Search papers, labs, and topics across Lattice.
University of Science and Technology of China, National Key Laboratory of Deep Space Exploration, Deep Space Exploration Laboratory
3
0
5
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.
Soft pseudo-labels, theoretically equivalent to hard labels when perfectly calibrated, tank performance in cross-domain semantic segmentation, motivating a new calibration framework.
