# Overcoming Concept Shift in Domain-Aware Settings through Consolidated Internal Distributions

arXiv: https://arxiv.org/abs/2007.00197 · HTML: https://mlsanity.com/paper/2007.00197/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jul 2020.

## Built on by (most cited first, 21 of 21)

- [Neuron Activation Coverage: Rethinking Out-of-distribution Detection and Generalization](https://mlsanity.com/paper/2306.02879/) (2023)
- [A Survey on the Robustness of Computer Vision Models against Common Corruptions](https://mlsanity.com/paper/2305.06024/) (2023)
- [Cognitively Inspired Learning of Incremental Drifting Concepts](https://mlsanity.com/paper/2110.04662/) (2021)
- [Unsupervised Domain Adaptation for Training Event-Based Networks Using Contrastive Learning and Uncorrelated Conditioning](https://mlsanity.com/paper/2303.12424/) (2023)
- [Unsupervised Model Adaptation for Source-free Segmentation of Medical Images](https://mlsanity.com/paper/2211.00807/) (2022)
- [Enhancing Traffic Safety with Parallel Dense Video Captioning for End-to-End Event Analysis](https://mlsanity.com/paper/2404.08229/) (2024)
- [Dynamic Transformer Architecture for Continual Learning of Multimodal Tasks](https://mlsanity.com/paper/2401.15275/) (2024)
- [History Repeats: Overcoming Catastrophic Forgetting For Event-Centric Temporal Knowledge Graph Completion](https://mlsanity.com/paper/2305.18675/) (2023)
- [Improved Region Proposal Network for Enhanced Few-Shot Object Detection](https://mlsanity.com/paper/2308.07535/) (2023)
- [Preserving Fairness in AI under Domain Shift](https://mlsanity.com/paper/2301.12369/) (2023)
- [Graph Harmony: Denoising and Nuclear-Norm Wasserstein Adaptation for Enhanced Domain Transfer in Graph-Structured Data](https://mlsanity.com/paper/2301.12361/) (2023)
- [Explainable Artificial Intelligence Architecture for Melanoma Diagnosis Using Indicator Localization and Self-Supervised Learning](https://mlsanity.com/paper/2303.14615/) (2023)
- [Cognitively Inspired Cross-Modal Data Generation Using Diffusion Models](https://mlsanity.com/paper/2305.18433/) (2023)
- [Continuous Unsupervised Domain Adaptation Using Stabilized Representations and Experience Replay](https://mlsanity.com/paper/2402.00580/) (2024)
- [Robust Internal Representations for Domain Generalization](https://mlsanity.com/paper/2309.15522/) (2023)
- [Online Continual Domain Adaptation for Semantic Image Segmentation Using Internal Representations](https://mlsanity.com/paper/2401.01035/) (2024)
- [Relating Events and Frames Based on Self-Supervised Learning and Uncorrelated Conditioning for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2401.01042/) (2024)
- [Unsupervised Federated Domain Adaptation for Segmentation of MRI Images](https://mlsanity.com/paper/2401.02941/) (2024)
- [Unsupervised Domain Adaptation Using Compact Internal Representations](https://mlsanity.com/paper/2401.07207/) (2024)
- [Early Detection of Misinformation for Infodemic Management: A Domain Adaptation Approach](https://mlsanity.com/paper/2406.10238/) (2024)
- [OT Score: An OT based Confidence Score for Prototype-Assisted Source Free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2505.11669/) (2025)

## Abstract (arXiv)

We develop an algorithm to improve the performance of a pre-trained model under concept shift without retraining the model from scratch when only unannotated samples of initial concepts are accessible. We model this problem as a domain adaptation problem, where the source domain data is inaccessible during model adaptation. The core idea is based on consolidating the intermediate internal distribution, learned to represent the source domain data, after adapting the model. We provide theoretical analysis and conduct extensive experiments to demonstrate that the proposed method is effective.