3 accepted papers
Recent advancements in deep neural networks have significantly enhanced the performance of semantic segmentation. However, class imbalance and instance imbalance remain persistent challenges, where smaller instances and thin boundaries are often overshadowed by larger structures. To address the mult…
Machine learning models are vulnerable to membership inference attacks (MIAs), where adversaries attempt to predict whether specific samples are part of the model’s training set. Previous studies have demonstrated a strong correlation between the distinguishability of training and testing loss distr…
Offline goal-conditioned reinforcement learning (GCRL) aims at solving goal-reaching tasks with sparse rewards from an offline dataset. While prior work has demonstrated various approaches for agents to learn near-optimal policies, these methods encounter limitations when dealing with diverse constr…