Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks211 from public data
- Frequency-Aware Feature Fusion for Dense Image Prediction325
Comprehensive visualization and quantitative analysis demonstrate that FreqFusion effectively improves feature consistency and sharpens object boundaries, and extensive experiments across various dense prediction tasks confirm its effectiveness.
- Partial FC: Training 10 Million Identities on a Single Machine300
This work theoretically analyze the upper limit of model parallelism in face recognition and proposes a load-balanced sparse distributed classification training method, Partial FC, which is capable of using a machine with only 8 Nvidia Tesla V100 GPUs to implement training on a face recognition data set with up to 29 million IDs.
- Infrared Small Target Detection with Scale and Location Sensitivity292
A novel Scale and Location Sensitive (SLS) loss is proposed to handle the limitations of existing losses and a simple Multi-Scale Head to the plain U-Net (MSHNet) is designed, which outperforms existing state-of-the-art methods by a large margin.
- A Physics-Based Noise Formation Model for Extreme Low-Light Raw Denoising280
A highly accurate noise formation model based on the characteristics of CMOS photosensors is presented, thereby enabling us to synthesize realistic samples that better match the physics of image formation process.
- 3-D Quasi-Recurrent Neural Network for Hyperspectral Image Denoising247
An alternating directional 3-D quasi-recurrent neural network for hyperspectral image (HSI) denoising, which can effectively embed the domain knowledge—structural spatiospectral correlation and global correlation along spectrum (GCS).
- Single Image Reflection Removal Exploiting Misaligned Training Data and Network Enhancements201
Experimental results collectively show that the method outperforms the state-of-the-art with aligned data, and that significant improvements are possible when using additional misaligned data.
- 201
- 192
- Physics-based Noise Modeling for Extreme Low-light Photography188
Extensive experiments on multiple low-light denoising datasets show that a deep neural network trained with the proposed noise formation model can reach surprisingly-high accuracy, opening a new door to real-world extreme low- light photography.
- Deep-Learning-Based Semantic Segmentation of Remote Sensing Images: A Survey173
A comprehensive review of semantic segmentation models based on deep learning in SSRSI, including semisupervised and weakly-supervised SSRSI, unsupervised domain adaption in SSRSI, multimodal data-fusion-based SSRSI, and pretrained models for SSRSI are reviewed.
- 173
- 141
- Spectral Enhanced Rectangle Transformer for Hyperspectral Image Denoising134
This paper proposes a spectral enhanced rectangle Trans-former, driving it to explore the nonlocal spatial similarity and global spectral low-rank property of HSIs, and designs a spectral enhancement module that is capable of extracting global underlying low- rank property of spatial-spectral cubes to suppress noise.
- Instance Segmentation in the Dark128
This work takes a deep look at instance segmentation in the dark and introduces several techniques that substantially boost the low-light inference accuracy and discovers that high-bit-depth RAW images can better preserve richer scene information in low-light conditions compared to typical camera sRGB outputs, thus supporting the use of RAW-input algorithms.
- 126
- 118
- Frequency Dynamic Convolution for Dense Image Prediction114
Frequency Dynamic Convolution is introduced, a novel approach that mitigates limitations by learning a fixed parameter budget in the Fourier domain and seamlessly integrates into a variety of architectures, including ConvNeXt, Swin-Transformer, offering a flexible and efficient solution for modern vision tasks.
- 107
- 105
- Bidirectional 3D Quasi-Recurrent Neural Network for Hyperspectral Image Super-Resolution103
A bidirectional 3D quasi-recurrent neural network is designed that can be well generalized to remote sensing HSI datasets with limited number of training data and demonstrates improvements over state-of-the-art methods, in terms of both restoration accuracy and visual quality.
- 101
- LG-BPN: Local and Global Blind-Patch Network for Self-Supervised Real-World Denoising99
A novel method called LG-BPN is presented, which takes the spatial correlation statistic into the authors' network design for local detail restoration, and also brings the long-range dependencies modeling ability to previously CNN-based BSN methods.
- 98
- 90
- 90
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-14. 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.