Large language models (LLMs) for natural language processing have been
g...
Zero-shot referring image segmentation is a challenging task because it ...
This paper presents a substantial extension of our work published at ICL...
Semantic understanding of programs has attracted great attention in the
...
Intermediate-level attacks that attempt to perturb feature representatio...
The transferability of adversarial examples across deep neural networks
...
Prompt tuning has been employed as an efficient way to adapt large
visio...
Vision Transformers (ViTs) have recently achieved competitive performanc...
The vulnerability of deep neural networks (DNNs) to adversarial examples...
This paper substantially extends our work published at ECCV, in which an...
The study of multi-task learning has drawn great attention from the
comm...
Backpropagation is widely used for calculating gradients in deep neural
...
The learned iterative shrinkage thresholding algorithm (LISTA) introduce...
In this big data era, we often confront large-scale data in many machine...
This paper serves as a survey of recent advances in large margin trainin...
With the progress in AI-based facial forgery (i.e., deepfake), people ar...
The vulnerability of deep neural networks (DNNs) to adversarial examples...
The study of adversarial vulnerabilities of deep neural networks (DNNs) ...
Learning from imperfect data becomes an issue in many industrial applica...
The transferability of adversarial examples across deep neural network (...
This paper analyzes regularization terms proposed recently for improving...
Metric learning aims to learn a distance metric such that semantically
s...
The tremendous recent success of deep neural networks (DNNs) has sparked...
Unlike the white-box counterparts that are widely studied and readily
ac...
For network architecture search (NAS), it is crucial but challenging to
...
Traditional clustering methods often perform clustering with low-level
i...
Convolutional neural networks have been proven very effective in a varie...
Deep neural networks (DNNs) are computationally/memory-intensive and
vul...
Despite the efficacy on a variety of computer vision tasks, deep neural
...
In this paper, we propose an alternative method to estimate room layouts...
Convolutional neural networks (CNNs) with deep architectures have
substa...
This paper presents incremental network quantization (INQ), a novel meth...
Deep learning has become a ubiquitous technology to improve machine
inte...