Search Results for author:
Found 6 papers, 2 papers with code
Quasar-ViT: Hardware-Oriented Quantization-Aware Architecture Search for Vision Transformers
This work proposes Quasar-ViT, a hardware-oriented quantization-aware architecture search framework for ViTs, to design efficient ViT models for hardware implementation while preserving the accuracy.
HeatViT: Hardware-Efficient Adaptive Token Pruning for Vision Transformers
While vision transformers (ViTs) have continuously achieved new milestones in the field of computer vision, their sophisticated network architectures with high computation and memory costs have impeded their deployment on resource-limited edge devices.
SuperYOLO: Super Resolution Assisted Object Detection in Multimodal Remote Sensing Imagery
Furthermore, we design a simple and flexible SR branch to learn HR feature representations that can discriminate small objects from vast backgrounds with low-resolution (LR) input, thus further improving the detection accuracy.
Ranked #3 on
Object Detection
on VEDAI
Auto-ViT-Acc: An FPGA-Aware Automatic Acceleration Framework for Vision Transformer with Mixed-Scheme Quantization
Compared with state-of-the-art ViT quantization work (algorithmic approach only without hardware acceleration), our quantization achieves 0. 47% to 1. 36% higher Top-1 accuracy under the same bit-width.
FitAct: Error Resilient Deep Neural Networks via Fine-Grained Post-Trainable Activation Functions
Deep neural networks (DNNs) are increasingly being deployed in safety-critical systems such as personal healthcare devices and self-driving cars.
BDFA: A Blind Data Adversarial Bit-flip Attack on Deep Neural Networks
Adversarial bit-flip attack (BFA) on Neural Network weights can result in catastrophic accuracy degradation by flipping a very small number of bits.
