
-
Effective Algorithm-Accelerator Co-design for AI Solutions on Edge Devices
High quality AI solutions require joint optimization of AI algorithms, s...
read it
-
Symplectic method for Hamiltonian stochastic differential equations with multiplicative Lévy noise in the sense of Marcus
A class of Hamiltonian stochastic differential equations with multiplica...
read it
-
GAP++: Learning to generate target-conditioned adversarial examples
Adversarial examples are perturbed inputs which can cause a serious thre...
read it
-
EDD: Efficient Differentiable DNN Architecture and Implementation Co-search for Embedded AI Solutions
High quality AI solutions require joint optimization of AI algorithms an...
read it
-
Learning To Characterize Adversarial Subspaces
Deep Neural Networks (DNNs) are known to be vulnerable to the maliciousl...
read it
-
Self-supervised Adversarial Training
Recent work has demonstrated that neural networks are vulnerable to adve...
read it
-
Self-Supervised Learning For Few-Shot Image Classification
Few-shot image classification aims to classify unseen classes with limit...
read it
-
SkyNet: a Hardware-Efficient Method for Object Detection and Tracking on Embedded Systems
Developing object detection and tracking on resource-constrained embedde...
read it
-
SkyNet: A Champion Model for DAC-SDC on Low Power Object Detection
Developing artificial intelligence (AI) at the edge is always challengin...
read it
-
A Bi-Directional Co-Design Approach to Enable Deep Learning on IoT Devices
Developing deep learning models for resource-constrained Internet-of-Thi...
read it
-
FPGA/DNN Co-Design: An Efficient Design Methodology for IoT Intelligence on the Edge
While embedded FPGAs are attractive platforms for DNN acceleration on ed...
read it
-
Bilinear Representation for Language-based Image Editing Using Conditional Generative Adversarial Networks
The task of Language-Based Image Editing (LBIE) aims at generating a tar...
read it
-
SiamVGG: Visual Tracking using Deeper Siamese Networks
Recently, we have seen a rapid development of Deep Neural Network (DNN) ...
read it
-
CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes
We propose a network for Congested Scene Recognition called CSRNet to pr...
read it