Search Results for author:
Found 3 papers, 1 papers with code
Spatial Reasoning for Few-Shot Object Detection
Although modern object detectors rely heavily on a significant amount of training data, humans can easily detect novel objects using a few training examples.
Character decomposition to resolve class imbalance problem in Hangul OCR
As the total number of the characters could overwhelm the capacity of a neural network, the existing OCR encoding methods pre-define a smaller set of characters that are frequently used.
Optical Character Recognition
Optical Character Recognition (OCR)
Few-Shot Object Detection via Knowledge Transfer
If there are only a few training data and annotations, the object detectors easily overfit and fail to generalize.
