Search Results for author:
Found 37 papers, 3 papers with code
Few-Shot Object Detection with Sparse Context Transformers
Few-shot detection is a major task in pattern recognition which seeks to localize objects using models trained with few labeled data.
One-Shot Multi-Rate Pruning of Graph Convolutional Networks
In this paper, we devise a novel lightweight Graph Convolutional Network (GCN) design dubbed as Multi-Rate Magnitude Pruning (MRMP) that jointly trains network topology and weights.
Reinforcement-based Display-size Selection for Frugal Satellite Image Change Detection
Then, we further explore the potential of this objective function, by considering a reinforcement learning approach that finds the best combination of diversity, representativity and uncertainty as well as display-sizes through active learning iterations, leading to better generalization as shown through experiments in interactive satellite image change detection.
MonoProb: Self-Supervised Monocular Depth Estimation with Interpretable Uncertainty
Self-supervised monocular depth estimation methods aim to be used in critical applications such as autonomous vehicles for environment analysis.
Frugal Satellite Image Change Detection with Deep-Net Inversion
The main contribution resides in a novel adversarial model that allows learning the most representative, diverse and uncertain virtual exemplars (as inverted preimages of the trained DNNs) that challenge (the most) the trained DNNs, and this leads to a better re-estimate of these networks in the subsequent iterations of active learning.
Miniaturized Graph Convolutional Networks with Topologically Consistent Pruning
This method is known to be successful, but under very high pruning regimes, it suffers from topological inconsistency which renders the extracted subnetworks disconnected, and this hinders their generalization ability.
Budget-Aware Graph Convolutional Network Design using Probabilistic Magnitude Pruning
Extensive experiments conducted on the challenging task of skeleton-based recognition show a substantial gain of our lightweight GCNs particularly at very high pruning regimes.
Adversarial Virtual Exemplar Learning for Label-Frugal Satellite Image Change Detection
Our method is interactive and relies on a question and answer model which asks the oracle (user) questions about the most informative display (dubbed as virtual exemplars), and according to the user's responses, updates change detections.
Training Lightweight Graph Convolutional Networks with Phase-field Models
In this paper, we design lightweight graph convolutional networks (GCNs) using a particular class of regularizers, dubbed as phase-field models (PFMs).
Frugal Reinforcement-based Active Learning
The proposed approach is probabilistic and unifies all these criteria in a single objective function whose solution models the probability of relevance of samples (i. e., how critical) when learning a decision function.
Lightweight Graph Convolutional Networks with Topologically Consistent Magnitude Pruning
Experiments conducted on the challenging FPHA dataset show the substantial gain of our topologically consistent pruning method especially at very high pruning regimes.
Frugal Learning of Virtual Exemplars for Label-Efficient Satellite Image Change Detection
In this paper, we devise a novel interactive satellite image change detection algorithm based on active learning.
Reinforcement-based frugal learning for satellite image change detection
To further explore the potential of this objective function, we consider a reinforcement learning approach that finds the best combination of diversity, representativity and uncertainty, through active learning iterations, leading to better generalization as corroborated through experiments in interactive satellite image change detection.
Extracting Effective Subnetworks with Gumbel-Softmax
Pruning is a group of methods, which seeks to remove redundant or unnecessary weights or groups of weights in a network.
Learning Connectivity with Graph Convolutional Networks for Skeleton-based Action Recognition
Learning graph convolutional networks (GCNs) is an emerging field which aims at generalizing convolutional operations to arbitrary non-regular domains.
FFNB: Forgetting-Free Neural Blocks for Deep Continual Visual Learning
An intermediate class of methods, based on dynamic networks, has been proposed in the literature and provides a reasonable balance between task memorization and computational footprint.
Active learning for interactive satellite image change detection
We introduce in this paper a novel active learning algorithm for satellite image change detection.
Weight Reparametrization for Budget-Aware Network Pruning
In this paper, we introduce an "end-to-end" lightweight network design that achieves training and pruning simultaneously without fine-tuning.
Learning Chebyshev Basis in Graph Convolutional Networks for Skeleton-based Action Recognition
Spectral graph convolutional networks (GCNs) are particular deep models which aim at extending neural networks to arbitrary irregular domains.
Skeleton-based Hand-Gesture Recognition with Lightweight Graph Convolutional Networks
In this paper, we introduce a novel method that learns the topology (or connectivity) of input graphs as a part of GCN design.
Action Recognition with Kernel-based Graph Convolutional Networks
The latter makes it possible to design, via implicit kernel representations, convolutional graph filters in a high dimensional and more discriminating space without increasing the number of training parameters.
Image Annotation based on Deep Hierarchical Context Networks
Context modeling is one of the most fertile subfields of visual recognition which aims at designing discriminant image representations while incorporating their intrinsic and extrinsic relationships.
End-to-end training of deep kernel map networks for image classification
Deep kernel map networks have shown excellent performances in various classification problems including image annotation.
Action Recognition with Deep Multiple Aggregation Networks
While convolutional and fully connected operations have been widely studied in the literature, the design of pooling operations that handle action recognition, with different sources of temporal granularity in action categories, has comparatively received less attention, and existing solutions rely mainly on max or averaging operations.
Deep hierarchical pooling design for cross-granularity action recognition
In this paper, we introduce a novel hierarchical aggregation design that captures different levels of temporal granularity in action recognition.
Deep Context-Aware Kernel Networks
This architecture is fully determined by the solution of an objective function mixing a content term that captures the intrinsic similarity between data, a context criterion which models their structure and a regularization term that helps designing smooth kernel network representations.
Totally Deep Support Vector Machines
In this paper, we relax this constraint and allow the support vectors to be learned (instead of being fixed/taken from training data) in order to better fit a given classification task.
Human Action Recognition with Multi-Laplacian Graph Convolutional Networks
The main contribution of this method resides in a new design principle that learns graph-laplacians as convex combinations of other elementary laplacians each one dedicated to a particular topology of the input graphs.
MLGCN: Multi-Laplacian Graph Convolutional Networks for Human Action Recognition
We also introduce a novel pooling operator, on graphs, that proceeds in two steps: context-dependent node expansion is achieved, followed by a global average pooling; the strength of this two-step process resides in its ability to preserve the discrimination power of nodes while achieving permutation invariance.
Ranked #2 on
Skeleton Based Action Recognition
on SBU
Human Action Recognition with Deep Temporal Pyramids
Our solution is based on a tree-structured temporal pyramid that aggregates outputs of CNNs at different levels.
Finite State Machines for Semantic Scene Parsing and Segmentation
We introduce in this work a novel stochastic inference process, for scene annotation and object class segmentation, based on finite state machines (FSMs).
Canonical Correlation Analysis for Misaligned Satellite Image Change Detection
Canonical correlation analysis (CCA) is a statistical learning method that seeks to build view-independent latent representations from multi-view data.
Cascaded Coarse-to-Fine Deep Kernel Networks for Efficient Satellite Image Change Detection
The design principle of these reduced complexity networks is based on a variant of the cross-entropy criterion that reduces the complexity of the networks in the cascade while preserving all the positive responses of the original kernel network.
Learning Explicit Deep Representations from Deep Kernel Networks
This scheme has proven to be effective, but intractable when handling large-scale datasets especially when the depth of the trained networks increases; indeed, the complexity of evaluating these networks scales quadratically w. r. t.
Learning Deep Context-Network Architectures for Image Annotation
We apply this context and kernel learning framework to image classification using the challenging ImageCLEF Photo Annotation benchmark; the latter shows that our deep context learning provides highly effective kernels for image classification as corroborated through extensive experiments.
Graph Kernels based on High Order Graphlet Parsing and Hashing
In order to build our graph representation, we measure the distribution of these graphlets into a given graph, using particular hash functions that efficiently assign sampled graphlets into isomorphic sets with a very low probability of collision.
BIG-bench Machine Learning
Vocal Bursts Intensity Prediction
Stochastic Graphlet Embedding
In order to build our graph representation, we measure the distribution of these graphlets into a given graph, using particular hash functions that efficiently assign sampled graphlets into isomorphic sets with a very low probability of collision.
