Search Results for author:
Found 9 papers, 7 papers with code
Rotary Position Embedding for Vision Transformer
This study provides a comprehensive analysis of RoPE when applied to ViTs, utilizing practical implementations of RoPE for 2D vision data.
SeiT++: Masked Token Modeling Improves Storage-efficient Training
A recent breakthrough by SeiT proposed the use of Vector-Quantized (VQ) feature vectors (i. e., tokens) as network inputs for vision classification.
SeiT: Storage-Efficient Vision Training with Tokens Using 1% of Pixel Storage
We need billion-scale images to achieve more generalizable and ground-breaking vision models, as well as massive dataset storage to ship the images (e. g., the LAION-4B dataset needs 240TB storage space).
Similarity of Neural Architectures using Adversarial Attack Transferability
In recent years, many deep neural architectures have been developed for image classification.
ECCV Caption: Correcting False Negatives by Collecting Machine-and-Human-verified Image-Caption Associations for MS-COCO
Image-Text matching (ITM) is a common task for evaluating the quality of Vision and Language (VL) models.
Few-shot Font Generation with Weakly Supervised Localized Representations
Existing methods learn to disentangle style and content elements by developing a universal style representation for each font style.
StyleAugment: Learning Texture De-biased Representations by Style Augmentation without Pre-defined Textures
Hence, StyleAugment let the model observe abundant confounding cues for each image by on-the-fly the augmentation strategy, while the augmented images are more realistic than artistic style transferred images.
Multiple Heads are Better than One: Few-shot Font Generation with Multiple Localized Experts
MX-Font extracts multiple style features not explicitly conditioned on component labels, but automatically by multiple experts to represent different local concepts, e. g., left-side sub-glyph.
Few-shot Font Generation with Localized Style Representations and Factorization
However, learning component-wise styles solely from reference glyphs is infeasible in the few-shot font generation scenario, when a target script has a large number of components, e. g., over 200 for Chinese.
