Search Results for author:
Found 5 papers, 0 papers with code
kNN-CLIP: Retrieval Enables Training-Free Segmentation on Continually Expanding Large Vocabularies
Rapid advancements in continual segmentation have yet to bridge the gap of scaling to large continually expanding vocabularies under compute-constrained scenarios.
CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor
Mask labels are labor-intensive, which limits the number of categories in segmentation datasets.
OxfordTVG-HIC: Can Machine Make Humorous Captions from Images?
Hence, humour generation and understanding can serve as a new task for evaluating the ability of deep-learning methods to process abstract and subjective information.
Real-time Blind Deblurring Based on Lightweight Deep-Wiener-Network
In this paper, we address the problem of blind deblurring with high efficiency.
Label Alignment Regularization for Distribution Shift
Recent work has highlighted the label alignment property (LAP) in supervised learning, where the vector of all labels in the dataset is mostly in the span of the top few singular vectors of the data matrix.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
