Search Results for author:
Found 24 papers, 9 papers with code
Avalanche: an End-to-End Library for Continual Learning
Learning continually from non-stationary data streams is a long-standing goal and a challenging problem in machine learning.
FeTrIL: Feature Translation for Exemplar-Free Class-Incremental Learning
Actual features of new classes and pseudo-features of past classes are fed into a linear classifier which is trained incrementally to discriminate between all classes.
ScaIL: Classifier Weights Scaling for Class Incremental Learning
The problem is non trivial if the agent runs on a limited computational budget and has a bounded memory of past data.
Active Class Incremental Learning for Imbalanced Datasets
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.
Initial Classifier Weights Replay for Memoryless Class Incremental Learning
It leverages initial classifier weights which provide a strong representation of past classes because they are trained with all class data.
A Comprehensive Study of Class Incremental Learning Algorithms for Visual Tasks
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.
Dataset Knowledge Transfer for Class-Incremental Learning without Memory
We introduce a two-step learning process which allows the transfer of bias correction parameters between reference and target datasets.
Face Verification with Challenging Imposters and Diversified Demographics
We introduce a series of design choices which address these challenges and make the dataset constitution and usage more sustainable and fairer.
Unveiling Real-Life Effects of Online Photo Sharing
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.
On Deep Representation Learning from Noisy Web Images
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.
Scalable domain adaptation of convolutional neural networks
Convolutional neural networks (CNNs) tend to become a standard approach to solve a wide array of computer vision problems.
DeeSIL: Deep-Shallow Incremental Learning
Incremental Learning (IL) is an interesting AI problem when the algorithm is assumed to work on a budget.
Webly Supervised Semantic Embeddings for Large Scale Zero-Shot Learning
When the number of classes is large, classes are usually represented by semantic class prototypes learned automatically from unannotated text collections.
Optimizing Active Learning for Low Annotation Budgets
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.
Minority Class Oriented Active Learning for Imbalanced Datasets
Here, we introduce a new active learning method which is designed for imbalanced datasets.
A Comparative Study of Calibration Methods for Imbalanced Class Incremental Learning
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.
PlaStIL: Plastic and Stable Memory-Free Class-Incremental Learning
Mainstream methods need to store two deep models since they integrate new classes using fine-tuning with knowledge distillation from the previous incremental state.
Don’t Burst Blindly: For a Better Use of Natural Language Processing to Fight Opinion Bubbles in News Recommendations
Online news consumption plays an important role in shaping the political opinions of citizens.
An Analysis of Initial Training Strategies for Exemplar-Free Class-Incremental Learning
Our main finding is that the initial training strategy is the dominant factor influencing the average incremental accuracy, but that the choice of CIL algorithm is more important in preventing forgetting.
Continual Learning: Applications and the Road Forward
Continual learning is a subfield of machine learning, which aims to allow machine learning models to continuously learn on new data, by accumulating knowledge without forgetting what was learned in the past.
FeTrIL++: Feature Translation for Exemplar-Free Class-Incremental Learning with Hill-Climbing
Exemplar-free class-incremental learning (EFCIL) poses significant challenges, primarily due to catastrophic forgetting, necessitating a delicate balance between stability and plasticity to accurately recognize both new and previous classes.
Recommendation of data-free class-incremental learning algorithms by simulating future data
Our method outperforms competitive baselines, and performance is close to that of an oracle choosing the best algorithm in each setting.
