mlsanityData to 7 Oct 2026

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

arXiv 2007.00197 ↗First posted 1 Jul 2020cs.LG eess.IV stat.MLcited by 21

Not on the map. Why?

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.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 1; 2023: 10; 2024: 8; 2025: 1.

21 papers.

Sort:

By area:

  1. 2023Neuron Activation Coverage: Rethinking Out-of-distribution Detection and Generalizationcited by 28
  2. 2023A Survey on the Robustness of Computer Vision Models against Common Corruptionscited by 20
  3. 2021Cognitively Inspired Learning of Incremental Drifting Conceptscited by 16
  4. 2023Unsupervised Domain Adaptation for Training Event-Based Networks Using Contrastive Learning and Uncorrelated Conditioningcited by 14
  5. 2022Unsupervised Model Adaptation for Source-free Segmentation of Medical Imagescited by 13
  6. 2024Enhancing Traffic Safety with Parallel Dense Video Captioning for End-to-End Event Analysiscited by 9
  7. 2024Dynamic Transformer Architecture for Continual Learning of Multimodal Taskscited by 8
  8. 2023History Repeats: Overcoming Catastrophic Forgetting For Event-Centric Temporal Knowledge Graph Completioncited by 5
  9. 2023Improved Region Proposal Network for Enhanced Few-Shot Object Detectioncited by 5
  10. 2023Preserving Fairness in AI under Domain Shiftcited by 3
  11. 2023Graph Harmony: Denoising and Nuclear-Norm Wasserstein Adaptation for Enhanced Domain Transfer in Graph-Structured Datacited by 2
  12. 2023Explainable Artificial Intelligence Architecture for Melanoma Diagnosis Using Indicator Localization and Self-Supervised Learningcited by 2
9 more
  1. 2023Cognitively Inspired Cross-Modal Data Generation Using Diffusion Modelscited by 1
  2. 2024Continuous Unsupervised Domain Adaptation Using Stabilized Representations and Experience Replaycited by 1
  3. 2023Robust Internal Representations for Domain Generalizationcited by 0
  4. 2024Online Continual Domain Adaptation for Semantic Image Segmentation Using Internal Representationscited by 0
  5. 2024Relating Events and Frames Based on Self-Supervised Learning and Uncorrelated Conditioning for Unsupervised Domain Adaptationcited by 0
  6. 2024Unsupervised Federated Domain Adaptation for Segmentation of MRI Imagescited by 0
  7. 2024Unsupervised Domain Adaptation Using Compact Internal Representationscited by 0
  8. 2024Early Detection of Misinformation for Infodemic Management: A Domain Adaptation Approachcited by 0
  9. 2025OT Score: An OT based Confidence Score for Prototype-Assisted Source Free Unsupervised Domain Adaptationcited by 0