Scaling the Number of Tasks in Continual Learning
By Timothée Lesort, Oleksiy Ostapenko, Diganta Misra, Md Rifat Arefin, P. Rodr'iguez, Laurent Charlin, Irina Rish. 2022
10 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Rahaf Aljundi
- Daniel Soudry
- Mohamed Elhoseiny
- Tinne Tuytelaars
- René Vidal
- Nati Srebro
- Richard E. Turner
- Yoshua Bengio
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Dacheng Tao
- Rahaf Aljundi
- Trevor Darrell
- Jitendra Malik
- Andrea Vedaldi
- Jiashi Feng
- Bernt Schiele
Citations in the corpus
- The Ideal Continual Learner: An Agent That Never Forgets (2023, background): “In the current deep continual learning practice, though, T is of the constant order, e.g., T ≤ 1000 (Lesort et al., 2022).”
- First Session Adaptation: A Strong Replay-Free Baseline for Class-Incremental Learning (2023, methodology): “Current SOTA methods for class incremental learning start from a pre-trained backbone [13, 19, 35, 34] and then adapt the features at each session of continual learning.”
- A Simple Baseline that Questions the Use of Pretrained-Models in Continual Learning (2022, background): “[12] empirically analyzed the effect of training the last layer with a fixed feature extractor.”
- Continual Learning in Linear Classification on Separable Data (2023, background): “Several recent papers have observed empirically that task repetitions mitigate catastrophic forgetting in continual learning (Stojanov et al., 2019; Cossu et al., 2022), even when training is performed with vanilla SGD, without any forgetting-preventing method (Lesort et al., 2022).”