3 papers
cs.CV2024
What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?
Guangkai Xu, Yongtao Ge, Mingyu Liu +5
Extensive pre-training with large data is indispensable for downstream geometry and semantic visual perception tasks. Thanks to large-scale text-to-image (T2I) pretraining, recent…
cs.CV2024
Generative Active Learning for Long-tailed Instance Segmentation
Muzhi Zhu, Chengxiang Fan, Hao Chen +4
Recently, large-scale language-image generative models have gained widespread attention and many works have utilized generated data from these models to further enhance the perform…
cs.CV2024
DiverGen: Improving Instance Segmentation by Learning Wider Data Distribution with More Diverse Generative Data
Chengxiang Fan, Muzhi Zhu, Hao Chen +4
Instance segmentation is data-hungry, and as model capacity increases, data scale becomes crucial for improving the accuracy. Most instance segmentation datasets today require cost…