1 code implementation • 15 Apr 2024 • Shakeeb Murtaza, Soufiane Belharbi, Marco Pedersoli, Eric Granger
Our experimental results with several WSOL methods on ILSVRC and CUB-200-2011 datasets show that our noisy boxes allow selecting models with performance close to those selected using ground truth boxes, and better than models selected using only image-class labels.
1 code implementation • 15 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.
1 code implementation • 1 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)
no code implementations • 27 Jan 2024 • Muhammad Haseeb Aslam, Muhammad Osama Zeeshan, Soufiane Belharbi, Marco Pedersoli, Alessandro Koerich, Simon Bacon, Eric Granger
State-of-the-art knowledge distillation (KD) methods have been proposed to distill multiple teacher models (each trained on a modality) to a common student model.
1 code implementation • 9 Dec 2023 • Muhammad Osama Zeeshan, Muhammad Haseeb Aslam, Soufiane Belharbi, Alessandro L. Koerich, Marco Pedersoli, Simon Bacon, Eric Granger
However, previous methods for MSDA adapt image classification models across datasets and do not scale well to a larger number of source domains.
Facial Expression Recognition Facial Expression Recognition (FER) +2
1 code implementation • 9 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.
1 code implementation • 16 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.
no code implementations • 9 Sep 2022 • Shakeeb Murtaza, Soufiane Belharbi, Marco Pedersoli, Aydin Sarraf, Eric Granger
In this paper, we propose a method to train deep weakly-supervised object localization (WSOL) models based only on image-class labels to locate object with high confidence.
no code implementations • 9 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.
1 code implementation • 30 Aug 2022 • Soufiane Belharbi, Ismail Ben Ayed, Luke McCaffrey, Eric Granger
Our proposed TCAM method achieves a new state-of-art in WSVOL accuracy, and visual results suggest that it can be adapted for subsequent tasks like visual object tracking and detection.
1 code implementation • 12 May 2022 • Soufiane Belharbi, Jérôme Rony, Jose Dolz, Ismail Ben Ayed, Luke McCaffrey, Eric Granger
Our method is composed of two networks: a localizer that yields segmentation mask, followed by a classifier.
1 code implementation • 7 Jan 2022 • Soufiane Belharbi, Marco Pedersoli, Ismail Ben Ayed, Luke McCaffrey, Eric Granger
The CNN is exploited to collect both positive and negative evidence at the pixel level to train the decoder.
1 code implementation • 15 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.
1 code implementation • 13 Apr 2021 • Madhu Kiran, R Gnana Praveen, Le Thanh Nguyen-Meidine, Soufiane Belharbi, Louis-Antoine Blais-Morin, Eric Granger
Hence, our proposed student-teacher framework is trained to address the occlusion problem by matching the distributions of between- and within-class distances (DCDs) of occluded samples with that of holistic (non-occluded) samples, thereby using the latter as a soft labeled reference to learn well separated DCDs.
2 code implementations • 14 Nov 2020 • Soufiane Belharbi, Jérôme Rony, Jose Dolz, Ismail Ben Ayed, Luke McCaffrey, Eric Granger
We propose novel regularization terms, which enable the model to seek both non-discriminative and discriminative regions, while discouraging unbalanced segmentations.
1 code implementation • 10 Oct 2020 • Soufiane Belharbi, Ismail Ben Ayed, Luke McCaffrey, Eric Granger
CNN visualization and interpretation methods, like class-activation maps (CAMs), are typically used to highlight the image regions linked to class predictions.
1 code implementation • 3 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.
1 code implementation • 25 Nov 2019 • Soufiane Belharbi, Ismail Ben Ayed, Luke McCaffrey, Eric Granger
We propose a new constrained-optimization formulation for deep ordinal classification, in which uni-modality of the label distribution is enforced implicitly via a set of inequality constraints over all the pairs of adjacent labels.
Ranked #1 on Historical Color Image Dating on HCI (MAE metric)
1 code implementation • 8 Sep 2019 • Jérôme Rony, Soufiane Belharbi, Jose Dolz, Ismail Ben Ayed, Luke McCaffrey, Eric Granger
Four key challenges are identified for the application of deep WSOL methods in histology -- under/over activation of CAMs, sensitivity to thresholding, and model selection.
1 code implementation • 25 Jul 2019 • Soufiane Belharbi, Jérôme Rony, Jose Dolz, Ismail Ben Ayed, Luke McCaffrey, Eric Granger
Pointwise localization allows more precise localization and accurate interpretability, compared to bounding box, in applications where objects are highly unstructured such as in medical domain.
1 code implementation • 13 Jul 2018 • Soufiane Belharbi
In this thesis, we tackle the neural network overfitting issue from a representation learning perspective by considering the situation where few training samples are available which is the case of many real world applications.
1 code implementation • 6 Sep 2017 • Soufiane Belharbi, Clément Chatelain, Romain Hérault, Sébastien Adam
In this work, we tackle the issue of training neural networks for classification task when few training samples are available.
1 code implementation • 28 Apr 2015 • Soufiane Belharbi, Romain Hérault, Clément Chatelain, Sébastien Adam
The motivation of this work is to learn the output dependencies that may lie in the output data in order to improve the prediction accuracy.