213 citations · 226 across the 8 of their papers we have counts for
7 papers · 1 filter
MultIOD: Rehearsal-free Multihead Incremental Object Detector
Eden Belouadah, Arnaud Dapogny, Kevin Bailly
Class-Incremental learning (CIL) refers to the ability of artificial agents to integrate new classes as they appear in a stream. It is particularly interesting in evolving environm…
PlaStIL: Plastic and Stable Memory-Free Class-Incremental Learning
Grégoire Petit, Adrian Popescu, Eden Belouadah +2
Plasticity and stability are needed in class-incremental learning in order to learn from new data while preserving past knowledge. Due to catastrophic forgetting, finding a comprom…
Dataset Knowledge Transfer for Class-Incremental Learning without Memory
Habib Slim, Eden Belouadah, Adrian Popescu +1
Incremental learning enables artificial agents to learn from sequential data. While important progress was made by exploiting deep neural networks, incremental learning remains ver…
Initial Classifier Weights Replay for Memoryless Class Incremental Learning
Eden Belouadah, Adrian Popescu, Ioannis Kanellos
Incremental Learning (IL) is useful when artificial systems need to deal with streams of data and do not have access to all data at all times. The most challenging setting requires…
Active Class Incremental Learning for Imbalanced Datasets
Eden Belouadah, Adrian Popescu, Umang Aggarwal +1
Incremental Learning (IL) allows AI systems to adapt to streamed data. Most existing algorithms make two strong hypotheses which reduce the realism of the incremental scenario: (1)…
ScaIL: Classifier Weights Scaling for Class Incremental Learning
Eden Belouadah, Adrian Popescu
Incremental learning is useful if an AI agent needs to integrate data from a stream. The problem is non trivial if the agent runs on a limited computational budget and has a bounde…
DeeSIL: Deep-Shallow Incremental Learning
Eden Belouadah, Adrian Popescu
Incremental Learning (IL) is an interesting AI problem when the algorithm is assumed to work on a budget. This is especially true when IL is modeled using a deep learning approach,…