Search Results for author:
Found 5 papers, 4 papers with code
BGM: Background Mixup for X-ray Prohibited Items Detection
The approach introduces 1) contour information of baggage and 2) variation of material information into the original image by Mixup at patch level.
Collaborative Vision-Text Representation Optimizing for Open-Vocabulary Segmentation
In this way, the vision and text representation of CLIP are optimized collaboratively, enhancing the alignment of the vision-text feature space.
Ranked #4 on
Open Vocabulary Panoptic Segmentation
on ADE20K
Open Vocabulary Panoptic Segmentation
Open Vocabulary Semantic Segmentation
+1
CTP: Towards Vision-Language Continual Pretraining via Compatible Momentum Contrast and Topology Preservation
Regarding the growing nature of real-world data, such an offline training paradigm on ever-expanding data is unsustainable, because models lack the continual learning ability to accumulate knowledge constantly.
CTP:Towards Vision-Language Continual Pretraining via Compatible Momentum Contrast and Topology Preservation
Regarding the growing nature of real-world data, such an offline training paradigm on ever-expanding data is unsustainable, because models lack the continual learning ability to accumulate knowledge constantly.
Towards Fast and Accurate Real-World Depth Super-Resolution: Benchmark Dataset and Baseline
Depth maps obtained by commercial depth sensors are always in low-resolution, making it difficult to be used in various computer vision tasks.
