-
Nanjing University
- www.liwenbin.cn
Stars
[ICCV 2025] Official code of paper "Dynamic Multi-Layer Null Space Projection for Vision-Language Continual Learning"
[TPAMI 2025] Official code of paper "ONNXPruner: ONNX-Based General Model Pruning Adapter"
Official github repo for SafeDialBench, a comprehensive multi-turn dialogue benchmark to evaluate LLMs' safety.
Exploiting Inter-sample and Inter-feature Relations in Dataset Distillation (CVPR24)
The Pytorch code of "Defensive Few-Shot Learning", TPAMI 2023.
The PyTorch code of "Trip-ROMA: Self-Supervised Learning with Triplets and Random Mappings", TMLR 2023.
A playbook for systematically maximizing the performance of deep learning models.
[CVPR 2023] Modeling Inter-Class and Intra-Class Constraints in Novel Class Discovery
Official implementation of Diffusion Autoencoders
Experiment on combining CLIP with SAM to do open-vocabulary image segmentation.
Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learning
solo-learn: a library of self-supervised methods for visual representation learning powered by Pytorch Lightning
PyCIL: A Python Toolbox for Class-Incremental Learning
PyTorch implementation of adversarial attacks [torchattacks]
Adversarial attacks including DeepFool and C&W
[ICCV 2021] Towards Interpretable Deep Metric Learning with Structural Matching
The road to hack SysML and become an system expert
LoFGAN: Fusing Local Representations for Few-shot Image Generation. (ICCV 2021)
Google Research
[TPAMI 2023] LibFewShot: A Comprehensive Library for Few-shot Learning.
X-modaler is a versatile and high-performance codebase for cross-modal analytics(e.g., image captioning, video captioning, vision-language pre-training, visual question answering, visual commonsens…
PyTorch implementation of SimSiam https//arxiv.org/abs/2011.10566
A review for latest few-shot learning works