Pinned Repositories
Divide-and-Co-training
[TIP 2022] Towards Better Accuracy-efficiency Trade-offs: Divide and Co-training. Plus, an image classification toolbox includes ResNet, Wide-ResNet, ResNeXt, ResNeSt, ResNeXSt, SENet, Shake-Shake, DenseNet, PyramidNet, and EfficientNet.
CenterCLIP
[SIGIR 2022] CenterCLIP: Token Clustering for Efficient Text-Video Retrieval. Also, a text-video retrieval toolbox based on CLIP + fast pyav video decoding.
CLIP4STR
[TIP 2024] CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model.
RLCF
[ICLR 2024] Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models.
simple_flann
simple_flann包括一个KDTrees检索算法和一个基于p稳定分布的LSH
SlimCLR
[IJCV 2024] Slimmable Networks for Contrastive Self-supervised Learning.
OpenRLHF
An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & RingAttention)
CLIP4STR
An implementation of "CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model".
RMI
This is the code for the NeurIPS 2019 paper Region Mutual Information Loss for Semantic Segmentation.
mzhaoshuai's Repositories
mzhaoshuai/CenterCLIP
[SIGIR 2022] CenterCLIP: Token Clustering for Efficient Text-Video Retrieval. Also, a text-video retrieval toolbox based on CLIP + fast pyav video decoding.
mzhaoshuai/RLCF
[ICLR 2024] Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models.
mzhaoshuai/simple_flann
simple_flann包括一个KDTrees检索算法和一个基于p稳定分布的LSH
mzhaoshuai/SlimCLR
[IJCV 2024] Slimmable Networks for Contrastive Self-supervised Learning.
mzhaoshuai/CLIP4STR
[TIP 2024] CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model.
mzhaoshuai/GLaDOS-CheckIn
GLaDOS AutoCheckIn 定时自动签到