TL;DR
A complementary prototype representation framework is proposed, employing three modules to collaboratively improve pseudo-label quality and improves the discriminative ability of confused categories by generating semantically similar sub-category negative samples.
Weakly supervised semantic segmentation (WSSS) aims to train dense prediction models from inexpensive supervision such as image-level labels. Recent foundation models provide complementary capabilities: promptable segmentation models can produce high-coverage object masks, while self-supervised vision transformers prov...
Image-level weakly supervised remote sensing semantic segmentation aims to learn pixel-level land-cover prediction using only image-level labels, greatly reducing the annotation cost of fully supervised methods. Class activation map (CAM)-based methods are widely used for this task, but they usually focus on the most d...
Fine-grained visual classification (FGVC) aims to distinguish highly similar subcategories, and its performance relies heavily on the accurate modeling of discriminative local parts and their structural relationships. However, existing Vision Transformer-based methods are susceptible to background noise interference, a...
An interactive multimodal scene understanding framework based on frequency-domain dynamic routing and activation-region guidance, aiming to enhance multimodal feature representation for semantic segmentation and object detection, consistently outperforms existing approaches in image fusion, semantic segmentation, and o...
As a key pixel-level analysis technology, semantic segmentation is widely deployed in autonomous driving and medical imaging. Fully supervised segmentation relies on labour-intensive pixel-wise annotations, so weakly supervised semantic segmentation (WSSS) with only image-level labels has attracted wide attention. Exis...
: Lightweight semantic segmentation remains challenging because compact backbones often weaken feature discriminability and lose fine-grained boundary details. In DeepLabV3 + -style encoder-decoder architectures, the direct fusion of high-level semantic features and low-level spatial features may introduce semantic-spa...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
