Search Results for author:
Found 8 papers, 4 papers with code
HiViT: Hierarchical Vision Transformer Meets Masked Image Modeling
A key idea of efficient implementation is to discard the masked image patches (or tokens) throughout the target network (encoder), which requires the encoder to be a plain vision transformer (e. g., ViT), albeit hierarchical vision transformers (e. g., Swin Transformer) have potentially better properties in formulating vision inputs.
Integrally Migrating Pre-trained Transformer Encoder-decoders for Visual Object Detection
Except for the backbone networks, however, other components such as the detector head and the feature pyramid network (FPN) remain trained from scratch, which hinders fully tapping the potential of representation models.
Ranked #1 on
Few-Shot Object Detection
on MS-COCO (30-shot)
Long-tailed Distribution Adaptation
We propose to jointly optimize empirical risks of the unbalanced and balanced domains and approximate their domain divergence by intra-class and inter-class distances, with the aim to adapt models trained on the long-tailed distribution to general distributions in an interpretable way.
Beyond Bounding-Box: Convex-Hull Feature Adaptation for Oriented and Densely Packed Object Detection
Detecting oriented and densely packed objects remains challenging for spatial feature aliasing caused by the intersection of reception fields between objects.
Ranked #31 on
Object Detection In Aerial Images
on DOTA
FreeAnchor: Learning to Match Anchors for Visual Object Detection
In this study, we propose a learning-to-match approach to break IoU restriction, allowing objects to match anchors in a flexible manner.
Ranked #136 on
Object Detection
on COCO test-dev
Adversarial Samples on Android Malware Detection Systems for IoT Systems
An automated testing framework is needed to help these learning-based malware detection systems for IoT devices perform security analysis.
A Black-box Attack on Neural Networks Based on Swarm Evolutionary Algorithm
Our experimental results show that both the MNIST images and the CIFAR-10 images can be perturbed to successful generate a black-box attack with 100\% probability on average.
Weighted-Sampling Audio Adversarial Example Attack
In this paper, we propose~\textit{weighted-sampling audio adversarial examples}, focusing on the numbers and the weights of distortion to reinforce the attack.
