V2 - Artclass

Three art history graduate students per image, with majority-vote labels. Inter-annotator agreement: Fleiss’ κ = 0.81 (style), 0.74 (subject).

ArtClass v2 utilizes a U-Net backbone operating in a latent space of $8 \times 8$ downsampling. The core innovation lies in the fine-tuning of the attention layers on the ArtClass-Corpus. artclass v2

[1] Original ArtClass authors. “Fine-grained artwork classification.” ICCV Workshops, 2019. [2] Tan et al. “OmniArt: A large-scale artistic benchmark.” ECCV, 2020. [3] Dosovitskiy et al. “An image is worth 16x16 words.” ICLR, 2021. Three art history graduate students per image, with

Due to its open-source nature, various community forks like Art Class Enhanced exist, offering integrated emulators and improved browser functionality. Technical Implementation CodeSandboxhttps://codesandbox.io proudparrot2/artclass-v2 - Codesandbox The core innovation lies in the fine-tuning of

: Advanced classes may cover 14 distinct types of paper crafts , including origami (folding) and kirigami (cutting/folding).

will be released at [anonymized for review].