Contrastive learning, which is a powerful technique for learning image-l...
End-to-end weakly supervised semantic segmentation aims at optimizing a
...
The performance of learning-based denoising largely depends on clean
sup...
Classification activation map (CAM), utilizing the classification struct...
Weakly supervised object localization (WSOL) focuses on localizing objec...
Weakly supervised object localization (WSOL) relaxes the requirement of ...
The nonlocal-based blocks are designed for capturing long-range
spatial-...
Diabetic retinopathy (DR) remains the most prevalent cause of vision
imp...
Superpixel is generated by automatically clustering pixels in an image i...