# Adaptively-Accumulated Knowledge Transfer for Partial Domain Adaptation

arXiv: https://arxiv.org/abs/2008.11873 · HTML: https://mlsanity.com/paper/2008.11873/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Aug 2020.

## Built on by (most cited first, 9 of 9)

- [Transferrable Contrastive Learning for Visual Domain Adaptation](https://mlsanity.com/paper/2112.07516/) (2021)
- [Towards Novel Target Discovery Through Open-Set Domain Adaptation](https://mlsanity.com/paper/2105.02432/) (2021)
- [Partial Network Cloning](https://mlsanity.com/paper/2303.10597/) (2023)
- [Jacobian Norm for Unsupervised Source-Free Domain Adaptation](https://mlsanity.com/paper/2204.03467/) (2022)
- [Calibrating Class Weights with Multi-Modal Information for Partial Video Domain Adaptation](https://mlsanity.com/paper/2204.06187/) (2022)
- [Coupling Adversarial Learning with Selective Voting Strategy for Distribution Alignment in Partial Domain Adaptation](https://mlsanity.com/paper/2207.08145/) (2022)
- [Subtype-Aware Dynamic Unsupervised Domain Adaptation](https://mlsanity.com/paper/2208.07754/) (2022)
- [Robust Class-Conditional Distribution Alignment for Partial Domain Adaptation](https://mlsanity.com/paper/2310.12060/) (2023)
- [Cross-Domain Attribute Alignment with CLIP: A Rehearsal-Free Approach for Class-Incremental Unsupervised Domain Adaptation](https://mlsanity.com/paper/2509.11264/) (2025)

## Abstract (arXiv)

Partial domain adaptation (PDA) attracts appealing attention as it deals with a realistic and challenging problem when the source domain label space substitutes the target domain. Most conventional domain adaptation (DA) efforts concentrate on learning domain-invariant features to mitigate the distribution disparity across domains. However, it is crucial to alleviate the negative influence caused by the irrelevant source domain categories explicitly for PDA. In this work, we propose an Adaptively-Accumulated Knowledge Transfer framework (A2KT) to align the relevant categories across two domains for effective domain adaptation. Specifically, an adaptively-accumulated mechanism is explored to gradually filter out the most confident target samples and their corresponding source categories, promoting positive transfer with more knowledge across two domains. Moreover, a dual distinct classifier architecture consisting of a prototype classifier and a multilayer perceptron classifier is built to capture intrinsic data distribution knowledge across domains from various perspectives. By maximizing the inter-class center-wise discrepancy and minimizing the intra-class sample-wise compactness, the proposed model is able to obtain more domain-invariant and task-specific discriminative representations of the shared categories data. Comprehensive experiments on several partial domain adaptation benchmarks demonstrate the effectiveness of our proposed model, compared with the state-of-the-art PDA methods.