Meta-learning methods typically follow a two-loop framework, where each ...
As semiconductor power density is no longer constant with the technology...
The high demand for memory capacity in modern datacenters has led to mul...
Adversarial robustness is a key concept in measuring the ability of neur...
Existing multi-view representation learning methods typically follow a
s...
Learning with noisy labels (LNL) aims to ensure model generalization giv...
Full-system simulation of computer systems is critical to capture the co...
Recent studies on backdoor attacks in model training have shown that
pol...
The advances in deep learning (DL) techniques have the potential to deli...
Few-shot class-incremental learning (FSCIL) faces challenges of memorizi...
Responding to the "datacenter tax" and "killer microseconds" problems fo...
Deep learning-based Multi-Task Classification (MTC) is widely used in
ap...
Depth estimation is a long-lasting yet important task in computer vision...
Recent works have theoretically and empirically shown that deep neural
n...
K-Nearest Neighbor (kNN)-based deep learning methods have been applied t...
Biomimetics has played a key role in the evolution of artificial neural
...
Model-agnostic meta-learning (MAML) has emerged as one of the most succe...
Adversarial attacks against deep neural networks are continuously evolvi...
Tone-mapping plays an essential role in high dynamic range (HDR) imaging...
Modeling imaging sensor noise is a fundamental problem for image process...
When the training data are maliciously tampered, the predictions of the
...
In modern server CPUs, last-level cache (LLC) is a critical hardware res...
Higher-order tensors can represent scores in a rating system, frames in ...
Social media sites are becoming a key factor in politics. These platform...