Search Results for author:
Found 4 papers, 1 papers with code
Rethinking Soft Label in Label Distribution Learning Perspective
The primary goal of training in early convolutional neural networks (CNN) is the higher generalization performance of the model.
Self-Supervised Knowledge Transfer via Loosely Supervised Auxiliary Tasks
The SSKT is independent of the network structure and dataset, and is trained differently from existing knowledge transfer methods; hence, it has an advantage in that the prior knowledge acquired from various tasks can be naturally transferred during the training process to the target task.
hSDB-instrument: Instrument Localization Database for Laparoscopic and Robotic Surgeries
Localization information for all instruments is provided in the form of a bounding box for object detection.
Semi-Supervised Object Detection with Sparsely Annotated Dataset
However, when training an anchor-based detectors with sparse annotations on an image, effort to find effective positive examples can hinder training performance.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
