metadata
license: mit
pipeline_tag: image-classification
TALON: Test-time Adaptive Learning for On-the-Fly Category Discovery
TALON is a test-time adaptation framework for on-the-fly category discovery (OCD) that enables a model to recognize known categories while simultaneously discovering novel ones from an unlabeled online stream.
This repository contains the official implementation and weights for the paper TALON: Test-time Adaptive Learning for On-the-Fly Category Discovery, presented at CVPR 2026.
- GitHub: https://github.com/ynanwu/TALON
- Paper: arXiv:2603.08075
Method Overview
Existing OCD methods often freeze the feature extractor, which limits the learning potential of incoming data. TALON addresses this with two complementary strategies:
- Semantic-aware prototype update: Dynamically refines class prototypes to improve classification.
- Stable test-time encoder update: Integrates new information directly into the parameter space.
- Margin-aware logit calibration: Applied during the offline stage to reserve embedding space for future class discovery.
Installation
This project uses uv for dependency management.
# Clone the repository
git clone https://github.com/ynanwu/TALON
cd TALON
# Install all dependencies
uv sync
Usage
To evaluate a pretrained checkpoint (e.g., CUB with a CLIP backbone):
uv run test.py --dataset_name cub --backbone clip --ckpt_path checkpoints/clip/cub/best_model.pth
Citation
If you find this work useful for your research, please consider citing the paper:
@inproceedings{talon2026,
title={TALON: Test-time Adaptive Learning for On-the-Fly Category Discovery},
author={Wu, Yanan and Yan, Yuhan and Chen, Tailai and Chi, Zhixiang and Wu, ZiZhang and Jin, Yi and Wang, Yang and Li Zhenbo},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year={2026}
}