Unlike the conventional machine learning paradigms where learning is performed on a static dataset, domain incremental learning, i.e., continual learning with evolving domains, hopes to accommodate the model to the dynamically changing data distributions, while retaining the knowledge learned from previous domains [

During optimization, contrastive learning keeps the different modalities separated by a certain distance, which is influenced by the temperature parameter in the loss function. Our experiments further demonstrate that varying the modality gap distance has a significant impact in improving the model's downstream zero-shot classification performance and fairness.

Towardsafinerlocalization thatbetterservesdownstream applications likerobot interaction, we extend the problem into task oriented instance segmentation.

In practice, the target sequence often follows certain model properties or patterns (e.g., reasonable ranges, consecutive changes, resource constraint, temporal correlations between multiple variables, existence, unusual cases, etc.). However,RNNs cannot guarantee their learned distributions satisfy these properties.

We appreciate the valuable comments from the reviewers. We will answer reviewers' questions from three aspects, i.e., In respond to Reviewer 5, this paper's major novelty is developing a new STL-based learning framework to Our method creates a practical way to ensure the logic rules' satisfaction in an end-to-end manner. Our approach achieves promising results on real city datasets, i.e., significantly We have carefully compared our work with all the related papers pointed out by the reviewers. Therefore, we also choose STL to express the model properties. Using STL to specify CPS properties is not our novelty.

Albeit, the objective of the learner is to achieve low task loss at an individual instance level.

It has been repeatedly shown that deep neural networks (DNNs) can achieve human-or superhuman-levelperformances on various tasks [1,17,32].