Deep Radial Embedding for Visual Sequence Learning
Connectionist Temporal Classification (CTC) is a popular objective function in sequence recognition, which provides supervision for unsegmented sequence data through aligning sequence and its corresponding labeling iteratively. The blank class of CTC plays a crucial role in the alignment process and is often considered responsible for the peaky behavior of CTC. In this study, we propose an objective function named RadialCTC that constrains sequence features on a hypersphere while retaining the iterative alignment mechanism of CTC. The learned features of each non-blank class are distributed on a radial arc from the center of the blank class, which provides a clear geometric interpretation and makes the alignment process more efficient. Besides, RadialCTC can control the peaky behavior by simply modifying the logit of the blank class. Experimental results of recognition and localization demonstrate the effectiveness of RadialCTC on two sequence recognition applications.
PDF Abstract
Datasets
MNIST
Results from the Paper
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
|---|---|---|---|---|---|---|
| Sign Language Recognition | RWTH-PHOENIX-Weather 2014 | RadialCTC | Word Error Rate (WER) | 20.2 | # 4 |
