Search Results for author:
Found 4 papers, 2 papers with code
Palantir: Towards Efficient Super Resolution for Ultra-high-definition Live Streaming
When compared to the naive method of applying DNN-based SR on all the frames, Palantir can reduce the SR DNN inference overhead by 20 times (or 60 times) while preserving 54. 0-82. 6% (or 32. 8-64. 0%) of the quality gain.
Learning Robust Correlation with Foundation Model for Weakly-Supervised Few-Shot Segmentation
In this work, we design a Correlation Enhancement Network (CORENet) with foundation model, which utilizes multi-information guidance to learn robust correlation.
Hard-aware Instance Adaptive Self-training for Unsupervised Cross-domain Semantic Segmentation
The divergence between labeled training data and unlabeled testing data is a significant challenge for recent deep learning models.
Multiple Narrow-band signals Direction Finding with TMLA by Nonuniform Period Modulation
A new array signal reconstruction and signal-channel DOA estimation method based on TMLA by nonuniform period modulation are proposed.
