Search Results for author: Adrian Popescu

Found 20 papers, 9 papers with code

PlaStIL: Plastic and Stable Memory-Free Class-Incremental Learning

no code implementations14 Sep 2022 Grégoire Petit, Adrian Popescu, Eden Belouadah, David Picard, Bertrand Delezoide

Mainstream methods need to store two deep models since they integrate new classes using fine tuning with knowledge distillation from the previous incremental state.

Class Incremental Learning Incremental Learning +1

A Comparative Study of Calibration Methods for Imbalanced Class Incremental Learning

no code implementations1 Feb 2022 Umang Aggarwal, Adrian Popescu, Eden Belouadah, Céline Hudelot

Since memory is bounded, old classes are learned with fewer images than new classes and an imbalance due to incremental learning is added to the initial dataset imbalance.

Class Incremental Learning Incremental Learning +1

Optimizing Active Learning for Low Annotation Budgets

no code implementations18 Jan 2022 Umang Aggarwal, Adrian Popescu, Céline Hudelot

It consists in learning a model on a small amount of annotated data (annotation budget) and in choosing the best set of points to annotate in order to improve the previous model and gain in generalization.

Active Learning Transfer Learning

Dataset Knowledge Transfer for Class-Incremental Learning without Memory

1 code implementation16 Oct 2021 Habib Slim, Eden Belouadah, Adrian Popescu, Darian Onchis

We introduce a two-step learning process which allows the transfer of bias correction parameters between reference and target datasets.

Class Incremental Learning Incremental Learning +1

Face Verification with Challenging Imposters and Diversified Demographics

1 code implementation16 Oct 2021 Adrian Popescu, Liviu-Daniel Ştefan, Jérôme Deshayes-Chossart, Bogdan Ionescu

We introduce a series of design choices which address these challenges and make the dataset constitution and usage more sustainable and fairer.

Face Verification

Unveiling Real-Life Effects of Online Photo Sharing

1 code implementation24 Dec 2020 Van-Khoa Nguyen, Adrian Popescu, Jerome Deshayes-Chossart

The approach relies on three components: (1) a set of visual objects with associated situation impact ratings obtained by crowdsourcing, (2) a corresponding set of object detectors for mining users' photos and (3) a ground truth dataset made of 500 visual user profiles which are manually rated per situation.

A Comprehensive Study of Class Incremental Learning Algorithms for Visual Tasks

1 code implementation3 Nov 2020 Eden Belouadah, Adrian Popescu, Ioannis Kanellos

A second type of approaches fix the deep model size and introduce a mechanism whose objective is to ensure a good compromise between stability and plasticity of the model.

Class Incremental Learning Incremental Learning +1

Initial Classifier Weights Replay for Memoryless Class Incremental Learning

1 code implementation31 Aug 2020 Eden Belouadah, Adrian Popescu, Ioannis Kanellos

It leverages initial classifier weights which provide a strong representation of past classes because they are trained with all class data.

Class Incremental Learning Fairness +2

Active Class Incremental Learning for Imbalanced Datasets

1 code implementation25 Aug 2020 Eden Belouadah, Adrian Popescu, Umang Aggarwal, Léo Saci

Most existing algorithms make two strong hypotheses which reduce the realism of the incremental scenario: (1) new data are assumed to be readily annotated when streamed and (2) tests are run with balanced datasets while most real-life datasets are actually imbalanced.

Class Incremental Learning Incremental Learning +1

Webly Supervised Semantic Embeddings for Large Scale Zero-Shot Learning

no code implementations6 Aug 2020 Yannick Le Cacheux, Adrian Popescu, Hervé Le Borgne

When the number of classes is large, classes are usually represented by semantic class prototypes learned automatically from unannotated text collections.

Object Recognition Zero-Shot Learning

ScaIL: Classifier Weights Scaling for Class Incremental Learning

1 code implementation16 Jan 2020 Eden Belouadah, Adrian Popescu

The problem is non trivial if the agent runs on a limited computational budget and has a bounded memory of past data.

Class Incremental Learning Incremental Learning

DeeSIL: Deep-Shallow Incremental Learning

no code implementations20 Aug 2018 Eden Belouadah, Adrian Popescu

Incremental Learning (IL) is an interesting AI problem when the algorithm is assumed to work on a budget.

Incremental Learning Transfer Learning

On Deep Representation Learning from Noisy Web Images

no code implementations15 Dec 2015 Phong D. Vo, Alexandru Ginsca, Hervé Le Borgne, Adrian Popescu

The keep-growing content of Web images may be the next important data source to scale up deep neural networks, which recently obtained a great success in the ImageNet classification challenge and related tasks.

Representation Learning

Scalable domain adaptation of convolutional neural networks

no code implementations7 Dec 2015 Adrian Popescu, Etienne Gadeski, Hervé Le Borgne

Convolutional neural networks (CNNs) tend to become a standard approach to solve a wide array of computer vision problems.

Domain Adaptation

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