Search Results for author:
Found 10 papers, 4 papers with code
Adversarial Purification and Fine-tuning for Robust UDC Image Restoration
This study delves into the enhancement of Under-Display Camera (UDC) image restoration models, focusing on their robustness against adversarial attacks.
Benchmarking Ultra-High-Definition Image Reflection Removal
To the best of our knowledge, these two datasets are the first largest-scale UHD datasets for SIRR.
RWKV: Reinventing RNNs for the Transformer Era
This work presents a significant step towards reconciling trade-offs between computational efficiency and model performance in sequence processing tasks.
Ranked #22 on
Natural Language Inference
on WNLI
Composite Sorting
We completely characterize optimal sorting and additionally show it is more positive when mismatch costs are less concave.
Robust Single Image Reflection Removal Against Adversarial Attacks
This paper addresses the problem of robust deep single-image reflection removal (SIRR) against adversarial attacks.
Ranked #2 on
Reflection Removal
on Real20
FedDTG:Federated Data-Free Knowledge Distillation via Three-Player Generative Adversarial Networks
This technique mitigates the user heterogeneity problem and better protects user privacy.
Simultaneous Optimal Transport
We propose a general framework of mass transport between vector-valued measures, which will be called simultaneous optimal transport (SOT).
Sparse-softmax: A Simpler and Faster Alternative Softmax Transformation
The softmax function is widely used in artificial neural networks for the multiclass classification problems, where the softmax transformation enforces the output to be positive and sum to one, and the corresponding loss function allows to use maximum likelihood principle to optimize the model.
A limit theorem for Bernoulli convolutions and the $Φ$-variation of functions in the Takagi class
We consider a probabilistic approach to compute the Wiener--Young $\Phi$-variation of fractal functions in the Takagi class.
Probability Classical Analysis and ODEs
TAMPC: A Controller for Escaping Traps in Novel Environments
We propose an approach to online model adaptation and control in the challenging case of hybrid and discontinuous dynamics where actions may lead to difficult-to-escape "trap" states, under a given controller.
