Deep Learning
On Transfer of Adversarial Robustness from Pretraining to Downstream Tasks
This illustrates the dependence of the classifier on the representation's robustness, i.e., the predictor can only be robust if
H2RBox-v2: Incorporating Symmetry for Boosting Horizontal Box Supervised Oriented Object Detection Yi Y u 1, Xue Y ang
With the rapidly increasing demand for oriented object detection, e.g. in autonomous driving and remote sensing, the recently proposed paradigm involving
Deep Non-line-of-sight Imaging from Under-scanning Measurements
Moreover, the proposed method delivers impressive robustness at an extremely low scanning grid (i.e., 8
On Optimal Caching and Model Multiplexing for Large Model Inference
By combining a caching algorithm, namely Greedy Dual Size with Frequency (GDSF) or Least Expected Cost (LEC), with a model multiplexer, we achieve optimal rates in both offline and online settings.
