Search Results for author:
Found 10 papers, 4 papers with code
Knowledge Assembly: Semi-Supervised Multi-Task Learning from Multiple Datasets with Disjoint Labels
In real-world scenarios we often need to perform multiple tasks simultaneously.
Booster-SHOT: Boosting Stacked Homography Transformations for Multiview Pedestrian Detection with Attention
Improving multi-view aggregation is integral for multi-view pedestrian detection, which aims to obtain a bird's-eye-view pedestrian occupancy map from images captured through a set of calibrated cameras.
Privacy Safe Representation Learning via Frequency Filtering Encoder
We further conduct a user study to qualitatively assess our defense of the reconstruction attack.
Depth-resolved vascular profile features for artery-vein classification in OCT and OCT angiography of human retina
Uniform lumen intensity was observed in both small and large arteries.
Self-Supervised Visual Learning by Variable Playback Speeds Prediction of a Video
We propose a self-supervised visual learning method by predicting the variable playback speeds of a video.
Training with the Invisibles: Obfuscating Images to Share Safely for Learning Visual Recognition Models
High-performance visual recognition systems generally require a large collection of labeled images to train.
Quantifying Generalization in Reinforcement Learning
In this paper, we investigate the problem of overfitting in deep reinforcement learning.
Transfer Learning via Unsupervised Task Discovery for Visual Question Answering
Specifically, we employ linguistic knowledge sources such as structured lexical database (e. g. WordNet) and visual descriptions for unsupervised task discovery, and transfer a learned task conditional visual classifier as an answering unit in a visual question answering model.
Music Source Separation Using Stacked Hourglass Networks
In this paper, we propose a simple yet effective method for multiple music source separation using convolutional neural networks.
Sound Audio and Speech Processing
ScreenerNet: Learning Self-Paced Curriculum for Deep Neural Networks
We propose to learn a curriculum or a syllabus for supervised learning and deep reinforcement learning with deep neural networks by an attachable deep neural network, called ScreenerNet.
