Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Jeeveswaran, Kishaan"'
Domain incremental learning (DIL) poses a significant challenge in real-world scenarios, as models need to be sequentially trained on diverse domains over time, all the while avoiding catastrophic forgetting. Mitigating representation drift, which re
Externí odkaz:
http://arxiv.org/abs/2406.16231
The ability of deep neural networks to continually learn and adapt to a sequence of tasks has remained challenging due to catastrophic forgetting of previously learned tasks. Humans, on the other hand, have a remarkable ability to acquire, assimilate
Externí odkaz:
http://arxiv.org/abs/2305.04769
Self-supervised monocular depth estimation is a salient task for 3D scene understanding. Learned jointly with monocular ego-motion estimation, several methods have been proposed to predict accurate pixel-wise depth without using labeled data. Neverth
Externí odkaz:
http://arxiv.org/abs/2210.02357
Autor:
Jeeveswaran, Kishaan, Kathiresan, Senthilkumar, Varma, Arnav, Magdy, Omar, Zonooz, Bahram, Arani, Elahe
Convolutional Neural Networks (CNNs), architectures consisting of convolutional layers, have been the standard choice in vision tasks. Recent studies have shown that Vision Transformers (VTs), architectures based on self-attention modules, achieve co
Externí odkaz:
http://arxiv.org/abs/2201.08683