# Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation arXiv: https://arxiv.org/abs/2411.16064 ยท HTML: https://mlsanity.com/paper/2411.16064/ ## Key facts - Cited by 10 papers in the map (data through 14 Oct 2026). - Builds on 37 of its 67 references that are in the map. - First posted on arXiv 25 Nov 2024. ## Builds on (most cited first, 30 of 37) - [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020) - [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014) - [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020) - [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016) - [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017) - [Large Scale Incremental Learning](https://mlsanity.com/paper/1905.13260/) (2019) - [Efficient Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2204.02610/) (2022) - [Self-Sustaining Representation Expansion for Non-Exemplar Class-Incremental Learning](https://mlsanity.com/paper/2203.06359/) (2022) - [Gait Recognition in the Wild with Dense 3D Representations and A Benchmark](https://mlsanity.com/paper/2204.02569/) (2022) - [Class-Incremental Learning by Knowledge Distillation with Adaptive Feature Consolidation](https://mlsanity.com/paper/2204.00895/) (2022) - [Learning to Transfer Examples for Partial Domain Adaptation](https://mlsanity.com/paper/1903.12230/) (2019) - [Partial Transfer Learning with Selective Adversarial Networks](https://mlsanity.com/paper/1707.07901/) (2017) - [Guiding Pseudo-labels with Uncertainty Estimation for Source-free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2303.03770/) (2023) - [A Prototype-Oriented Framework for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2110.12024/) (2021) - [Source-Free Domain Adaptation with Frozen Multimodal Foundation Model](https://mlsanity.com/paper/2311.16510/) (2023) - [C-SFDA: A Curriculum Learning Aided Self-Training Framework for Efficient Source Free Domain Adaptation](https://mlsanity.com/paper/2303.17132/) (2023) - [Class-Incremental Learning with CLIP: Adaptive Representation Adjustment and Parameter Fusion](https://mlsanity.com/paper/2407.14143/) (2024) - [BMD: A General Class-balanced Multicentric Dynamic Prototype Strategy for Source-free Domain Adaptation](https://mlsanity.com/paper/2204.02811/) (2022) - [Gradient Reweighting: Towards Imbalanced Class-Incremental Learning](https://mlsanity.com/paper/2402.18528/) (2024) - [Class-Incremental Domain Adaptation](https://mlsanity.com/paper/2008.01389/) (2020) - [Prototype-Guided Continual Adaptation for Class-Incremental Unsupervised Domain Adaptation](https://mlsanity.com/paper/2207.10856/) (2022) - [Upcycling Models under Domain and Category Shift](https://mlsanity.com/paper/2303.07110/) (2023) - [DARE-GRAM : Unsupervised Domain Adaptation Regression by Aligning Inverse Gram Matrices](https://mlsanity.com/paper/2303.13325/) (2023) - [LEAD: Learning Decomposition for Source-free Universal Domain Adaptation](https://mlsanity.com/paper/2403.03421/) (2024) - [UMAD: Universal Model Adaptation under Domain and Category Shift](https://mlsanity.com/paper/2112.08553/) (2021) - [DiffClass: Diffusion-Based Class Incremental Learning](https://mlsanity.com/paper/2403.05016/) (2024) - [Entity-enhanced Adaptive Reconstruction Network for Weakly Supervised Referring Expression Grounding](https://mlsanity.com/paper/2207.08386/) (2022) - [OVOR: OnePrompt with Virtual Outlier Regularization for Rehearsal-Free Class-Incremental Learning](https://mlsanity.com/paper/2402.04129/) (2024) - [Class Incremental Learning via Likelihood Ratio Based Task Prediction](https://mlsanity.com/paper/2309.15048/) (2023) - [Unsupervised Video Domain Adaptation with Masked Pre-Training and Collaborative Self-Training](https://mlsanity.com/paper/2312.02914/) (2023) ## Built on by (most cited first, 10 of 10) - [Prosody-Enhanced Acoustic Pre-training and Acoustic-Disentangled Prosody Adapting for Movie Dubbing](https://mlsanity.com/paper/2503.12042/) (2025) - [Investigating Domain Gaps for Indoor 3D Object Detection](https://mlsanity.com/paper/2508.17439/) (2025) - [Dance Across Shifts: Forward-Facilitation Continual Test-Time Adaptation through Dynamic Style Bridging](https://mlsanity.com/paper/2605.18608/) (2026) - [Progressive Homeostatic and Plastic Prompt Tuning for Audio-Visual Multi-Task Incremental Learning](https://mlsanity.com/paper/2507.21588/) (2025) - [Leveraging Unlabeled Data from Unknown Sources via Dual-Path Guidance for Deepfake Face Detection](https://mlsanity.com/paper/2508.09022/) (2025) - [Cross-Domain Attribute Alignment with CLIP: A Rehearsal-Free Approach for Class-Incremental Unsupervised Domain Adaptation](https://mlsanity.com/paper/2509.11264/) (2025) - [SloMo-Fast: Slow-Momentum and Fast-Adaptive Teachers for Source-Free Continual Test-Time Adaptation](https://mlsanity.com/paper/2511.18468/) (2025) - [Unsupervised Collaborative Domain Adaptation for Driving Scene Parsing](https://mlsanity.com/paper/2606.01818/) (2026) - [LFM: Leveraging Foundation Models for Source-Free Universal Domain Adaptation](https://mlsanity.com/paper/2607.17653/) (2026) - [SPACE: Semantic Projection and Alignment of CLIP Embeddings for Domain Adaptation](https://mlsanity.com/paper/2609.23248/) (2026) ## Abstract (arXiv) This paper explores the Class-Incremental Source-Free Unsupervised Domain Adaptation (CI-SFUDA) problem, where the unlabeled target data come incrementally without access to labeled source instances. This problem poses two challenges, the interference of similar source-class knowledge in target-class representation learning and the shocks of new target knowledge to old ones. To address them, we propose the Multi-Granularity Class Prototype Topology Distillation (GROTO) algorithm, which effectively transfers the source knowledge to the class-incremental target domain. Concretely, we design the multi-granularity class prototype self-organization module and the prototype topology distillation module. First, we mine the positive classes by modeling accumulation distributions. Next, we introduce multi-granularity class prototypes to generate reliable pseudo-labels, and exploit them to promote the positive-class target feature self-organization. Second, the positive-class prototypes are leveraged to construct the topological structures of source and target feature spaces. Then, we perform the topology distillation to continually mitigate the shocks of new target knowledge to old ones. Extensive experiments demonstrate that our proposed method achieves state-of-the-art performance on three public datasets. Code is available at https://github.com/dengpeihua/GROTO.