Search papers, labs, and topics across Lattice.
German Research Center for Artificial Intelligence (DFKI)
3
0
4
Continual learning for anomaly detection can now effectively handle heterogeneous data without succumbing to catastrophic forgetting or performance drops.
Image classification accuracy jumps by nearly 3% simply by whispering text embeddings into the ear of a vision model during training.
Stunning visuals from the latest text-to-image models don't guarantee better training data -- in fact, they can make your image classifiers *worse*.
