Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks43 from public data
- BiFormer: Vision Transformer with Bi-Level Routing Attention1,180
This work proposes a novel dynamic sparse attention via bi-level routing to enable a more flexible allocation of computations with content awareness and presents a new general vision transformer, named BiFormer, which enjoys both good performance and high computational efficiency, especially in dense prediction tasks.
- 545
- Bidirectional Feature Pyramid Network with Recurrent Attention Residual Modules for Shadow Detection285
This paper presents a network to detect shadows by exploring and combining global context in deep layers and local context in shallow layers of a deep convolutional neural network (CNN) and develops a bidirectional feature pyramid network (BFPN) to aggregate shadow contexts spanned across different CNN layers.
- Direction-Aware Spatial Context Features for Shadow Detection248
A novel network for shadow detection is presented by analyzing image context in a direction-aware manner by introducing attention weights when aggregating spatial context features in a spatial recurrent neural network (RNN).
- 174
- Recurrently Aggregating Deep Features for Salient Object Detection164
This paper develops a novel deep saliency network equipped with recurrently aggregated deep features (RADF) to more accurately detect salient objects from an image by fully exploiting the complementary saliency information captured in different layers.
- 128
- Sparse Sampling Transformer with Uncertainty-Driven Ranking for Unified Removal of Raindrops and Rain Streaks89
This paper proposes a Sparse Sampling Transformer based on Uncertainty-Driven Ranking, dubbed UDR-S2Former, which can adaptively sample relevant image degradation information to model underlying degradation relationships and clearly outperforms state-of-the-art methods for all benchmarks.
- 86
- Neural Preset for Color Style Transfer73
A Neural Preset technique to address the limitations of existing color style transfer methods, including visual artifacts, vast memory requirement, and slow style switching speed, and it is shown that the trained model can naturally support multiple applications without fine-tuning.
- 70
- 66
- Cross-conditioned Diffusion Model for Medical Image to Image Translation58
A Cross-conditioned Diffusion Model (CDM) is introduced for medical image-to-image translation to use the distribution of target modalities as guidance to improve synthesis quality while achieving higher generation efficiency compared to conventional diffusion models.
- Unsupervised neighborhood component analysis for clustering56
The proposed algorithm aims to maximize a stochastic variant of the leave-one-out K-nearest neighbor (KNN) score on unlabeled data, which performs distance metric learning and clustering simultaneously, and can also learn a low dimensional projection of high dimensional data.
- Learning to Detect Specular Highlights from Real-world Images44
This paper presents a large-scale real-world highlight dataset containing a rich variety of material categories, with diverse highlight shapes and appearances, and develops a deep learning-based specular highlight detection network (SHDNet) leveraging multi-scale context contrasted features to accurately detect specular highlights of varying scales.
- 43
- A Simple Data Augmentation for Feature Distribution Skewed Federated Learning42
A simple yet remarkably effective input-level data augmentation method, namely FedRDN, which randomly injects the statistical information of the local distribution from the entire federation into the client’s data to mitigate feature shift, thereby mitigating feature shift.
- Diff-UNet: A diffusion embedded network for robust 3D medical image segmentation39
Experimental results on the three latest large-scale datasets show that the first diffusion-based model with two branches with two branches for general 3D medical image segmentation, Diff-UNet quantitatively and qualitatively outperforms state-of-the-art 3D medical segmentation methods, especially on regions with small or complex structures.
- Low-Res Leads the Way: Improving Generalization for Super-Resolution by Self-Supervised Learning37
This work introduces a novel “Low-Res Leads the Way” (LWay) training framework, merging Supervised Pre-training with Self-supervised Learning to enhance the adaptability of SR models to real-world images.
- 36
- 30
- 26
- 26
- 16
- 14
- 13
- 12
- 10
- 10
- 8
- 8
- Shape Mask Generator: Learning to Refine Shape Priors for Segmenting Overlapping Cervical Cytoplasms6
A conceptually simple and effective technique, called shape mask generator, for segmenting overlapping cytoplasms, which model shape priors from shape templates and feed them to the shape mask generators that generates a shape mask for the cytoplasm as the segmentation result.
- 5
- 4
- 3
- 2
- 2
- 2
- 1
- 1
- –
- –
- –
Publication data from OpenAlex; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-13. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.