Log In Sign Up

Seq-UPS: Sequential Uncertainty-aware Pseudo-label Selection for Semi-Supervised Text Recognition

by   Gaurav patel, et al.

This paper looks at semi-supervised learning (SSL) for image-based text recognition. One of the most popular SSL approaches is pseudo-labeling (PL). PL approaches assign labels to unlabeled data before re-training the model with a combination of labeled and pseudo-labeled data. However, PL methods are severely degraded by noise and are prone to over-fitting to noisy labels, due to the inclusion of erroneous high confidence pseudo-labels generated from poorly calibrated models, thus, rendering threshold-based selection ineffective. Moreover, the combinatorial complexity of the hypothesis space and the error accumulation due to multiple incorrect autoregressive steps posit pseudo-labeling challenging for sequence models. To this end, we propose a pseudo-label generation and an uncertainty-based data selection framework for semi-supervised text recognition. We first use Beam-Search inference to yield highly probable hypotheses to assign pseudo-labels to the unlabelled examples. Then we adopt an ensemble of models, sampled by applying dropout, to obtain a robust estimate of the uncertainty associated with the prediction, considering both the character-level and word-level predictive distribution to select good quality pseudo-labels. Extensive experiments on several benchmark handwriting and scene-text datasets show that our method outperforms the baseline approaches and the previous state-of-the-art semi-supervised text-recognition methods.


page 1

page 2

page 3

page 4


Pseudo-Labeled Auto-Curriculum Learning for Semi-Supervised Keypoint Localization

Localizing keypoints of an object is a basic visual problem. However, su...

Positive-Unlabeled Learning with Uncertainty-aware Pseudo-label Selection

Pseudo-labeling solutions for positive-unlabeled (PU) learning have the ...

Learning with Pseudo-Ensembles

We formalize the notion of a pseudo-ensemble, a (possibly infinite) coll...

Cross-Model Pseudo-Labeling for Semi-Supervised Action Recognition

Semi-supervised action recognition is a challenging but important task d...

SoftCTC x2013 Semi-Supervised Learning for Text Recognition using Soft Pseudo-Labels

This paper explores semi-supervised training for sequence tasks, such as...

An Empirical Study of Pseudo-Labeling for Image-based 3D Object Detection

Image-based 3D detection is an indispensable component of the perception...