Shuan

FireFlow-Fast-Inversion-of-Rectified-Flow-for-Image-Semantic-Editing. [ICML2025] An 8-step inversion and 8-step editing process works effectively with the FLUX-dev model. (3x speedup with results that are comparable or even superior to baseline methods)

ResNet-18-Caffemodel-on-ImageNet. ResNet-18 Caffemodel @ilsvrc12 shrt 256 with Top-1 69% Top-5 89%

ShuffleNet-An-Extremely-Efficient-CNN-for-Mobile-Devices-Caffe-Reimplementation. Caffe re-implementation of ShuffleNet

Zero-shot-Style-Transfer-via-Attention-Rearrangement. [CVPR2024] Official implementation of the paper "Z∗: Zero-shot Style Transfer via Attention Rearrangement" a.k.a. "Z∗: Zero-shot Style Transfer via Attention Reweighting"

Location-aware-Upsampling-for-Semantic-Segmentation. The Pytorch implementation of "Location-aware Upsampling for Semantic Segmentation" (LaU)

SNNs-Self-Normalizing-Neural-Networks-Caffe-Reimplementation. Caffe re-implementation of SNNs.

EDSR-ssim. Different SSIM metrics in CNN-based super resolution algorithms (e.g., EDSR CVPRW2017, RDN CVPR2018, MSRN ECCV2018).

Caffe-Computation-Graph-Optimization. Caffe Computation Graph Optimization.

Compact-Global-Descriptor. Pytorch implementation of "Compact Global Descriptor for Neural Networks" (CGD).

AIM2020-Real-Super-Resolution. Our solution to AIM2020 Real Image Super-Resolution Challenge (x2)

A-Variation-of-Dice-coefficient-Loss-Caffe-Layer. Compute the variation of dice coefficient loss for real-value regression task.

Dynamic-Network-Surgery-Caffe-Reimplementation. Caffe re-implementation of dynamic network surgery.

PyTorch-MixNet-SS. Extremely light-weight MixNet with Top-1 75.7% and 2.5M params

Inversion-Free-Style-Transfer-with-Dual-Rectified-Flows. Inversion-free Image Style Transfer

UCAS-Pattern-Recognition. The implementations of programming homeworks in UCAS PR class. (Autumn 2017-2018).

AlexNet-BN-Caffemodel-on-ImageNet. AlexNet-BN Caffemodel @ilsvrc12 shrt 256 with Top-1 60.43% Top-5 82.47%

Bias-Variance-Decomposition-for-KL-Divergence. This repository includes some detailed proofs of "Bias Variance Decomposition for KL Divergence".

News-Spider. Tencent NetEase SouHu etc. news spider. Including date, title, body and comments of the news.

Vision-Language-Action-VLA-for-Recommendation-System. Vision-Language-Action and world-model-based reinforcement learning for next-generation recommendation systems. (VLA+Rec 的一些想法)

EWGS. An official implementation of "Network Quantization with Element-wise Gradient Scaling" (CVPR 2021) in PyTorch.

MW-ISPNet. This is the official PyTorch implement of MW-ISPNet. Our Team recieved a Winner award in the AIM 2020 Learned Image ISP challenge (ECCVW 2020).