag of Tricks for Fully Test-Time Adaptation

1 code implementation3 Oct 2023 Saypraseuth Mounsaveng, Florent Chiaroni, Malik Boudiaf, Marco Pedersoli, Ismail Ben Ayed

Fully Test-Time Adaptation (TTA), which aims at adapting models to data drifts, has recently attracted wide interest.

Test-time Adaptation

Multi-Source Domain Adaptation for Object Detection with Prototype-based Mean-teacher

1 code implementation26 Sep 2023 Atif Belal, Akhil Meethal, Francisco Perdigon Romero, Marco Pedersoli, Eric Granger

Given the use of prototypes, the number of parameters required for our PMT method does not increase significantly with the number of source domains, thus reducing memory issues and possible overfitting.

Multi-Source Unsupervised Domain Adaptation object-detection +2

Density Crop-guided Semi-supervised Object Detection in Aerial Images

1 code implementation9 Aug 2023 Akhil Meethal, Eric Granger, Marco Pedersoli

One of the important bottlenecks in training modern object detectors is the need for labeled images where bounding box annotations have to be produced for each object present in the image.

Object object-detection +2

Balanced Mixture of SuperNets for Learning the CNN Pooling Architecture

1 code implementation21 Jun 2023 Mehraveh Javan, Matthew Toews, Marco Pedersoli

To fully understand this problem, we analyse the performance of models independently trained with each pooling configurations on CIFAR10, using a ResNet20 network, and show that the position of the downsampling layers can highly influence the performance of a network and predefined downsampling configurations are not optimal.

 Ranked #1 on Neural Architecture Search on Food-101 (Accuracy (% ) metric)

Image Classification Neural Architecture Search

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.

CoLo-CAM: Class Activation Mapping for Object Co-Localization in Weakly-Labeled Unconstrained Videos

1 code implementation16 Mar 2023 Soufiane Belharbi, Shakeeb Murtaza, Marco Pedersoli, Ismail Ben Ayed, Luke McCaffrey, Eric Granger

This paper proposes a novel CAM method for WSVOL that exploits spatiotemporal information in activation maps during training without constraining an object's position.

Object Object Localization

Cascaded Zoom-in Detector for High Resolution Aerial Images

1 code implementation15 Mar 2023 Akhil Meethal, Eric Granger, Marco Pedersoli

Detecting objects in aerial images is challenging because they are typically composed of crowded small objects distributed non-uniformly over high-resolution images.

object-detection Small Object Detection +1

Re-basin via implicit Sinkhorn differentiation

1 code implementation CVPR 2023 Fidel A. Guerrero Peña, Heitor Rapela Medeiros, Thomas Dubail, Masih Aminbeidokhti, Eric Granger, Marco Pedersoli

The recent emergence of new algorithms for permuting models into functionally equivalent regions of the solution space has shed some light on the complexity of error surfaces, and some promising properties like mode connectivity.

Continual Learning Incremental Learning +3

Camera Alignment and Weighted Contrastive Learning for Domain Adaptation in Video Person ReID

no code implementations7 Nov 2022 Djebril Mekhazni, Maximilien Dufau, Christian Desrosiers, Marco Pedersoli, Eric Granger

In this scenario, the ReID model must adapt to a complex target domain defined by a network of diverse video cameras based on tracklet information.

Clustering Contrastive Learning +2

OCR-VQGAN: Taming Text-within-Image Generation

3 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.

Decoder Optical Character Recognition (OCR) +1

Privacy-Preserving Person Detection Using Low-Resolution Infrared Cameras

no code implementations22 Sep 2022 Thomas Dubail, Fidel Alejandro Guerrero Peña, Heitor Rapela Medeiros, Masih Aminbeidokhti, Eric Granger, Marco Pedersoli

In intelligent building management, knowing the number of people and their location in a room are important for better control of its illumination, ventilation, and heating with reduced costs and improved comfort.

Human Detection Management +1

Constrained Sampling for Class-Agnostic Weakly Supervised Object Localization

no code implementations9 Sep 2022 Shakeeb Murtaza, Soufiane Belharbi, Marco Pedersoli, Aydin Sarraf, Eric Granger

Then, foreground and background pixels are sampled from these regions in order to train a WSOL model for generating activation maps that can accurately localize objects belonging to a specific class.

Object Weakly-Supervised Object Localization

Semi-Weakly Supervised Object Detection by Sampling Pseudo Ground-Truth Boxes

1 code implementation1 Apr 2022 Akhil Meethal, Marco Pedersoli, Zhongwen Zhu, Francisco Perdigon Romero, Eric Granger

Semi- and weakly-supervised learning have recently attracted considerable attention in the object detection literature since they can alleviate the cost of annotation needed to successfully train deep learning models.

Data Augmentation object-detection +2

A Joint Cross-Attention Model for Audio-Visual Fusion in Dimensional Emotion Recognition

1 code implementation28 Mar 2022 R. Gnana Praveen, Wheidima Carneiro de Melo, Nasib Ullah, Haseeb Aslam, Osama Zeeshan, Théo Denorme, Marco Pedersoli, Alessandro Koerich, Simon Bacon, Patrick Cardinal, Eric Granger

Specifically, we propose a joint cross-attention model that relies on the complementary relationships to extract the salient features across A-V modalities, allowing for accurate prediction of continuous values of valence and arousal.

Multimodal Emotion Recognition

Boundary-aware Information Maximization for Self-supervised Medical Image Segmentation

no code implementations4 Feb 2022 Jizong Peng, Ping Wang, Marco Pedersoli, Christian Desrosiers

Unsupervised pre-training has been proven as an effective approach to boost various downstream tasks given limited labeled data.

Contrastive Learning Image Segmentation +4

Diversified Multi-prototype Representation for Semi-supervised Segmentation

no code implementations16 Nov 2021 Jizong Peng, Christian Desrosiers, Marco Pedersoli

This work considers semi-supervised segmentation as a dense prediction problem based on prototype vector correlation and proposes a simple way to represent each segmentation class with multiple prototypes.

Segmentation

F-CAM: Full Resolution Class Activation Maps via Guided Parametric Upscaling

1 code implementation15 Sep 2021 Soufiane Belharbi, Aydin Sarraf, Marco Pedersoli, Ismail Ben Ayed, Luke McCaffrey, Eric Granger

Interpolation is required to restore full size CAMs, yet it does not consider the statistical properties of objects, such as color and texture, leading to activations with inconsistent boundaries, and inaccurate localizations.

Weakly-Supervised Object Localization

Self-Paced Contrastive Learning for Semi-supervised Medical Image Segmentation with Meta-labels

1 code implementation NeurIPS 2021 Jizong Peng, Ping Wang, Chrisitian Desrosiers, Marco Pedersoli

Pre-training a recognition model with contrastive learning on a large dataset of unlabeled data has shown great potential to boost the performance of a downstream task, e. g., image classification.

Contrastive Learning Image Classification +3

Context-aware virtual adversarial training for anatomically-plausible segmentation

no code implementations12 Jul 2021 Ping Wang, Jizong Peng, Marco Pedersoli, Yuanfeng Zhou, Caiming Zhang, Christian Desrosiers

Despite their outstanding accuracy, semi-supervised segmentation methods based on deep neural networks can still yield predictions that are considered anatomically impossible by clinicians, for instance, containing holes or disconnected regions.

Segmentation

Incremental Multi-Target Domain Adaptation for Object Detection with Efficient Domain Transfer

1 code implementation13 Apr 2021 Le Thanh Nguyen-Meidine, Madhu Kiran, Marco Pedersoli, Jose Dolz, Louis-Antoine Blais-Morin, Eric Granger

Recent advances in unsupervised domain adaptation have significantly improved the recognition accuracy of CNNs by alleviating the domain shift between (labeled) source and (unlabeled) target data distributions.

Incremental Learning Knowledge Distillation +5

Boosting Semi-supervised Image Segmentation with Global and Local Mutual Information Regularization

1 code implementation8 Mar 2021 Jizong Peng, Marco Pedersoli, Christian Desrosiers

In this method, we maximize the MI for intermediate feature embeddings that are taken from both the encoder and decoder of a segmentation network.

Decoder Image Segmentation +3

Augmented Lagrangian Adversarial Attacks

2 code implementations ICCV 2021 Jérôme Rony, Eric Granger, Marco Pedersoli, Ismail Ben Ayed

Our attack enjoys the generality of penalty methods and the computational efficiency of distance-customized algorithms, and can be readily used for a wide set of distances.

Adversarial Attack Computational Efficiency

Temporal Stochastic Softmax for 3D CNNs: An Application in Facial Expression Recognition

no code implementations10 Nov 2020 Théo Ayral, Marco Pedersoli, Simon Bacon, Eric Granger

The proposed softmax strategy provides several advantages: a reduced computational complexity due to efficient clip sampling, and an improved accuracy since temporal weighting focuses on more relevant clips during both training and inference.

Facial Expression Recognition Facial Expression Recognition (FER)

Self-paced and self-consistent co-training for semi-supervised image segmentation

1 code implementation31 Oct 2020 Ping Wang, Jizong Peng, Marco Pedersoli, Yuanfeng Zhou, Caiming Zhang, Christian Desrosiers

Moreover, to encourage predictions from different networks to be both consistent and confident, we enhance this generalized JSD loss with an uncertainty regularizer based on entropy.

Image Segmentation Segmentation +1

A unifying mutual information view of metric learning: cross-entropy vs. pairwise losses

1 code implementation ECCV 2020 Malik Boudiaf, Jérôme Rony, Imtiaz Masud Ziko, Eric Granger, Marco Pedersoli, Pablo Piantanida, Ismail Ben Ayed

Second, we show that, more generally, minimizing the cross-entropy is actually equivalent to maximizing the mutual information, to which we connect several well-known pairwise losses.

Ranked #12 on Metric Learning on CARS196 (using extra training data)

Metric Learning

Semi-supervised few-shot learning for medical image segmentation

no code implementations18 Mar 2020 Abdur R Feyjie, Reza Azad, Marco Pedersoli, Claude Kauffman, Ismail Ben Ayed, Jose Dolz

To handle this new learning paradigm, we propose to include surrogate tasks that can leverage very powerful supervisory signals --derived from the data itself-- for semantic feature learning.

Few-Shot Learning Image Segmentation +4

On the Texture Bias for Few-Shot CNN Segmentation

1 code implementation9 Mar 2020 Reza Azad, Abdur R Fayjie, Claude Kauffman, Ismail Ben Ayed, Marco Pedersoli, Jose Dolz

Despite the initial belief that Convolutional Neural Networks (CNNs) are driven by shapes to perform visual recognition tasks, recent evidence suggests that texture bias in CNNs provides higher performing models when learning on large labeled training datasets.

Few-Shot Semantic Segmentation Segmentation +1

Convolutional STN for Weakly Supervised Object Localization

1 code implementation3 Dec 2019 Akhil Meethal, Marco Pedersoli, Soufiane Belharbi, Eric Granger

Weakly supervised object localization is a challenging task in which the object of interest should be localized while learning its appearance.

Object Weakly-Supervised Object Localization

A Computing Kernel for Network Binarization on PyTorch

1 code implementation11 Nov 2019 Xianda Xu, Marco Pedersoli

Deep Neural Networks have now achieved state-of-the-art results in a wide range of tasks including image classification, object detection and so on.

Binarization Image Classification +3

Information based Deep Clustering: An experimental study

no code implementations3 Oct 2019 Jizong Peng, Christian Desrosiers, Marco Pedersoli

The second, named Invariant Information Clustering (IIC), maximizes the mutual information between the clustering of a sample and its geometrically transformed version.

Clustering Deep Clustering

Emotion Recognition with Spatial Attention and Temporal Softmax Pooling

no code implementations2 Oct 2019 Masih Aminbeidokhti, Marco Pedersoli, Patrick Cardinal, Eric Granger

Video-based emotion recognition is a challenging task because it requires to distinguish the small deformations of the human face that represent emotions, while being invariant to stronger visual differences due to different identities.

Emotion Recognition

Adversarial Learning of General Transformations for Data Augmentation

no code implementations ICLR Workshop LLD 2019 Saypraseuth Mounsaveng, David Vazquez, Ismail Ben Ayed, Marco Pedersoli

Data augmentation (DA) is fundamental against overfitting in large convolutional neural networks, especially with a limited training dataset.

Data Augmentation Decoder

Discretely-constrained deep network for weakly supervised segmentation

no code implementations15 Aug 2019 Jizong Peng, Hoel Kervadec, Jose Dolz, Ismail Ben Ayed, Marco Pedersoli, Christian Desrosiers

An efficient strategy for weakly-supervised segmentation is to impose constraints or regularization priors on target regions.

Cardiac Segmentation Segmentation +1

Progressive Gradient Pruning for Classification, Detection and DomainAdaptation

1 code implementation20 Jun 2019 Le Thanh Nguyen-Meidine, Eric Granger, Madhu Kiran, Louis-Antoine Blais-Morin, Marco Pedersoli

Although deep neural networks (NNs) have achievedstate-of-the-art accuracy in many visual recognition tasks, the growing computational complexity and energy con-sumption of networks remains an issue, especially for ap-plications on platforms with limited resources and requir-ing real-time processing.

Classification General Classification +2

Deep Co-Training for Semi-Supervised Image Segmentation

2 code implementations27 Mar 2019 Jizong Peng, Guillermo Estrada, Marco Pedersoli, Christian Desrosiers

In this paper, we aim to improve the performance of semantic image segmentation in a semi-supervised setting in which training is effectuated with a reduced set of annotated images and additional non-annotated images.

Diversity Image Segmentation +2

Deep clustering: On the link between discriminative models and K-means

1 code implementation9 Oct 2018 Mohammed Jabi, Marco Pedersoli, Amar Mitiche, Ismail Ben Ayed

Typically, they use multinomial logistic regression posteriors and parameter regularization, as is very common in supervised learning.

Clustering Deep Clustering +2

An Attention Model for group-level emotion recognition

1 code implementation9 Jul 2018 Aarush Gupta, Dakshit Agrawal, Hardik Chauhan, Jose Dolz, Marco Pedersoli

In this paper we propose a new approach for classifying the global emotion of images containing groups of people.

Emotion Recognition

Modeling Information Flow Through Deep Neural Networks

no code implementations29 Nov 2017 Ahmad Chaddad, Behnaz Naisiri, Marco Pedersoli, Eric Granger, Christian Desrosiers, Matthew Toews

This paper proposes a principled information theoretic analysis of classification for deep neural network structures, e. g. convolutional neural networks (CNN).

Classification General Classification +2

DeepProposals: Hunting Objects and Actions by Cascading Deep Convolutional Layers

1 code implementation15 Jun 2016 Amir Ghodrati, Ali Diba, Marco Pedersoli, Tinne Tuytelaars, Luc van Gool

In this paper, a new method for generating object and action proposals in images and videos is proposed.

Object

Learning Where to Position Parts in 3D

no code implementations ICCV 2015 Marco Pedersoli, Tinne Tuytelaars

In this paper we propose a new method for the detection and pose estimation of 3D objects, that does not use any 3D CAD model or other 3D information.

Object object-detection +3

Towards Automatic Image Editing: Learning to See another You

no code implementations26 Nov 2015 Amir Ghodrati, Xu Jia, Marco Pedersoli, Tinne Tuytelaars

Learning the distribution of images in order to generate new samples is a challenging task due to the high dimensionality of the data and the highly non-linear relations that are involved.

Attribute Image Generation +1

DeepProposal: Hunting Objects by Cascading Deep Convolutional Layers

1 code implementation ICCV 2015 Amir Ghodrati, Ali Diba, Marco Pedersoli, Tinne Tuytelaars, Luc van Gool

We generate hypotheses in a sliding-window fashion over different activation layers and show that the final convolutional layers can find the object of interest with high recall but poor localization due to the coarseness of the feature maps.

Object

Weakly Supervised Object Detection With Convex Clustering

no code implementations CVPR 2015 Hakan Bilen, Marco Pedersoli, Tinne Tuytelaars

However, as learning appearance and localization are two interconnected tasks, the optimization is not convex and the procedure can easily get stuck in a poor local minimum, the algorithm "misses" the object in some images.

Clustering Object +2

Object Classification with Adaptable Regions

no code implementations CVPR 2014 Hakan Bilen, Marco Pedersoli, Vinay P. Namboodiri, Tinne Tuytelaars, Luc van Gool

In classification of objects substantial work has gone into improving the low level representation of an image by considering various aspects such as different features, a number of feature pooling and coding techniques and considering different kernels.

Classification General Classification +1

Using a Deformation Field Model for Localizing Faces and Facial Points under Weak Supervision

no code implementations CVPR 2014 Marco Pedersoli, Tinne Tuytelaars, Luc van Gool

Additionally, without any facial point annotation at the level of individual training images, our method can localize facial points with an accuracy similar to fully supervised approaches.

Face Detection

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