Related papers: Self-supervised Implicit Glyph Attention for Text …

Recently, there have been efforts to improve the performance in sign language recognition by designing self-supervised learning methods. However, these methods capture limited information from sign pose data in a frame-wise learning manner,…

In this work, we present a novel mask guided attention (MGA) method for fine-grained patchy image classification. The key challenge of fine-grained patchy image classification lies in two folds, ultra-fine-grained inter-category variances…

The divergence between labeled training data and unlabeled testing data is a significant challenge for recent deep learning models. Unsupervised domain adaptation (UDA) attempts to solve such problem. Recent works show that self-training is…

Given data with noisy labels, over-parameterized deep networks can gradually memorize the data, and fit everything in the end. Although equipped with corrections for noisy labels, many learning methods in this area still suffer overfitting…

Self-supervised learning approaches for unsupervised domain adaptation (UDA) of semantic segmentation models suffer from challenges of predicting and selecting reasonable good quality pseudo labels. In this paper, we propose a novel…

The divergence between labeled training data and unlabeled testing data is a significant challenge for recent deep learning models. Unsupervised domain adaptation (UDA) attempts to solve such a problem. Recent works show that self-training…

Scene text recognition has attracted particular research interest because it is a very challenging problem and has various applications. The most cutting-edge methods are attentional encoder-decoder frameworks that learn the alignment…

The emerging graph Transformers have achieved impressive performance for graph representation learning over graph neural networks (GNNs). In this work, we regard the self-attention mechanism, the core module of graph Transformers, as a…

Zero-Shot Learning (ZSL) is achieved via aligning the semantic relationships between the global image feature vector and the corresponding class semantic descriptions. However, using the global features to represent fine-grained images may…

Accurate cancer diagnosis remains a critical challenge in digital pathology, largely due to the gigapixel size and complex spatial relationships present in whole slide images. Traditional multiple instance learning (MIL) methods often…

Due to the impressive zero-shot capabilities, pre-trained vision-language models (e.g., CLIP), have attracted widespread attention and adoption across various domains. Nonetheless, CLIP has been observed to be susceptible to adversarial…

Scene text recognition (STR) is still a hot research topic in computer vision field due to its various applications. Existing works mainly focus on learning a general model with a huge number of synthetic text images to recognize…

Pseudo-labelling is a popular technique in unsuper-vised domain adaptation for semantic segmentation. However, pseudo labels are noisy and inevitably have confirmation bias due to the discrepancy between source and target domains and…

"Self-training" has become a dominant method for semantic segmentation via unsupervised domain adaptation (UDA). It creates a set of pseudo labels for the target domain to give explicit supervision. However, the pseudo labels are noisy,…

Semi-supervised medical image segmentation has attracted much attention in recent years because of the high cost of medical image annotations. In this paper, we propose a novel Inherent Consistent Learning (ICL) method, aims to learn robust…

Triggered by the success of transformers in various visual tasks, the spatial self-attention mechanism has recently attracted more and more attention in the computer vision community. However, we empirically found that a typical vision…

Scene text recognition (STR) attracts much attention over the years because of its wide application. Most methods train STR model in a fully supervised manner which requires large amounts of labeled data. Although synthetic data contributes…

Many continuous sign language recognition (CSLR) studies adopt transformer-based architectures for sequence modeling due to their powerful capacity for capturing global contexts. Nevertheless, vanilla self-attention, which serves as the…

Training recognition models with synthetic images have achieved remarkable results in text recognition. However, recognizing text from real-world images still faces challenges due to the domain shift between synthetic and real-world text…

Apart from the high accuracy of machine learning models, what interests many researchers in real-life problems (e.g., fraud detection, credit scoring) is to find hidden patterns in data; particularly when dealing with their challenging…