20 citations · 40 across the 46 of their papers we have counts for
46 papers · 1 filter
Multi-label Classification with Panoptic Context Aggregation Networks
Mingyuan Jiu, Hailong Zhu, Wenchuan Wei +3
Context modeling is crucial for visual recognition, enabling highly discriminative image representations by integrating both intrinsic and extrinsic relationships between objects a…
Active Learning for GCN-based Action Recognition
Hichem Sahbi
Despite the notable success of graph convolutional networks (GCNs) in skeleton-based action recognition, their performance often depends on large volumes of labeled data, which are…
Label-Efficient Skeleton-based Recognition with Stable-Invertible Graph Convolutional Networks
Hichem Sahbi
Skeleton-based action recognition is a hotspot in image processing. A key challenge of this task lies in its dependence on large, manually labeled datasets whose acquisition is cos…
Image augmentation with invertible networks in interactive satellite image change detection
Hichem Sahbi
This paper devises a novel interactive satellite image change detection algorithm based on active learning. Our framework employs an iterative process that leverages a question-and…
Label-frugal satellite image change detection with generative virtual exemplar learning
Hichem Sahbi
Change detection is a major task in remote sensing which consists in finding all the occurrences of changes in multi-temporal satellite or aerial images. The success of existing me…
Deep Generative Continual Learning using Functional LoRA: FunLoRA
Victor Enescu, Hichem Sahbi
Continual adaptation of deep generative models holds tremendous potential and critical importance, given their rapid and expanding usage in text and vision based applications. Incr…
Frugal Incremental Generative Modeling using Variational Autoencoders
Victor Enescu, Hichem Sahbi
Continual or incremental learning holds tremendous potential in deep learning with different challenges including catastrophic forgetting. The advent of powerful foundation and gen…
Image Classification with Deep Reinforcement Active Learning
Mingyuan Jiu, Xuguang Song, Hichem Sahbi +5
Deep learning is currently reaching outstanding performances on different tasks, including image classification, especially when using large neural networks. The success of these m…
Multi-label Classification using Deep Multi-order Context-aware Kernel Networks
Mingyuan Jiu, Hailong Zhu, Hichem Sahbi
Multi-label classification is a challenging task in pattern recognition. Many deep learning methods have been proposed and largely enhanced classification performance. However, mos…
Learning Coarse-to-Fine Pruning of Graph Convolutional Networks for Skeleton-based Recognition
Hichem Sahbi
Magnitude Pruning is a staple lightweight network design method which seeks to remove connections with the smallest magnitude. This process is either achieved in a structured or un…
Designing Semi-Structured Pruning of Graph Convolutional Networks for Skeleton-based Recognition
Hichem Sahbi
Deep neural networks (DNNs) are nowadays witnessing a major success in solving many pattern recognition tasks including skeleton-based classification. The deployment of DNNs on edg…
Few-Shot Object Detection with Sparse Context Transformers
Jie Mei, Mingyuan Jiu, Hichem Sahbi +2
Few-shot detection is a major task in pattern recognition which seeks to localize objects using models trained with few labeled data. One of the mainstream few-shot methods is tran…
One-Shot Multi-Rate Pruning of Graph Convolutional Networks
Hichem Sahbi
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
Hichem Sahbi
We introduce a novel interactive satellite image change detection algorithm based on active learning. The proposed method is iterative and consists in frugally probing the user (or…
MonoProb: Self-Supervised Monocular Depth Estimation with Interpretable Uncertainty
Rémi Marsal, Florian Chabot, Angelique Loesch +2
Self-supervised monocular depth estimation methods aim to be used in critical applications such as autonomous vehicles for environment analysis. To circumvent the potential imperfe…
Frugal Satellite Image Change Detection with Deep-Net Inversion
Hichem Sahbi, Sebastien Deschamps
Change detection in satellite imagery seeks to find occurrences of targeted changes in a given scene taken at different instants. This task has several applications ranging from la…
Miniaturized Graph Convolutional Networks with Topologically Consistent Pruning
Hichem Sahbi
Magnitude pruning is one of the mainstream methods in lightweight architecture design whose goal is to extract subnetworks with the largest weight connections. This method is known…
Budget-Aware Graph Convolutional Network Design using Probabilistic Magnitude Pruning
Hichem Sahbi
Graph convolutional networks (GCNs) are nowadays becoming mainstream in solving many image processing tasks including skeleton-based recognition. Their general recipe consists in l…
Adversarial Virtual Exemplar Learning for Label-Frugal Satellite Image Change Detection
Hichem Sahbi, Sebastien Deschamps
Satellite image change detection aims at finding occurrences of targeted changes in a given scene taken at different instants. This task is highly challenging due to the acquisitio…
Training Lightweight Graph Convolutional Networks with Phase-field Models
Hichem Sahbi
In this paper, we design lightweight graph convolutional networks (GCNs) using a particular class of regularizers, dubbed as phase-field models (PFMs). PFMs exhibit a bi-phase beha…
Frugal Reinforcement-based Active Learning
Sebastien Deschamps, Hichem Sahbi
Most of the existing learning models, particularly deep neural networks, are reliant on large datasets whose hand-labeling is expensive and time demanding. A current trend is to ma…
Reinforcement-based frugal learning for satellite image change detection
Sebastien Deschamps, Hichem Sahbi
In this paper, we introduce a novel interactive satellite image change detection algorithm based on active learning. The proposed approach is iterative and asks the user (oracle) q…
Frugal Learning of Virtual Exemplars for Label-Efficient Satellite Image Change Detection
Hichem Sahbi, Sebastien Deschamps
In this paper, we devise a novel interactive satellite image change detection algorithm based on active learning. The proposed framework is iterative and relies on a question and a…
Extracting Effective Subnetworks with Gumbel-Softmax
Robin Dupont, Mohammed Amine Alaoui, Hichem Sahbi +1
Large and performant neural networks are often overparameterized and can be drastically reduced in size and complexity thanks to pruning. Pruning is a group of methods, which seeks…