Search Results - "Perez, Patrick"

Boosting Few-Shot Visual Learning With Self-Supervision by Gidaris, Spyros, Bursuc, Andrei, Komodakis, Nikos, Perez, Patrick Perez, Cord, Matthieu

“…Few-shot learning and self-supervised learning address different facets of the same problem: how to train a model with little or no labeled data. Few-shot…”
Get full text

Explainability of Deep Vision-Based Autonomous Driving Systems: Review and Challenges by Zablocki, Éloi, Ben-Younes, Hédi, Pérez, Patrick, Cord, Matthieu

“…This survey reviews explainability methods for vision-based self-driving systems trained with behavior cloning. The concept of explainability has several…”
Get full text

Adversarial frontier stitching for remote neural network watermarking by Le Merrer, Erwan, Pérez, Patrick, Trédan, Gilles

“…The state-of-the-art performance of deep learning models comes at a high cost for companies and institutions, due to the tedious data collection and the heavy…”
Get full text

DADA: Depth-Aware Domain Adaptation in Semantic Segmentation by Vu, Tuan-Hung, Jain, Himalaya, Bucher, Maxime, Cord, Matthieu, Perez, Patrick Perez

“…Unsupervised domain adaptation (UDA) is important for applications where large scale annotation of representative data is challenging. For semantic…”
Get full text

View-Independent Action Recognition from Temporal Self-Similarities by Junejo, I N, Dexter, E, Laptev, I, Pérez, Patrick

“…This paper addresses recognition of human actions under view changes. We explore self-similarities of action sequences over time and observe the striking…”
Get full text

Deep Reinforcement Learning for Autonomous Driving: A Survey by Kiran, B Ravi, Sobh, Ibrahim, Talpaert, Victor, Mannion, Patrick, Sallab, Ahmad A. Al, Yogamani, Senthil, Perez, Patrick

“…With the development of deep representation learning, the domain of reinforcement learning (RL) has become a powerful learning framework now capable of…”
Get full text

Finding Beans in Burgers: Deep Semantic-Visual Embedding with Localization by Engilberge, Martin, Chevallier, Louis, Perez, Patrick, Cord, Matthieu

“…Several works have proposed to learn a two-path neural network that maps images and texts, respectively, to a same shared Euclidean space where geometry…”
Get full text

Driving behavior explanation with multi-level fusion by Ben-Younes, Hédi, Zablocki, Éloi, Pérez, Patrick, Cord, Matthieu

“…•A deep architecture, called BEEF, explains the behavior of a trajectory prediction model, in an online fashion.•The core module discovers fine-grained…”
Get full text

Aggregating Local Image Descriptors into Compact Codes by Jegou, H., Perronnin, F., Douze, M., Sanchez, J., Perez, P., Schmid, C.

“…This paper addresses the problem of large-scale image search. Three constraints have to be taken into account: search accuracy, efficiency, and memory usage…”
Get full text

Cross-Modal Learning for Domain Adaptation in 3D Semantic Segmentation by Jaritz, Maximilian, Vu, Tuan-Hung, de Charette, Raoul, Wirbel, Emilie, Perez, Patrick

“…Domain adaptation is an important task to enable learning when labels are scarce. While most works focus only on the image modality, there are many important…”
Get full text

Solving Time-Domain Audio Inverse Problems Using Nonnegative Tensor Factorization by Bilen, Cagdas, Ozerov, Alexey, Perez, Patrick

“…Nonnegative matrix factorization (NMF) and nonnegative tensor factorization (NTF) are important tools for modeling nonnegative data, which gained increasing…”
Get full text

Confidence Estimation via Auxiliary Models by Corbiere, Charles, Thome, Nicolas, Saporta, Antoine, Vu, Tuan-Hung, Cord, Matthieu, Perez, Patrick

“…Reliably quantifying the confidence of deep neural classifiers is a challenging yet fundamental requirement for deploying such models in safety-critical…”
Get full text

LiDARTouch: Monocular metric depth estimation with a few-beam LiDAR by Bartoccioni, Florent, Zablocki, Éloi, Pérez, Patrick, Cord, Matthieu, Alahari, Karteek

“…Vision-based depth estimation is a key feature in autonomous systems, which often relies on a single camera or several independent ones. In such a monocular…”
Get full text

CARRADA Dataset: Camera and Automotive Radar with Range- Angle- Doppler Annotations by Ouaknine, Arthur, Newson, Alasdair, Rebut, Julien, Tupin, Florence, Perez, Patrick

“…High quality perception is essential for autonomous driving (AD) systems. To reach the accuracy and robustness thatare required by such systems, several types…”
Get full text

OBoW: Online Bag-of-Visual-Words Generation for Self-Supervised Learning by Gidaris, Spyros, Bursuc, Andrei, Puy, Gilles, Komodakis, Nikos, Cord, Matthieu, Perez, Patrick

“…Learning image representations without human supervision is an important and active research field. Several recent approaches have successfully leveraged the…”
Get full text

Spherical perspective on learning with normalization layers by Roburin, Simon, de Mont-Marin, Yann, Bursuc, Andrei, Marlet, Renaud, Pérez, Patrick, Aubry, Mathieu

“…Normalization Layers (NLs) are widely used in modern deep-learning architectures. Despite their apparent simplicity, their effect on optimization is not yet…”
Get full text

Aggregating local descriptors into a compact image representation by Jégou, H, Douze, M, Schmid, C, Pérez, P

“…We address the problem of image search on a very large scale, where three constraints have to be considered jointly: the accuracy of the search, its…”
Get full text

Handling new target classes in semantic segmentation with domain adaptation by Bucher, Maxime, Vu, Tuan-Hung, Cord, Matthieu, Pérez, Patrick

“…In this work, we define and address a novel domain adaptation (DA) problem in semantic scene segmentation, where the target domain not only exhibits a data…”
Get full text

Automatic Face Reenactment by Garrido, Pablo, Valgaerts, Levi, Rehmsen, Ole, Thormaehlen, Thorsten, Perez, Patrick, Theobalt, Christian

“…We propose an image-based, facial reenactment system that replaces the face of an actor in an existing target video with the face of a user from a source…”
Get full text

Region filling and object removal by exemplar-based image inpainting by Criminisi, A., Perez, P., Toyama, K.

“…A new algorithm is proposed for removing large objects from digital images. The challenge is to fill in the hole that is left behind in a visually plausible…”
Get full text