Search Results for author: Philippe Giguère

Found 25 papers, 14 papers with code

BoQ: A Place is Worth a Bag of Learnable Queries

1 code implementation CVPR 2024 Amar Ali-bey, Brahim Chaib-Draa, Philippe Giguère

In visual place recognition, accurately identifying and matching images of locations under varying environmental conditions and viewpoints remains a significant challenge.

Image Similarity Search Retrieval +1

Proprioception Is All You Need: Terrain Classification for Boreal Forests

1 code implementation25 Mar 2024 Damien LaRocque, William Guimont-Martin, David-Alexandre Duclos, Philippe Giguère, François Pomerleau

We show that the combination of two TC datasets yields a latent space that can be interpreted with the properties of the terrains.

 Ranked #1 on Time Series Classification on BorealTC (Accuracy (5-fold) metric)

Autonomous Navigation Time Series Classification

Global Proxy-based Hard Mining for Visual Place Recognition

1 code implementation28 Feb 2023 Amar Ali-bey, Brahim Chaib-Draa, Philippe Giguère

These proxy representations are thus used to construct a global index that encompasses the similarities between all places in the dataset, allowing for highly informative mini-batch sampling at each training iteration.

Image Retrieval Image Similarity Search +2

GSV-Cities: Toward Appropriate Supervised Visual Place Recognition

1 code implementation19 Oct 2022 Amar Ali-bey, Brahim Chaib-Draa, Philippe Giguère

This paper aims to investigate representation learning for large scale visual place recognition, which consists of determining the location depicted in a query image by referring to a database of reference images.

Image Retrieval Metric Learning +2

Training Deep Learning Algorithms on Synthetic Forest Images for Tree Detection

1 code implementation8 Oct 2022 Vincent Grondin, François Pomerleau, Philippe Giguère

In this work, we propose to use simulated forest environments to automatically generate 43 k realistic synthetic images with pixel-level annotations, and use it to train deep learning algorithms for tree detection.

Diversity object-detection +3

Instance Segmentation for Autonomous Log Grasping in Forestry Operations

1 code implementation3 Mar 2022 Jean-Michel Fortin, Olivier Gamache, Vincent Grondin, François Pomerleau, Philippe Giguère

Using our dataset, we then compare three neural network architectures on the task of individual logs detection and segmentation; two region-based methods and one attention-based method.

Inductive Bias Instance Segmentation +1

Stability analysis of SGD through the normalized loss function

no code implementations1 Jan 2021 Alexandre Lemire Paquin, Brahim Chaib-Draa, Philippe Giguère

We prove new generalization bounds for stochastic gradient descent for both the convex and non-convex case.

Generalization Bounds

The Indian Chefs Process

no code implementations29 Jan 2020 Patrick Dallaire, Luca Ambrogioni, Ludovic Trottier, Umut Güçlü, Max Hinne, Philippe Giguère, Brahim Chaib-Draa, Marcel van Gerven, Francois Laviolette

This paper introduces the Indian Chefs Process (ICP), a Bayesian nonparametric prior on the joint space of infinite directed acyclic graphs (DAGs) and orders that generalizes Indian Buffet Processes.

Tree bark re-identification using a deep-learning feature descriptor

1 code implementation6 Dec 2019 Martin Robert, Patrick Dallaire, Philippe Giguère

Oftentimes, it relies on collections of visual signatures based on descriptors, such as SIFT or SURF.

Deep Template-based Object Instance Detection

1 code implementation26 Nov 2019 Jean-Philippe Mercier, Mathieu Garon, Philippe Giguère, Jean-François Lalonde

In this context, we propose a generic 2D object instance detection approach that uses example viewpoints of the target object at test time to retrieve its 2D location in RGB images, without requiring any additional training (i. e. fine-tuning) step.

Object object-detection +2

Driving Datasets Literature Review

no code implementations26 Oct 2019 Charles-Éric Noël Laflamme, François Pomerleau, Philippe Giguère

This report is a survey of the different autonomous driving datasets which have been published up to date.

Autonomous Driving

On the implicit minimization of alternative loss functions when training deep networks

no code implementations25 Sep 2019 Alexandre Lemire Paquin, Brahim Chaib-Draa, Philippe Giguère

One approach to try to exploit such understanding would be to then make the bias explicit in the loss function.

Inductive Bias

ReFusion: 3D Reconstruction in Dynamic Environments for RGB-D Cameras Exploiting Residuals

1 code implementation6 May 2019 Emanuele Palazzolo, Jens Behley, Philipp Lottes, Philippe Giguère, Cyrill Stachniss

For localization and mapping, we employ an efficient direct tracking on the truncated signed distance function (TSDF) and leverage color information encoded in the TSDF to estimate the pose of the sensor.


GQ-STN: Optimizing One-Shot Grasp Detection based on Robustness Classifier

no code implementations6 Mar 2019 Alexandre Gariépy, Jean-Christophe Ruel, Brahim Chaib-Draa, Philippe Giguère

To this effect, we present Grasp Quality Spatial Transformer Network (GQ-STN), a one-shot grasp detection network.

Analysis of Robust Functions for Registration Algorithms

no code implementations2 Oct 2018 Philippe Babin, Philippe Giguère, François Pomerleau

However, without a large scale comparison of solutions to filter outliers, it is becoming tedious to select an appropriate algorithm for a given application.


CELLO-3D: Estimating the Covariance of ICP in the Real World

no code implementations2 Oct 2018 David Landry, François Pomerleau, Philippe Giguère

The fusion of Iterative Closest Point (ICP) reg- istrations in existing state estimation frameworks relies on an accurate estimation of their uncertainty.


Learning Object Localization and 6D Pose Estimation from Simulation and Weakly Labeled Real Images

no code implementations18 Jun 2018 Jean-Philippe Mercier, Chaitanya Mitash, Philippe Giguère, Abdeslam Boularias

We then show that the performance of the detector can be substantially improved by using a small set of weakly annotated real images, where a human provides only a list of objects present in each image without indicating the location of the objects.

6D Pose Estimation 6D Pose Estimation using RGB +4

Tree Species Identification from Bark Images Using Convolutional Neural Networks

2 code implementations2 Mar 2018 Mathieu Carpentier, Philippe Giguère, Jonathan Gaudreault

Tree species identification using bark images is a challenging problem that could prove useful for many forestry related tasks.

Dictionary Learning for Robotic Grasp Recognition and Detection

no code implementations2 Jun 2016 Ludovic Trottier, Philippe Giguère, Brahim Chaib-Draa

The ability to grasp ordinary and potentially never-seen objects is an important feature in both domestic and industrial robotics.

Dictionary Learning

Parametric Exponential Linear Unit for Deep Convolutional Neural Networks

no code implementations30 May 2016 Ludovic Trottier, Philippe Giguère, Brahim Chaib-Draa

Object recognition is an important task for improving the ability of visual systems to perform complex scene understanding.

Object Recognition Scene Understanding

Sign Language Fingerspelling Classification from Depth and Color Images using a Deep Belief Network

no code implementations19 Mar 2015 Lucas Rioux-Maldague, Philippe Giguère

We applied our technique to American Sign Language fingerspelling classification using a Deep Belief Network, for which our feature extraction technique is tailored.

General Classification Sign Language Recognition

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