(AAAI 2026) HABIT: Chrono-Synergia Robust Progressive Learning Framework for Composed Image Retrieval

Zixu Li¹, Yupeng Hu^1✉, Zhiwei Chen¹, Shiqi Zhang¹, Qinlei Huang¹, Zhiheng Fu¹, Yinwei Wei¹

¹School of Software, Shandong University
^✉Corresponding author

Accepted by AAAI 2026: A robust progressive learning framework tackling the Noise Triplet Correspondence (NTC) problem in Composed Image Retrieval (CIR).

📌 Introduction

HABIT (cHrono-synergiA roBust progressIve learning framework for composed image reTrieval) is our proposed robust learning framework for Composed Image Retrieval, accepted by AAAI 2026. Based on an in-depth analysis of the "Noisy Triplet Correspondence (NTC)" problem in real-world retrieval scenarios, HABIT effectively addresses the shortcomings of existing methods in precisely estimating composed semantic discrepancies and progressively adapting to modification discrepancies.

⬆ Back to top

📢 News

[2026-03-20] 🚀 Official paper is released at AAAI 2026.

[2026-03-18] 🚀 Released all codes for HABIT.
[2025-11-08] 🔥 Our paper "HABIT: Chrono-Synergia Robust Progressive Learning Framework for Composed Image Retrieval" has been accepted by AAAI 2026!

⬆ Back to top

✨ Key Features

🧠 Mutual Knowledge Estimation (MKE): Precisely quantifies sample cleanliness by computing the Transition Rate of mutual knowledge between composed features and target images, effectively identifying clean samples that align with modification semantics.
⏳ Dual-consistency Progressive Learning (DPL): Introduces a collaborative mechanism between historical and current models to simulate human habit formation (retaining good habits and calibrating bad ones), enabling robust learning against noisy data interference.
🛡️ Highly Robust to NTC: Maintains State-of-the-Art (SOTA) retrieval performance under various Noise Triplet Correspondence (NTC) settings with different noise ratios (0%, 20%, 50%, 80%).

⬆ Back to top

🏗️ Architecture

Figure 1. HABIT consists of two modules: (a) Mutual Knowledge Estimation and (b) Dual-consistency Progressive Learning.

⬆ Back to top

🏃‍♂️ Experiment-Results

CIR Task Performance

💡 Note for Fully-Supervised CIR Benchmarking:
🎯 The 0% noise setting in the table below is equivalent to the traditional fully-supervised CIR paradigm. We highlight this 0% block to facilitate direct and fair comparisons for researchers working on conventional supervised methods.

FIQ:

Table 1. Performance comparison on FashionIQ in terms of R@K (%). The best result under each noise ratio is highlighted in bold, while the second-best result is underlined.

CIRR：

Table 2. Performance comparison on the CIRR test set in terms of R@K (%) and Rsub@K (%). The best and second-best results are highlighted in bold and underlined, respectively.

⬆ Back to top

Introduction
News
Key Features
Architecture
Experiment Results
Install
Data Preparation
Quick Start
- Training under Noisy Settings
- Testing
Project Structure
Acknowledgement
Contact
Citation
Support & Contributing

📦 Install

1. Clone the repository

git clone https://github.com/Lee-zixu/HABIT
cd HABIT

2. Setup Python Environment

The code is evaluated on Python 3.8.10 and CUDA 12.6. We recommend using Anaconda to create an isolated virtual environment:

conda create -n habit python=3.8
conda activate habit

# Install PyTorch (The evaluated environment uses Torch 2.1.0 with CUDA 12.1 compatibility)
pip install torch==2.1.0 torchvision==0.16.0 torchaudio==2.1.0 --index-url [https://download.pytorch.org/whl/cu121](https://download.pytorch.org/whl/cu121)

# Install core dependencies
pip install open-clip-torch==2.24.0 scikit-learn==1.3.2 transformers==4.25.0 salesforce-lavis==1.0.2 timm==0.9.16

Note: Key dependencies include salesforce-lavis for the base architecture, open-clip-torch for vision-language features, and scikit-learn for DBSCAN clustering during Noise Discrimination.

⬆ Back to top

📂 Data Preparation

We evaluated our framework on two standard datasets: FashionIQ and CIRR. Please download the datasets first.

Click to expand: FashionIQ Dataset Directory Structure

Please follow the official instructions to download the FashionIQ dataset. Once downloaded, ensure the folder structure looks like this:

├── FashionIQ
│   ├── captions
│   │   ├── cap.dress.[train | val | test].json
│   │   ├── cap.toptee.[train | val | test].json
│   │   ├── cap.shirt.[train | val | test].json
│   ├── image_splits
│   │   ├── split.dress.[train | val | test].json
│   │   ├── split.toptee.[train | val | test].json
│   │   ├── split.shirt.[train | val | test].json
│   ├── dress
│   │   ├── [B000ALGQSY.jpg | B000AY2892.jpg | B000AYI3L4.jpg |...]
│   ├── shirt
│   │   ├── [B00006M009.jpg | B00006M00B.jpg | B00006M6IH.jpg | ...]
│   ├── toptee
│   │   ├── [B0000DZQD6.jpg | B000A33FTU.jpg | B000AS2OVA.jpg | ...]

Click to expand: CIRR Dataset Directory Structure

Please follow the official instructions to download the CIRR dataset. Once downloaded, ensure the folder structure looks like this:

├── CIRR
│   ├── train
│   │   ├── [0 | 1 | 2 | ...]
│   │   │   ├── [train-10108-0-img0.png | train-10108-0-img1.png | ...]
│   ├── dev
│   │   ├── [dev-0-0-img0.png | dev-0-0-img1.png | ...]
│   ├── test1
│   │   ├── [test1-0-0-img0.png | test1-0-0-img1.png | ...]
│   ├── cirr
│   ├── captions
│   │   ├── cap.rc2.[train | val | test1].json
│   ├── image_splits
│   │   ├── split.rc2.[train | val | test1].json

⬆ Back to top

🚀 Quick Start

1. Training under Noisy Settings

In our implementation, we introduce the noise_ratio parameter to simulate varying degrees of NTC (Noise Triplet Correspondence) interference. You can reproduce the experimental results from the paper by modifying the --noise_ratio parameter (default options evaluated are 0.0, 0.2, 0.5, 0.8).

Training on FashionIQ:

python train.py \
    --dataset fashioniq \
    --fashioniq_path "/path/to/FashionIQ/" \
    --model_dir "./checkpoints/fashioniq_noise0.2" \
    --noise_ratio 0.2 \
    --batch_size 256 \
    --num_epochs 20 \
    --lr 2e-5

Training on CIRR:

python train.py \
    --dataset cirr \
    --cirr_path "/path/to/CIRR/" \
    --model_dir "./checkpoints/cirr_noise0.5" \
    --noise_ratio 0.5 \
    --batch_size 256 \
    --num_epochs 20 \
    --lr 2e-5

💡 Tips: > - Our model is based on the powerful BLIP-2 architecture. It is highly recommended to run the training on GPUs with sufficient memory (e.g., NVIDIA A40 48G / V100 32G).

The best model weights and evaluation metrics generated during training will be automatically saved in the best_model.pt and metrics_best.json files within your specified --model_dir.

2. Testing

To generate the prediction files on the CIRR dataset for submission to the CIRR Evaluation Server, run the following command:

python src/cirr_test_submission.py checkpoints/cirr_noise0.5/

(The corresponding script will automatically output .json based on the generated best checkpoints in the folder for online evaluation.)

⬆ Back to top

📁 Project Structure

Our code is deeply customized based on the LAVIS framework. The core implementations are centralized in the following files:

HABIT/
├── lavis/
│   ├── models/
│   │   └── blip2_models/
│   │       └── HABIT.py      # 🧠 Core model implementation: Includes MKE, DPL modules, and loss functions
├── train.py                  # 🚀 Training entry point: Controls noise_ratio injection and training loops
├── datasets.py 
├── test.py 
├── utils.py 
├── data_utils.py 
├── cirr_test_submission.py   # Auxiliary scripts
├── datasets/                 # Dataset loading and processing logic
└── README.md

🤝 Acknowledgement

The implementation of this project references the LAVIS framework and the noise setting concepts from TME. We express our sincere gratitude to these open-source contributions!

⬆ Back to top

✉️ Contact

For any questions, issues, or feedback, please open an issue on GitHub or reach out to me at lizixu.cs@gmail.com.

⬆ Back to top

🔗 Related Projects

Ecosystem & Other Works from our Team

TEMA (ACL'26) Web \| Code \|	ConeSep (CVPR'26) Web \| Code \|	Air-Know (CVPR'26) Web \| Code \|
ReTrack (AAAI'26) Web \| Code \| Paper	INTENT (AAAI'26) Web \| Code \| Paper	HUD (ACM MM'25) Web \| Code \| Paper
OFFSET (ACM MM'25) Web \| Code \| Paper	ENCODER (AAAI'25) Web \| Code \| Paper

📝⭐️ Citation

If you find our work or this code useful in your research, please consider leaving a Star⭐️ or Citing📝 our paper 🥰. Your support is our greatest motivation!

@inproceedings{HABIT,
  title={HABIT: Chrono-Synergia Robust Progressive Learning Framework for Composed Image Retrieval},
  author={Li, Zixu and Hu, Yupeng and Chen, Zhiwei and Zhang, Shiqi and Huang, Qinlei and Fu, Zhiheng and Wei, Yinwei},
  booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
  year={2026}
}

⬆ Back to top

🫡 Support & Contributing

We welcome all forms of contributions! If you have any questions, ideas, or find a bug, please feel free to:

Open an Issue for discussions or bug reports.
Submit a Pull Request to improve the codebase.

⬆ Back to top

📄 License

This project is released under the terms of the LICENSE file included in this repository.

TEMA (ACL'26) Web \| Code \|	ConeSep (CVPR'26) Web \| Code \|	Air-Know (CVPR'26) Web \| Code \|
ReTrack (AAAI'26) Web \| Code \| Paper	INTENT (AAAI'26) Web \| Code \| Paper	HUD (ACM MM'25) Web \| Code \| Paper
OFFSET (ACM MM'25) Web \| Code \| Paper	ENCODER (AAAI'25) Web \| Code \| Paper

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

(AAAI 2026) HABIT: Chrono-Synergia Robust Progressive Learning Framework for Composed Image Retrieval

📌 Introduction

📢 News

✨ Key Features

🏗️ Architecture

🏃‍♂️ Experiment-Results

CIR Task Performance

FIQ:

CIRR：

Table of Contents

📦 Install

📂 Data Preparation

🚀 Quick Start

1. Training under Noisy Settings

2. Testing

📁 Project Structure

🤝 Acknowledgement

✉️ Contact

🔗 Related Projects

📝⭐️ Citation

🫡 Support & Contributing

📄 License

FilesExpand file tree

README.md

Latest commit

History

README.md

File metadata and controls

(AAAI 2026) HABIT: Chrono-Synergia Robust Progressive Learning Framework for Composed Image Retrieval

📌 Introduction

📢 News

✨ Key Features

🏗️ Architecture

🏃‍♂️ Experiment-Results

CIR Task Performance

FIQ:

CIRR：

Table of Contents

📦 Install

📂 Data Preparation

🚀 Quick Start

1. Training under Noisy Settings

2. Testing

📁 Project Structure

🤝 Acknowledgement

✉️ Contact

🔗 Related Projects

📝⭐️ Citation

🫡 Support & Contributing

📄 License