Adapt or perish: Adaptive sparse transformer with attentive feature refinement for image restoration
Transformer-based approaches have achieved promising performance in image restoration
tasks given their ability to model long-range dependencies which is crucial for recovering …
tasks given their ability to model long-range dependencies which is crucial for recovering …
Extdm: Distribution extrapolation diffusion model for video prediction
Video prediction is a challenging task due to its nature of uncertainty especially for
forecasting a long period. To model the temporal dynamics advanced methods benefit from …
forecasting a long period. To model the temporal dynamics advanced methods benefit from …
Alignsam: Aligning segment anything model to open context via reinforcement learning
Powered by massive curated training data Segment Anything Model (SAM) has
demonstrated its impressive generalization capabilities in open-world scenarios with the …
demonstrated its impressive generalization capabilities in open-world scenarios with the …
Lake-red: Camouflaged images generation by latent background knowledge retrieval-augmented diffusion
Camouflaged vision perception is an important vision task with numerous practical
applications. Due to the expensive collection and labeling costs this community struggles …
applications. Due to the expensive collection and labeling costs this community struggles …
Annotation-efficient polyp segmentation via active learning
Deep learning-based techniques have proven effective in polyp segmentation tasks when
provided with sufficient pixel-wise labeled data. However, the high cost of manual …
provided with sufficient pixel-wise labeled data. However, the high cost of manual …