Search Results for author:
Found 21 papers, 4 papers with code
Dynamic Y-KD: A Hybrid Approach to Continual Instance Segmentation
In this paper, our contributions for continual instance segmentation are threefold.
MixVPR: Feature Mixing for Visual Place Recognition
It refers to the process of identifying a place depicted in a query image using only computer vision.
Ranked #2 on
Visual Place Recognition
on SPED
Global Proxy-based Hard Mining for Visual Place Recognition
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.
Ranked #5 on
Visual Place Recognition
on Nordland
GSV-Cities: Toward Appropriate Supervised Visual Place Recognition
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.
Ranked #5 on
Visual Place Recognition
on Pittsburgh-250k-test
Multi-task Learning by Leveraging the Semantic Information
To confirm the effectiveness of the proposed method, we first compare the algorithm with several baselines on some benchmarks and then test the algorithms under label space shift conditions.
Stability analysis of SGD through the normalized loss function
We prove new generalization bounds for stochastic gradient descent for both the convex and non-convex case.
Domain Generalization via Optimal Transport with Metric Similarity Learning
Previous domain generalization approaches mainly focused on learning invariant features and stacking the learned features from each source domain to generalize to a new target domain while ignoring the label information, which will lead to indistinguishable features with an ambiguous classification boundary.
Discriminative Active Learning for Domain Adaptation
To this end, we introduce a discriminative active learning approach for domain adaptation to reduce the efforts of data annotation.
The Indian Chefs Process
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.
Towards Contextual Learning in Few-shot Object Classification
Inspired by the concept of contextual learning in educational sciences, we propose to make a step towards adopting this principle in FSL by studying the contribution that context can have in object classification in a low-data regime.
On the implicit minimization of alternative loss functions when training deep networks
One approach to try to exploit such understanding would be to then make the bias explicit in the loss function.
GQ-STN: Optimizing One-Shot Grasp Detection based on Robustness Classifier
To this effect, we present Grasp Quality Spatial Transformer Network (GQ-STN), a one-shot grasp detection network.
Generative Adversarial Positive-Unlabelled Learning
However, given limited P data, the conventional PU models tend to suffer from overfitting when adapted to very flexible deep neural networks.
Multi-Task Learning by Deep Collaboration and Application in Facial Landmark Detection
We show that CNNs connected with our Deep Collaboration obtain better accuracy on facial landmark detection with related tasks.
Dictionary Learning for Robotic Grasp Recognition and Detection
The ability to grasp ordinary and potentially never-seen objects is an important feature in both domestic and industrial robotics.
Parametric Exponential Linear Unit for Deep Convolutional Neural Networks
Object recognition is an important task for improving the ability of visual systems to perform complex scene understanding.
Online Planning Algorithms for POMDPs
Partially Observable Markov Decision Processes (POMDPs) provide a rich framework for sequential decision-making under uncertainty in stochastic domains.
A Marginalized Particle Gaussian Process Regression
We present a novel marginalized particle Gaussian process (MPGP) regression, which provides a fast, accurate online Bayesian filtering framework to model the latent function.
Bootstrapping Apprenticeship Learning
We consider the problem of apprenticeship learning where the examples, demonstrated by an expert, cover only a small part of a large state space.
Theoretical Analysis of Heuristic Search Methods for Online POMDPs
The algorithm uses search heuristics based on an error analysis of lookahead search, to guide the online search towards reachable beliefs with the most potential to reduce error.
