Latest Research
Destruction from sky: Weakly supervised approach for destruction detection in satellite imagery
ISPRS Journal of Photogrammetry and Remote Sensing 2020
• usmanali414/Destruction-Detection-in-Satellite-Imagery
• 
Natural and man-made disasters cause huge damage to built infrastructures and results in loss of human lives.
TResNet: High Performance GPU-Dedicated Architecture
• mrT23/TResNet
• 
In this work, we introduce a series of architecture modifications that aim to boost neural networks' accuracy, while retaining their GPU training and inference efficiency.
Squeezed Deep 6DoF Object Detection Using Knowledge Distillation
• heitorcfelix/singleshot6Dpose
•
We used the LINEMOD dataset to evaluate the proposed method and the experimental results show that the proposed method reduces the memory requirement almost 99\% in comparison to the original architecture reducing half the accuracy in one of the metrics.
RPM-Net: Robust Point Matching using Learned Features
The hard assignments of closest point correspondences based on spatial distances are sensitive to the initial rigid transformation and noisy/outlier points, which often cause ICP to converge to wrong local minima.
Ultrasound-Guided Robotic Navigation with Deep Reinforcement Learning
• hhase/spinal-navigation-rl
•
In this paper we introduce the first reinforcement learning (RL) based robotic navigation method which utilizes ultrasound (US) images as an input.
Gradually Vanishing Bridge for Adversarial Domain Adaptation
• cuishuhao/GVB
•
On the discriminator, GVB contributes to enhance the discriminating ability, and balance the adversarial training process.
Cross-Domain Document Object Detection: Benchmark Suite and Method
We establish a benchmark suite consisting of different types of PDF document datasets that can be utilized for cross-domain DOD model training and evaluation.
Decentralized Learning for Channel Allocation in IoT Networks over Unlicensed Bandwidth as a Contextual Multi-player Multi-armed Bandit Game
We study a decentralized channel allocation problem in an ad-hoc Internet of Things (IoT) network underlaying on a spectrum licensed to an existing wireless network.
Multi-Objective Matrix Normalization for Fine-grained Visual Recognition
• mboboGO/MOMN
•
In this paper, we propose an efficient Multi-Objective Matrix Normalization (MOMN) method that can simultaneously normalize a bilinear representation in terms of square-root, low-rank, and sparsity.
Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation
• XingangPan/deep-generative-prior
•
Learning a good image prior is a long-term goal for image restoration and manipulation.