Search papers, labs, and topics across Lattice.
Universit茅 Paris-Saclay
2
0
5
Controllable diffusion models can be trained twice as fast and achieve better image quality simply by directly supervising the clean target image during training.
Transformer-based object detectors are surprisingly resistant to adversarial attacks crafted for CNNs, but can be hardened further by training against a diverse "cocktail" of strong attacks.
