Search Results - "Pedersoli, Marco"

DeepProposal: Hunting Objects by Cascading Deep Convolutional Layers by Ghodrati, Amir, Diba, Ali, Pedersoli, Marco, Tuytelaars, Tinne, Van Gool, Luc

“…In this paper we evaluate the quality of the activation layers of a convolutional neural network (CNN) for the generation of object proposals. We generate…”
Get full text

Unsupervised Exemplar-Based Learning for Improved Document Image Classification by Abuelwafa, Sherif, Pedersoli, Marco, Cheriet, Mohamed

“…Many recent state-of-the-art approaches for document image classification are based on supervised feature learning that requires a large amount of labeled…”
Get full text

A coarse-to-fine approach for fast deformable object detection by Pedersoli, M., Vedaldi, A., Gonzalez, J.

“…We present a method that can dramatically accelerate object detection with part based models. The method is based on the observation that the cost of detection…”
Get full text

Deep co-training for semi-supervised image segmentation by Peng, Jizong, Estrada, Guillermo, Pedersoli, Marco, Desrosiers, Christian

“…•Semi-supervised semantic segmentation based on an ensemble of deep learning models.•All models are trained jointly in a co-training setting.•Coherence among…”
Get full text

Weakly supervised object detection with convex clustering by Bilen, Hakan, Pedersoli, Marco, Tuytelaars, Tinne

“…Weakly supervised object detection, is a challenging task, where the training procedure involves learning at the same time both, the model appearance and the…”
Get full text

Deep Clustering: On the Link Between Discriminative Models and K-Means by Jabi, Mohammed, Pedersoli, Marco, Mitiche, Amar, Ayed, Ismail Ben

“…In the context of recent deep clustering studies, discriminative models dominate the literature and report the most competitive performances. These models…”
Get full text

Areas of Attention for Image Captioning by Pedersoli, Marco, Lucas, Thomas, Schmid, Cordelia, Verbeek, Jakob

“…We propose "Areas of Attention", a novel attentionbased model for automatic image captioning. Our approach models the dependencies between image regions,…”
Get full text

DiPS: Discriminative pseudo-label sampling with self-supervised transformers for weakly supervised object localization by Murtaza, Shakeeb, Belharbi, Soufiane, Pedersoli, Marco, Sarraf, Aydin, Granger, Eric

“…Self-supervised vision transformers (SSTs) have shown great potential to yield rich localization maps that highlight different objects in an image. However,…”
Get full text

Boundary-aware information maximization for self-supervised medical image segmentation by Peng, Jizong, Wang, Ping, Pedersoli, Marco, Desrosiers, Christian

“…Self-supervised representation learning can boost the performance of a pre-trained network on downstream tasks for which labeled data is limited. A popular…”
Get full text

Self-paced and self-consistent co-training for semi-supervised image segmentation by Wang, Ping, Peng, Jizong, Pedersoli, Marco, Zhou, Yuanfeng, Zhang, Caiming, Desrosiers, Christian

“…•We propose, to our knowledge, the first self-paced co-training method for semi-supervised segmentation. We show that the proposed self-paced learning strategy…”
Get full text

CAT: Constrained Adversarial Training for Anatomically-plausible Semi-supervised Segmentation by Wang, Ping, Peng, Jizong, Pedersoli, Marco, Zhou, Yuanfeng, Zhang, Caiming, Desrosiers, Christian

“…Deep learning models for semi-supervised medical image segmentation have achieved unprecedented performance for a wide range of tasks. Despite their high…”
Get full text

A coarse-to-fine approach for fast deformable object detection by Pedersoli, Marco, Vedaldi, Andrea, Gonzàlez, Jordi, Roca, Xavier

“…We present a method that can dramatically accelerate object detection with part based models. The method is based on the observation that the cost of detection…”
Get full text

Discretely-constrained deep network for weakly supervised segmentation by Peng, Jizong, Kervadec, Hoel, Dolz, Jose, Ben Ayed, Ismail, Pedersoli, Marco, Desrosiers, Christian

“…An efficient strategy for weakly-supervised segmentation is to impose constraints or regularization priors on target regions. Recent efforts have focused on…”
Get full text

Shape-Aware Joint Distribution Alignment for Cross-Domain Image Segmentation by Wang, Ping, Peng, Jizong, Pedersoli, Marco, Zhou, Yuanfeng, Zhang, Caiming, Desrosiers, Christian

“…We present an unsupervised domain adaptation method for image segmentation which aligns high-order statistics, computed for the source and target domains,…”
Get full text

Incremental multi-target domain adaptation for object detection with efficient domain transfer by Nguyen-Meidine, Le Thanh, Kiran, Madhu, Pedersoli, Marco, Dolz, Jose, Blais-Morin, Louis-Antoine, Granger, Eric

“…•Unsupervised multi-target domain adaptation for object detection.•Formulate multi-target adaptation problem as an incremental adaptation problem.•Take…”
Get full text

Toward Real-Time Pedestrian Detection Based on a Deformable Template Model by Pedersoli, Marco, Gonzalez, Jordi, Xu Hu, Roca, Xavier

“…Most advanced driving assistance systems already include pedestrian detection systems. Unfortunately, there is still a tradeoff between precision and real…”
Get full text

DeepProposals: Hunting Objects and Actions by Cascading Deep Convolutional Layers by Ghodrati, Amir, Diba, Ali, Pedersoli, Marco, Tuytelaars, Tinne, Van Gool, Luc

“…In this paper, a new method for generating object and action proposals in images and videos is proposed. It builds on activations of different convolutional…”
Get full text

Camera Alignment and Weighted Contrastive Learning for Domain Adaptation in Video Person ReID by Mekhazni, Djebril, Dufau, Maximilien, Desrosiers, Christian, Pedersoli, Marco, Granger, Eric

“…Systems for person re-identification (ReID) can achieve a high accuracy when trained on large fully-labeled image datasets. However, the domain shift typically…”
Get full text

Augmented Lagrangian Adversarial Attacks by Rony, Jerome, Granger, Eric, Pedersoli, Marco, Ben Ayed, Ismail

“…Adversarial attack algorithms are dominated by penalty methods, which are slow in practice, or more efficient distance-customized methods, which are heavily…”
Get full text

On the Texture Bias for Few-Shot CNN Segmentation by Azad, Reza, Fayjie, Abdur R., Kauffmann, Claude, Ayed, Ismail Ben, Pedersoli, Marco, Dolz, Jose

“…Despite the initial belief that Convolutional Neural Networks (CNNs) are driven by shapes to perform visual recognition tasks, recent evidence suggests that…”
Get full text