7 accepted papers
In this paper, we focus on enhancing a diffusion-based text-to-video (T2V) model during the post-training phase by distilling a highly capable consistency model from a pretrained T2V model. Our proposed method, T2V-Turbo-v2, introduces a significant advancement by integrating various supervision sig…
Radiologists highly desire fully automated versatile AI for medical imaging interpretation. However the lack of extensively annotated large-scale multi-disease datasets has hindered the achievement of this goal. In this paper we explore the feasibility of leveraging language as a naturally high-qual…
Designing neural architectures requires immense manual efforts. This has promoted the development of neural architecture search (NAS) to automate the design. While previous NAS methods achieve promising results but run slowly, zero-cost proxies run extremely fast but are less promising. Therefore, i…
"Knowledge distillation compresses a large model (teacher) to a smaller one by letting the student imitate the outputs of the teacher. An interesting question is why the student still typically underperforms the teacher after the imitation. The existing literature usually attributes this to model ca…
Although various image-based domain adaptation (DA) techniques have been proposed in recent years, domain shift in videos is still not well-explored. Most previous works only evaluate performance on small-scale datasets which are saturated. Therefore, we first propose two large-scale video DA datase…
In this paper we develop a new spectrum sharing scheme that uses compressive sensing to support the coexistence of the sporadic machine-to-machine (M2M) communications and the persistent conventional communications such as the 5G cellular transmissions within the same channel. The redundancy in the…
In this paper, we develop a novel scheme to reduce the amount of training data required for training deep neural networks (DNNs). We first apply a partial mutual information (PMI) technique to seek for the optimal DNN feature set. Then we use a correlation matching based active learning (CMAL) techn…