Search papers, labs, and topics across Lattice.
University of Science and Technology of China
2
0
4
Adversarial images in CLIP reveal a consistent directional bias that can be exploited to enhance model robustness, leading to surprising cases where adversarial accuracy surpasses clean accuracy.
Achieve state-of-the-art category-level object pose estimation by unifying shape completion and pose reasoning, without relying on category-level shape priors.
