3 accepted papers
Training-free open-vocabulary semantic segmentation (OVS) aims to segment images given a set of arbitrary textual categories without costly model fine-tuning. Existing solutions often explore attention mechanisms of pre-trained models, such as CLIP, or generate synthetic data and design complex retr…
"Recent studies highlight that deep learning models often learn spurious features mistakenly linked to labels, compromising their reliability in real-world scenarios where such correlations do not hold. Despite the increasing research effort, existing solutions often face two main challenges: they e…
Multiple-player games involving cooperative and adversarial agents are a type of problems of great practical significance. In this letter, we consider an attack-defense game with a single attacker and multiple defenders. The attacker attempts to enter a protected region, while the defenders attempt