Specifically, the proposed method aims to learn arbitrary image-to-text mapping for pseudo-labeling of arbitrary concepts, named Pseudo-Labeling for Arbitrary Concepts (PLAC).
Existing open-world segmentation methods have shown impressive advances by employing contrastive learning (CL) to learn diverse visual concepts and transferring the learned image-level understanding to the segmentation task.
Domain generalization (DG) aims to learn a generalized model to an unseen target domain using only limited source domains.
Ranked #2 on Domain Generalization on TerraIncognita
Existing methods learn to disentangle style and content elements by developing a universal style representation for each font style.
Compared to previous works, our method shows better or comparable performance on dense prediction fine-tuning tasks.
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.
Domain generalization (DG) methods aim to achieve generalizability to an unseen target domain by using only training data from the source domains.
Ranked #16 on Domain Generalization on TerraIncognita
This paper introduces a method that efficiently reduces the computational cost and parameter size of Transformer.
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.
By utilizing the compositionality of compositional scripts, we propose a novel font generation framework, named Dual Memory-augmented Font Generation Network (DM-Font), which enables us to generate a high-quality font library with only a few samples.
When compared to Transformers with a comparable number of parameters and time complexity, the proposed model shows better performance.