Three frameworks adapt foundation models for generalized category discovery under domain shifts via disentanglement and prompt tuning, showing gains on synthetic and real multi-domain data.
Benchmarking neural network robustness to common corruptions and perturbations
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2roles
dataset 1polarities
use dataset 1representative citing papers
EVT improves Vision Transformers by using Euclidean distance decay for spatial priors and simpler grouping, achieving 86.6% top-1 accuracy on ImageNet-1k.
citing papers explorer
-
Generalized Category Discovery under Domain Shifts: From Vision to Vision-Language Models
Three frameworks adapt foundation models for generalized category discovery under domain shifts via disentanglement and prompt tuning, showing gains on synthetic and real multi-domain data.
-
Advancing Vision Transformer with Enhanced Spatial Priors
EVT improves Vision Transformers by using Euclidean distance decay for spatial priors and simpler grouping, achieving 86.6% top-1 accuracy on ImageNet-1k.