584 citations · 1.1k across the 43 of their papers we have counts for
10 papers · 1 filter
Exemplar-free Continual Learning of Vision Transformers via Gated Class-Attention and Cascaded Feature Drift Compensation
Marco Cotogni, Fei Yang, Claudio Cusano +2
We propose a new method for exemplar-free class incremental training of ViTs. The main challenge of exemplar-free continual learning is maintaining plasticity of the learner withou…
Attribution-aware Weight Transfer: A Warm-Start Initialization for Class-Incremental Semantic Segmentation
Dipam Goswami, René Schuster, Joost van de Weijer +1
In class-incremental semantic segmentation (CISS), deep learning architectures suffer from the critical problems of catastrophic forgetting and semantic background shift. Although…
Positive Pair Distillation Considered Harmful: Continual Meta Metric Learning for Lifelong Object Re-Identification
Kai Wang, Chenshen Wu, Andy Bagdanov +4
Lifelong object re-identification incrementally learns from a stream of re-identification tasks. The objective is to learn a representation that can be applied to all tasks and tha…
Attention Distillation: self-supervised vision transformer students need more guidance
Kai Wang, Fei Yang, Joost van de Weijer
Self-supervised learning has been widely applied to train high-quality vision transformers. Unleashing their excellent performance on memory and compute constraint devices is there…
OneRing: A Simple Method for Source-free Open-partial Domain Adaptation
Shiqi Yang, Yaxing Wang, Kai Wang +2
In this paper, we investigate Source-free Open-partial Domain Adaptation (SF-OPDA), which addresses the situation where there exist both domain and category shifts between source a…
MVMO: A Multi-Object Dataset for Wide Baseline Multi-View Semantic Segmentation
Aitor Alvarez-Gila, Joost van de Weijer, Yaxing Wang +1
We present MVMO (Multi-View, Multi-Object dataset): a synthetic dataset of 116,000 scenes containing randomly placed objects of 10 distinct classes and captured from 25 camera loca…