# Technical Report for the 5th CLVision Challenge at CVPR: Addressing the Class-Incremental with Repetition using Unlabeled Data -- 4th Place Solution

arXiv: https://arxiv.org/abs/2503.15697 · HTML: https://mlsanity.com/paper/2503.15697/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 13 references that are in the map.
- First posted on arXiv 19 Mar 2025.

## Builds on (most cited first, 10 of 10)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [A Survey on Deep Semi-supervised Learning](https://mlsanity.com/paper/2103.00550/) (2021)
- [Class-Incremental Learning: A Survey](https://mlsanity.com/paper/2302.03648/) (2023)
- [Avalanche: an End-to-End Library for Continual Learning](https://mlsanity.com/paper/2104.00405/) (2021)
- [Avalanche: A PyTorch Library for Deep Continual Learning](https://mlsanity.com/paper/2302.01766/) (2023)
- [An Investigation of Replay-based Approaches for Continual Learning](https://mlsanity.com/paper/2108.06758/) (2021)
- [Localizing Catastrophic Forgetting in Neural Networks](https://mlsanity.com/paper/1906.02568/) (2019)

## Abstract (arXiv)

This paper outlines our approach to the 5th CLVision challenge at CVPR, which addresses the Class-Incremental with Repetition (CIR) scenario. In contrast to traditional class incremental learning, this novel setting introduces unique challenges and research opportunities, particularly through the integration of unlabeled data into the training process. In the CIR scenario, encountered classes may reappear in later learning experiences, and each experience may involve only a subset of the overall class distribution. Additionally, the unlabeled data provided during training may include instances of unseen classes, or irrelevant classes which should be ignored. Our approach focuses on retaining previously learned knowledge by utilizing knowledge distillation and pseudo-labeling techniques. The key characteristic of our method is the exploitation of unlabeled data during training, in order to maintain optimal performance on instances of previously encountered categories and reduce the detrimental effects of catastrophic forgetting. Our method achieves an average accuracy of 16.68% during the pre-selection phase and 21.19% during the final evaluation phase, outperforming the baseline accuracy of 9.39%. We provide the implementation code at https://github.com/panagiotamoraiti/continual-learning-challenge-2024 .