# Lifelong Learning and Selective Forgetting via Contrastive Strategy

arXiv: https://arxiv.org/abs/2405.18663 · HTML: https://mlsanity.com/paper/2405.18663/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 39 references that are in the map.
- First posted on arXiv 28 May 2024.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Continual Learning with Deep Generative Replay](https://mlsanity.com/paper/1705.08690/) (2017)
- [Memory Aware Synapses: Learning what (not) to forget](https://mlsanity.com/paper/1711.09601/) (2017)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks](https://mlsanity.com/paper/1911.04933/) (2019)
- [A Survey on Contrastive Self-supervised Learning](https://mlsanity.com/paper/2011.00362/) (2020)
- [PathNet: Evolution Channels Gradient Descent in Super Neural Networks](https://mlsanity.com/paper/1701.08734/) (2017)
- [Modeling the Background for Incremental Learning in Semantic Segmentation](https://mlsanity.com/paper/2002.00718/) (2020)
- [DeltaGrad: Rapid retraining of machine learning models](https://mlsanity.com/paper/2006.14755/) (2020)
- [Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representations](https://mlsanity.com/paper/2103.06342/) (2021)
- [SSUL: Semantic Segmentation with Unknown Label for Exemplar-based Class-Incremental Learning](https://mlsanity.com/paper/2106.11562/) (2021)
- [Privacy Preserving Image-Based Localization](https://mlsanity.com/paper/1903.05572/) (2019)
- [Growing a Brain: Fine-Tuning by Increasing Model Capacity](https://mlsanity.com/paper/1907.07844/) (2019)
- [Generative Prompt Model for Weakly Supervised Object Localization](https://mlsanity.com/paper/2307.09756/) (2023)
- [Continual Learning for Image Segmentation with Dynamic Query](https://mlsanity.com/paper/2311.17450/) (2023)
- [Explore Faster Localization Learning For Scene Text Detection](https://mlsanity.com/paper/2207.01342/) (2022)
- [FlowText: Synthesizing Realistic Scene Text Video with Optical Flow Estimation](https://mlsanity.com/paper/2305.03327/) (2023)

## Built on by (most cited first, 3 of 3)

- [ErrorEraser: Unlearning Data Bias for Improved Continual Learning](https://mlsanity.com/paper/2506.09347/) (2025)
- [A Global-Local Cross-Attention Network for Ultra-high Resolution Remote Sensing Image Semantic Segmentation](https://mlsanity.com/paper/2506.19406/) (2025)
- [MAViE: A Multi-scale Adaptive Vision Encoder for Fine-grained Visual Perception and Efficient Multimodal Reasoning](https://mlsanity.com/paper/2607.24424/) (2026)

## Abstract (arXiv)

Lifelong learning aims to train a model with good performance for new tasks while retaining the capacity of previous tasks. However, some practical scenarios require the system to forget undesirable knowledge due to privacy issues, which is called selective forgetting. The joint task of the two is dubbed Learning with Selective Forgetting (LSF). In this paper, we propose a new framework based on contrastive strategy for LSF. Specifically, for the preserved classes (tasks), we make features extracted from different samples within a same class compacted. And for the deleted classes, we make the features from different samples of a same class dispersed and irregular, i.e., the network does not have any regular response to samples from a specific deleted class as if the network has no training at all. Through maintaining or disturbing the feature distribution, the forgetting and memory of different classes can be or independent of each other. Experiments are conducted on four benchmark datasets, and our method acieves new state-of-the-art.