Introduces BIP framework and GapGen generator to allocate and synthesize millions of non-colliding virtual face identities within gaps of the real face manifold.
An image is worth 16x16 words: Transformers for image recognition at scale
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Diversity-aware memory policies improve test-time adaptation performance most under constrained memory budgets and challenging non-i.i.d. streams.
citing papers explorer
-
Non-Colliding Biometric Identities for Digital Entities: Geometry, Capacity, and Million-Scale Virtual Identity Provisioning
Introduces BIP framework and GapGen generator to allocate and synthesize millions of non-colliding virtual face identities within gaps of the real face manifold.
-
GoTTA be Diverse: Rethinking Memory Policies for Test-Time Adaptation
Diversity-aware memory policies improve test-time adaptation performance most under constrained memory budgets and challenging non-i.i.d. streams.