A Metacognitive Framework for Test-Time Adaptation: Taxonomy and Research Challenges
A cognitive psychology perspective of Test-Time Adaptation: how adaptation should be designed and evaluated to be robust to real-world conditions.
Computer vision
Recognizing, generating, and inspecting images.
Papers on computer vision
A Metacognitive Perspective on Anomaly Detection with Vision Foundation Models
A metacognitive perspective on anomaly detection: a simpler scorer ranks defects better but decides worse until its threshold is recalibrated, so ranking and decisions should be evaluated separately.
Implicit Inversion turns CLIP into a Decoder
We turn the discriminative CLIP model into a generator capable of addressing multiple tasks, such as text-to-image synthesis, style transfer, and image editing, without fine-tuning.