Upload 5 files

Pretrain_1K_S.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:500747ef072bc15c441c4db4c14d49d1611165707e79a667bd836a685a899772
+size 307815239

Pretrain_mini_B.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e717a01a944f19cc8689f4e87f2d2fcd11d0bfa06f0c368fe0d1d0ea906926a8
+size 1343778951

Pretrain_mini_L.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cc671e9a67cfe10301681698912fd245f1913845780cab4944405333e9bf486
+size 3955103761

Pretrain_mini_S.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e940d04dd3e1b8c69a4b8550f49e4fa4b66e6530636ad557d6ca7a0ed86ce252
+size 307815239

README.md

@@ -0,0 +1,132 @@
+---
+license: apache-2.0
+tags:
+- masked-image-modeling
+- self-supervised-learning
+- visual-representation-learning
+- vision-transformer
+- mae
+- pytorch
+---
+
+<a id="top"></a>
+<div align="center">
+  <h1> CurMIM: Curriculum Masked Image Modeling</h1>
+
+  <p>
+    <b>Hao Liu</b><sup>1</sup>&nbsp;
+    <b>Kun Wang</b><sup>1</sup>&nbsp;
+    <b>Yudong Han</b><sup>1</sup>&nbsp;
+    <b>Haocong Wang</b><sup>1</sup>&nbsp;
+    <b>Yupeng Hu</b><sup>1</sup>&nbsp;
+    <b>Chunxiao Wang</b><sup>2</sup>&nbsp;
+    <b>Liqiang Nie</b><sup>3</sup>
+  </p>
+
+  <p>
+    <sup>1</sup>School of Software, Shandong University, Jinan, China<br>
+    <sup>2</sup>Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China<br>
+    <sup>3</sup>School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China
+  </p>
+</div>
+
+This is the official PyTorch implementation of **CurMIM**, a curriculum-based masked image modeling framework for self-supervised visual representation learning.
+
+🔗 **Paper:** [CurMIM: Curriculum Masked Image Modeling](https://ieeexplore.ieee.org/document/10890877)
+🔗 **GitHub Repository:** [iLearn-Lab/ICASSP25-CurMIM](https://github.com/iLearn-Lab/ICASSP25-CurMIM)
+
+---
+
+##  Model Information
+
+### 1. Model Name
+**CurMIM** (**Cur**riculum **M**asked **I**mage **M**odeling).
+
+### 2. Task Type & Applicable Tasks
+- **Task Type:** Masked Image Modeling (MIM) / Self-Supervised Visual Representation Learning / Vision Transformer Pretraining
+- **Applicable Tasks:** Curriculum-based masked image pretraining, visual representation learning, finetuning, and linear probing for image classification.
+
+### 3. Project Introduction
+Masked Image Modeling (MIM) usually adopts a fixed masking strategy during pretraining. **CurMIM** introduces a curriculum-style masking strategy that progressively adjusts masking behavior, enabling the model to learn from easier to harder reconstruction targets and thereby improving representation quality.
+
+The repository provides a complete workflow for **pretraining**, **finetuning**, and **linear probing**, together with utilities for distributed training and experiment management.
+
+### 4. Training Data Source
+The model follows the dataset preparation protocol of [MAE](https://github.com/facebookresearch/mae) and is mainly designed for:
+- **ImageNet**
+- **miniImageNet**
+
+---
+
+##  Usage & Basic Inference
+
+This codebase provides scripts for curriculum-based MIM pretraining, finetuning, and linear probing.
+
+### Step 1: Prepare the Environment
+Clone the GitHub repository and install dependencies:
+```bash
+git clone https://github.com/iLearn-Lab/ICASSP25-CurMIM.git
+cd CurMIM
+python -m venv .venv
+source .venv/bin/activate   # Linux / Mac
+# .venv\Scripts\activate    # Windows
+pip install torch torchvision timm==0.3.2 tensorboard
+```
+
+### Step 2: Download Model Weights & Data
+Follow [MAE](https://github.com/facebookresearch/mae)'s dataset preparation for [ImageNet](https://www.image-net.org/).
+
+
+### Step 3: Run Testing / Inference
+To pretrain the model, run:
+```bash
+python -m torch.distributed.launch --nproc_per_node {GPU_number} ./main_pretrain.py --batch_size 128 \
+--accum_iter 2 \
+--model {model_type} \
+--mask_ratio 0.75 --epochs 300 --warmup_epochs 40 \
+--blr 4e-4 --weight_decay 0.05 \
+--data_path ../path --output_dir ./output_dir/
+```
+
+To finetune the model, run:
+```bash
+python -m torch.distributed.launch --nproc_per_node={GPU_number} ./main_finetune.py \
+    --batch_size 128 \
+    --nb_classes {nb_classes} \
+    --model {model_type} \
+    --finetune ./checkpoint.pth \
+    --epochs 100 \
+    --blr 1e-3 --layer_decay 0.65 --output_dir ./finetune \
+    --weight_decay 0.05 --drop_path 0.1 --mixup 0.8 --cutmix 1.0 --reprob 0.25 \
+    --dist_eval --data_path ../data/
+```
+
+---
+
+##  Limitations & Notes
+
+**Disclaimer:** This repository is intended for **academic research purposes only**.
+- The model requires access to the original datasets for pretraining and downstream evaluation.
+- Training performance may vary depending on model size, masking ratio, and distributed training configuration.
+- Users should prepare the dataset following the MAE protocol before reproduction.
+
+---
+
+## Citation
+
+If you find our work useful in your research, please consider citing our paper:
+
+```bibtex
+@inproceedings{liu2025curmim,
+  title={CurMIM: Curriculum Masked Image Modeling},
+  author={Liu, Hao and Wang, Kun and Han, Yudong and Wang, Haocong and Hu, Yupeng and Wang, Chunxiao and Nie, Liqiang},
+  booktitle={2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
+  pages={1--5},
+  year={2025},
+  doi={10.1109/ICASSP49660.2025.10890877}
+}
+```
+
+---
+## Contact
+**If you have any questions, feel free to contact me at liuh90210@gmail.com**.