Figure - available via license: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
Content may be subject to copyright.
Comparison with baselines on number of parameters, sampling steps and sampling time required for BAIR robot push dataset.
Source publication
Multi-step prediction models, such as diffusion and rectified flow models, have emerged as state-of-the-art solutions for generation tasks. However, these models exhibit higher latency in sampling new frames compared to single-step methods. This latency issue becomes a significant bottleneck when adapting such methods for video prediction tasks, gi...
Context in source publication
Context 1
... indicated in Table 2, our method consistently outperforms baseline models. Qualitative results of our CVF model on the BAIR dataset can be seen in Fig. 5. Table 3 highlights the superior efficiency of the proposed CVF model compared to diffusion based baselines across key metrics. CVF has the fewest parameters and requires only 5 sampling steps per frame. ...Similar publications
![Parameter sensitivity analysis for α\documentclass[12pt]{minimal}...](publication/389748499/figure/fig4/AS:11431281362858266@1744164942815/Parameter-sensitivity-analysis-for-adocumentclass12ptminimal-usepackageamsmath_Q320.jpg)
![Parameter sensitivity analysis for β\documentclass[12pt]{minimal}...](publication/389748499/figure/fig5/AS:11431281362858267@1744164943025/Parameter-sensitivity-analysis-for-bdocumentclass12ptminimal-usepackageamsmath_Q320.jpg)
Unsupervised domain adaptation (UDA) is a technique for learning from a label-rich source domain and transferring the learned knowledge to an unlabeled target domain. Current researches on feature-based UDA methods usually utilize the pseudo labels to find new feature representations that can minimize the distribution difference between the two dom...
