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...
A Prior-Guided Part Aggregator (PGA) is designed, which leverages the foreground prior provided by foundation models to guide discriminative part discovery, enhancing target region responses while suppressing background interference, and a Topology-Informed Semantic Graph Convolutional Network (TIS-GCN) is designed to...
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...
A single-stage weakly supervised segmentation algorithm based on local–global class labelling comparison that effectively improves the completeness of target activation regions and suppresses background noise, and it maintains strong generalization for slender, small and texture-sparse objects.
BFANet is proposed, a boundary-aware lightweight semantic segmentation framework based on DeepLabV3 + with a MobileNetV2 backbone that integrates parameter-free SimAM feature refinement, low-level-guided Dynamic Feature Alignment, and progressive decoder fusion to enhance discriminative feature responses, reduce cross-...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
