ArcVQ-VAE constrains VQ-VAE codebook vectors inside a time-dependent ball and adds angular margin loss to increase separability and codebook utilization.
As shown in Table 12, fixing M(t) = 1 throughout training still improves over vanilla VQ-V AE
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ArcVQ-VAE: A Spherical Vector Quantization Framework with ArcCosine Additive Margin
ArcVQ-VAE constrains VQ-VAE codebook vectors inside a time-dependent ball and adds angular margin loss to increase separability and codebook utilization.