Related papers: On Calibration of Scene-Text Recognition Models
Scene text recognition (STR) task has a common practice: All state-of-the-art STR models are trained on large synthetic data. In contrast to this practice, training STR models only on fewer real labels (STR with fewer labels) is important…
We develop a Deep-Text Recurrent Network (DTRN) that regards scene text reading as a sequence labelling problem. We leverage recent advances of deep convolutional neural networks to generate an ordered high-level sequence from a whole word…
Scene text recognition (STR) pre-training methods have achieved remarkable progress, primarily relying on synthetic datasets. However, the domain gap between synthetic and real images poses a challenge in acquiring feature representations…
Scene text recognition is a hot research topic in computer vision. Recently, many recognition methods based on the encoder-decoder framework have been proposed, and they can handle scene texts of perspective distortion and curve shape.…
Scene text recognition (STR) has been widely studied in academia and industry. Training a text recognition model often requires a large amount of labeled data, but data labeling can be difficult, expensive, or time-consuming, especially for…
We study calibration in question answering, estimating whether model correctly predicts answer for each question. Unlike prior work which mainly rely on the model's confidence score, our calibrator incorporates information about the input…
The attention-based encoder-decoder framework has recently achieved impressive results for scene text recognition, and many variants have emerged with improvements in recognition quality. However, it performs poorly on contextless texts…
In-Context Learning (ICL) allows Large Language Models (LLMs) to adapt to new tasks with just a few examples, but their predictions often suffer from systematic biases, leading to unstable performance in classification. While calibration…
With the rise of deep learning algorithms nowadays, scene image representation methods have achieved a significant performance boost in classification. However, the performance is still limited because the scene images are mostly complex…
Recent advancements in scene text spotting have focused on end-to-end methodologies that heavily rely on precise location annotations, which are often costly and labor-intensive to procure. In this study, we introduce an innovative approach…
Confidence calibration -- the problem of predicting probability estimates representative of the true correctness likelihood -- is important for classification models in many applications. We discover that modern neural networks, unlike…
Scene text recognition (STR) is a challenging problem due to the imperfect imagery conditions in natural images. State-of-the-art methods utilize both visual cues and linguistic knowledge to tackle this challenging problem. Specifically,…
While large language models (LLMs) achieve strong performance on text-to-SQL parsing, they sometimes exhibit unexpected failures in which they are confidently incorrect. Building trustworthy text-to-SQL systems thus requires eliciting…
The recent large-scale Contrastive Language-Image Pretraining (CLIP) model has shown great potential in various downstream tasks via leveraging the pretrained vision and language knowledge. Scene text, which contains rich textual and visual…
Nowadays, scene text recognition has attracted more and more attention due to its diverse applications. Most state-of-the-art methods adopt an encoder-decoder framework with the attention mechanism, autoregressively generating text from…
Sequence labeling architectures use word embeddings for capturing similarity, but suffer when handling previously unseen or rare words. We investigate character-level extensions to such models and propose a novel architecture for combining…
The recognition of texts existing in camera-captured images has become an important issue for a great deal of research during the past few decades. This give birth to Scene Character Recognition (SCR) which is an important step in scene…
The ability to recognize and reason about text embedded in visual inputs is often lacking in vision-and-language (V&L) models, perhaps because V&L pre-training methods have often failed to include such an ability in their training…
Scene text image super-resolution (STISR), aiming to improve image quality while boosting downstream scene text recognition accuracy, has recently achieved great success. However, most existing methods treat the foreground (character…
Building accurate language models that capture meaningful long-term dependencies is a core challenge in natural language processing. Towards this end, we present a calibration-based approach to measure long-term discrepancies between a…