most citedDivide and not forget: Ensemble of selectively trained experts in Continual Learning

11 citations · 11 across the 2 of their papers we have counts for

collaborators

7 papers

cs.LG2024

A deep cut into Split Federated Self-supervised Learning

Marcin Przewięźlikowski, Marcin Osial, Bartosz Zieliński +1

Collaborative self-supervised learning has recently become feasible in highly distributed environments by dividing the network layers between client devices and a central server. H…

cs.CV2024

LucidPPN: Unambiguous Prototypical Parts Network for User-centric Interpretable Computer Vision

Mateusz Pach, Dawid Rymarczyk, Koryna Lewandowska +2

Prototypical parts networks combine the power of deep learning with the explainability of case-based reasoning to make accurate, interpretable decisions. They follow the this looks…

cs.CV2024

AdaGlimpse: Active Visual Exploration with Arbitrary Glimpse Position and Scale

Adam Pardyl, Michał Wronka, Maciej Wołczyk +3

Active Visual Exploration (AVE) is a task that involves dynamically selecting observations (glimpses), which is critical to facilitate comprehension and navigation within an enviro…

cs.LG202411 cited

Divide and not forget: Ensemble of selectively trained experts in Continual Learning

Grzegorz Rypeść, Sebastian Cygert, Valeriya Khan +3

Class-incremental learning is becoming more popular as it helps models widen their applicability while not forgetting what they already know. A trend in this area is to use a mixtu…

cs.LG2023

TORE: Token Recycling in Vision Transformers for Efficient Active Visual Exploration

Jan Olszewski, Dawid Rymarczyk, Piotr Wójcik +2

Active Visual Exploration (AVE) optimizes the utilization of robotic resources in real-world scenarios by sequentially selecting the most informative observations. However, modern…

cs.CV2023

Beyond Grids: Exploring Elastic Input Sampling for Vision Transformers

Adam Pardyl, Grzegorz Kurzejamski, Jan Olszewski +2

Vision transformers have excelled in various computer vision tasks but mostly rely on rigid input sampling using a fixed-size grid of patches. It limits their applicability in real…