Search Results for author:
Found 5 papers, 3 papers with code
Compensation Learning in Semantic Segmentation
In this paper, we propose Compensation Learning in Semantic Segmentation, a framework to identify and compensate ambiguities as well as label noise.
Blind Knowledge Distillation for Robust Image Classification
We introduce Blind Knowledge Distillation - a novel teacher-student approach for learning with noisy labels by masking the ground truth related teacher output to filter out potentially corrupted knowledge and to estimate the tipping point from generalizing to overfitting.
ChimeraMix: Image Classification on Small Datasets via Masked Feature Mixing
In this work, we address the problem of learning deep neural networks on small datasets.
Neural Random Forest Imitation
We present Neural Random Forest Imitation - a novel approach for transforming random forests into neural networks.
Object Recognition from very few Training Examples for Enhancing Bicycle Maps
These algorithms are usually trained on large datasets consisting of thousands or millions of labeled training examples.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
