Search Results for author:
Found 6 papers, 4 papers with code
GeoMask3D: Geometrically Informed Mask Selection for Self-Supervised Point Cloud Learning in 3D
We introduce a pioneering approach to self-supervised learning for point clouds, employing a geometrically informed mask selection strategy called GeoMask3D (GM3D) to boost the efficiency of Masked Auto Encoders (MAE).
CLIPArTT: Light-weight Adaptation of CLIP to New Domains at Test Time
In this study, we introduce CLIP Adaptation duRing Test-Time (CLIPArTT), a fully test-time adaptation (TTA) approach for CLIP, which involves automatic text prompts construction during inference for their use as text supervision.
NC-TTT: A Noise Contrastive Approach for Test-Time Training
Despite their exceptional performance in vision tasks, deep learning models often struggle when faced with domain shifts during testing.
ClusT3: Information Invariant Test-Time Training
Deep Learning models have shown remarkable performance in a broad range of vision tasks.
TFS-ViT: Token-Level Feature Stylization for Domain Generalization
This paper presents a first Token-level Feature Stylization (TFS-ViT) approach for domain generalization, which improves the performance of ViTs to unseen data by synthesizing new domains.
TTTFlow: Unsupervised Test-Time Training with Normalizing Flow
A major problem of deep neural networks for image classification is their vulnerability to domain changes at test-time.
