Although current semantic segmentation approaches have achieved impressive
performance, their ability to incrementally learn new classes is limited. Moreover, pixel-by …

The detection, localization, and interpretation of defects in textured surfaces pose
challenges for automatic visual inspection. Both fully-supervised and weakly-supervised …

Weakly supervised object localization (WSOL) aims to localize objects with only image-level
labels. As a common WSOL method, adversarial erasing always masks the most …

Security systems place great emphasis on the safety of stored cargo, as any loss or
tampering can result in significant economic damage. The cargo identification module within …

Abstract Unsupervised Image Segmentation (UIS) is a challenging problem in computer
vision that aims to classify pixels in an image into different semantic classes without using …

Learning the relationship between weak and strong perturbations has been considered a
major part of semi-supervised semantic segmentation. We observed two problems with a …

Compared with biometrics based on fingerprints, face and voice, gait biometrics can provide
person identification and authentication at a longer distance, which is a desired property in …

Abstract Vision Transformers (ViTs) have demonstrated remarkable performances on
various computer vision tasks. Attention scores are often used to explain the decision …

Semi-supervised learning (SSL) aims to reduce reliance on labeled data. Achieving high
performance often requires more complex algorithms, therefore, generic SSL algorithms are …