all AI news
Intriguing properties of generative classifiers
Feb. 15, 2024, 5:43 a.m. | Priyank Jaini, Kevin Clark, Robert Geirhos
cs.LG updates on arXiv.org arxiv.org
Abstract: What is the best paradigm to recognize objects -- discriminative inference (fast but potentially prone to shortcut learning) or using a generative model (slow but potentially more robust)? We build on recent advances in generative modeling that turn text-to-image models into classifiers. This allows us to study their behavior and to compare them against discriminative models and human psychophysical data. We report four intriguing emergent properties of generative classifiers: they show a record-breaking human-like shape …
abstract advances arxiv behavior build classifiers cs.ai cs.cv cs.lg generative generative modeling image inference modeling objects paradigm q-bio.nc robust shortcut stat.ml study text text-to-image type
More from arxiv.org / cs.LG updates on arXiv.org
Testing the Segment Anything Model on radiology data
1 day, 3 hours ago |
arxiv.org
Calorimeter shower superresolution
1 day, 3 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Software Engineer for AI Training Data (School Specific)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Python)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Tier 2)
@ G2i Inc | Remote
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US