microsoft/BridgeTower
Open source code for AAAI 2023 Paper "BridgeTower: Building Bridges Between Encoders in Vision-Language Representation Learning"
PythonMIT
Issues
- 3
- 1
Processor only accepts 3 channel images
#12 opened by swtb3 - 1
checkpoint 链接失效
#14 opened by sukeey - 0
processor support for single channel?
#13 opened by swtb3 - 2
about code
#2 opened by zhenjia2017 - 1
Pretraining Result of BridgeTower
#4 opened by jsg921019 - 4
- 5
Pre-trained visual encoder, 4M pretraining?
#1 opened by m-bain