Search Results for author:
Found 6 papers, 5 papers with code
HarDNet: A Low Memory Traffic Network
We propose a Harmonic Densely Connected Network to achieve high efficiency in terms of both low MACs and memory traffic.
Ranked #9 on
Real-Time Semantic Segmentation
on Cityscapes test
HarDNet-MSEG: A Simple Encoder-Decoder Polyp Segmentation Neural Network that Achieves over 0.9 Mean Dice and 86 FPS
The decoder part is inspired by the Cascaded Partial Decoder, known for fast and accurate salient object detection.
Ranked #15 on
Medical Image Segmentation
on ETIS-LARIBPOLYPDB
NeighborTrack: Improving Single Object Tracking by Bipartite Matching with Neighbor Tracklets
Our proposed NeighborTrack takes advantage of unoccluded neighbors' information to reconfirm the tracking target and reduces false tracking when the target is occluded.
Ranked #1 on
Visual Object Tracking
on UAV123
HarDNet-DFUS: An Enhanced Harmonically-Connected Network for Diabetic Foot Ulcer Image Segmentation and Colonoscopy Polyp Segmentation
The codes are available on https://github. com/kytimmylai/DFUC2022 (for Diabetic Foot Ulcers Segmentation) and https://github. com/YuWenLo/HarDNet-DFUS (for Colonoscopy Polyp Segmentation).
Ranked #6 on
Medical Image Segmentation
on Kvasir-SEG
SearchTrack: Multiple Object Tracking with Object-Customized Search and Motion-Aware Features
For each object, a customized fully convolutional search engine is created by SearchTrack by learning a set of weights for dynamic convolutions specific to the object.
RNNAccel: A Fusion Recurrent Neural Network Accelerator for Edge Intelligence
Many edge devices employ Recurrent Neural Networks (RNN) to enhance their product intelligence.
