A Caltech Library Service

Towards Weakly-Supervised Text Spotting using a Multi-Task Transformer

Kittenplon, Yair and Lavi, Inbal and Fogel, Sharon and Bar, Yarin and Manmatha, R. and Perona, Pietro (2022) Towards Weakly-Supervised Text Spotting using a Multi-Task Transformer. . (Unpublished)

[img] PDF - Submitted Version
See Usage Policy.


Use this Persistent URL to link to this item:


Text spotting end-to-end methods have recently gained attention in the literature due to the benefits of jointly optimizing the text detection and recognition components. Existing methods usually have a distinct separation between the detection and recognition branches, requiring exact annotations for the two tasks. We introduce TextTranSpotter (TTS), a transformer-based approach for text spotting and the first text spotting framework which may be trained with both fully- and weakly-supervised settings. By learning a single latent representation per word detection, and using a novel loss function based on the Hungarian loss, our method alleviates the need for expensive localization annotations. Trained with only text transcription annotations on real data, our weakly-supervised method achieves competitive performance with previous state-of-the-art fully-supervised methods. When trained in a fully-supervised manner, TextTranSpotter shows state-of-the-art results on multiple benchmarks.

Item Type:Report or Paper (Discussion Paper)
Related URLs:
URLURL TypeDescription Paper
Manmatha, R.0000-0003-2315-8583
Perona, Pietro0000-0002-7583-5809
Record Number:CaltechAUTHORS:20220224-200946567
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:113607
Deposited By: George Porter
Deposited On:25 Feb 2022 00:22
Last Modified:25 Feb 2022 00:22

Repository Staff Only: item control page