Dec 27, 2020 · We propose a novel multi-domain adaptation method for object detection based on incremental learning. Specifically, the incremental learning network saves the ...

This work is the first to increase the granularity of the background category by building the foundation model using contrastive vision-language ...

Apr 13, 2021 · In this paper, we introduce an efficient approach for incremental learning that generalizes well to multiple target domains.

Sep 13, 2024 · Techniques for multi-target domain adaptation (MTDA) seek to adapt a recognition model such that it can generalize well across multiple ...

For the high-level features that are impor- tant for object recognition, we weakly align each source and target in corresponding supervised source subnet.

In this paper, we introduce an efficient approach for incremental learning that generalizes well to multiple target domains. Our MTDA approach is more suitable ...

If we want to learn to detect/localize new concepts from new domains on devices for these models without losing the detection ability in previous domains, we ...

In this paper, we identify the unexplored yet valuable scenario, i.e., class-incremental learning under domain shift, and propose a novel 3D domain adaptive ...

We introduce a practical Domain Adaptation (DA) paradigm called Class-Incremental Domain Adaptation (CIDA). Existing DA meth- ods tackle domain-shift but are ...

Recent efforts in multi-domain learning for semantic seg- mentation attempt to learn multiple geographical datasets in a universal, joint model.