Search Results for author:
Found 9 papers, 8 papers with code
Foundational Models for Continual Learning: An Empirical Study of Latent Replay
Motivated by this, we study the efficacy of pre-trained vision models as a foundation for downstream continual learning (CL) scenarios.
Multi-Head Distillation for Continual Unsupervised Domain Adaptation in Semantic Segmentation
Unsupervised Domain Adaptation (UDA) is a transfer learning task which aims at training on an unlabeled target domain by leveraging a labeled source domain.
DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion
Our strategy scales to a large number of tasks while having negligible memory and time overheads due to strict control of the parameters expansion.
Ranked #1 on
Incremental Learning
on ImageNet - 10 steps
Tackling Catastrophic Forgetting and Background Shift in Continual Semantic Segmentation
classes predicted by the old model to deal with background shift and avoid catastrophic forgetting of the old classes.
Ranked #3 on
Overlapped 15-1
on PASCAL VOC 2012
class-incremental learning
Continual Semantic Segmentation
+4
Continuum: Simple Management of Complex Continual Learning Scenarios
Those drifts might cause interferences in the trained model and knowledge learned on previous states of the data distribution might be forgotten.
PLOP: Learning without Forgetting for Continual Semantic Segmentation
classes predicted by the old model to deal with background shift and avoid catastrophic forgetting of the old classes.
Ranked #1 on
Domain 1-1
on Cityscapes val
class-incremental learning
Continual Semantic Segmentation
+15
CORE: Color Regression for Multiple Colors Fashion Garments
The second stage combines a colorname-attention (dependent of the detected color) with an object-attention (dependent of the clothing category) and finally weights a spatial pooling over the image pixels' RGB values.
Insights from the Future for Continual Learning
Continual learning aims to learn tasks sequentially, with (often severe) constraints on the storage of old learning samples, without suffering from catastrophic forgetting.
PODNet: Pooled Outputs Distillation for Small-Tasks Incremental Learning
Lifelong learning has attracted much attention, but existing works still struggle to fight catastrophic forgetting and accumulate knowledge over long stretches of incremental learning.
