# Boosting Novel Category Discovery Over Domains with Soft Contrastive Learning and All-in-One Classifier

arXiv: https://arxiv.org/abs/2211.11262 · HTML: https://mlsanity.com/paper/2211.11262/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 46 references that are in the map.
- First posted on arXiv 21 Nov 2022.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [Self-supervised Learning: Generative or Contrastive](https://mlsanity.com/paper/2006.08218/) (2020)
- [VisDA: The Visual Domain Adaptation Challenge](https://mlsanity.com/paper/1710.06924/) (2017)
- [Universal Domain Adaptation through Self Supervision](https://mlsanity.com/paper/2002.07953/) (2020)
- [Open Set Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1804.10427/) (2018)
- [Partial Adversarial Domain Adaptation](https://mlsanity.com/paper/1808.04205/) (2018)
- [OVANet: One-vs-All Network for Universal Domain Adaptation](https://mlsanity.com/paper/2104.03344/) (2021)
- [On the Effectiveness of Image Rotation for Open Set Domain Adaptation](https://mlsanity.com/paper/2007.12360/) (2020)
- [Unsupervised Feature Learning by Cross-Level Instance-Group Discrimination](https://mlsanity.com/paper/2008.03813/) (2020)
- [Trustworthy Long-Tailed Classification](https://mlsanity.com/paper/2111.09030/) (2021)
- [Robust Contrastive Learning against Noisy Views](https://mlsanity.com/paper/2201.04309/) (2022)
- [Subsidiary Prototype Alignment for Universal Domain Adaptation](https://mlsanity.com/paper/2210.15909/) (2022)
- [DLME: Deep Local-flatness Manifold Embedding](https://mlsanity.com/paper/2207.03160/) (2022)
- [UDRN: Unified Dimensional Reduction Neural Network for Feature Selection and Feature Projection](https://mlsanity.com/paper/2207.03809/) (2022)
- [Exploiting Inter-Sample Affinity for Knowability-Aware Universal Domain Adaptation](https://mlsanity.com/paper/2207.09280/) (2022)
- [Towards Adaptive Unknown Authentication for Universal Domain Adaptation by Classifier Paradox](https://mlsanity.com/paper/2207.04494/) (2022)

## Built on by (most cited first, 18 of 18)

- [Continual-MAE: Adaptive Distribution Masked Autoencoders for Continual Test-Time Adaptation](https://mlsanity.com/paper/2312.12480/) (2023)
- [Unified Language-driven Zero-shot Domain Adaptation](https://mlsanity.com/paper/2404.07155/) (2024)
- [HiLo: A Learning Framework for Generalized Category Discovery Robust to Domain Shifts](https://mlsanity.com/paper/2408.04591/) (2024)
- [Open-Set Domain Adaptation with Visual-Language Foundation Models](https://mlsanity.com/paper/2307.16204/) (2023)
- [DiffAug: Enhance Unsupervised Contrastive Learning with Domain-Knowledge-Free Diffusion-based Data Augmentation](https://mlsanity.com/paper/2309.07909/) (2023)
- [Cross-domain Open-world Discovery](https://mlsanity.com/paper/2406.11422/) (2024)
- [Category Discovery: An Open-World Perspective](https://mlsanity.com/paper/2509.22542/) (2025)
- [Open-World Deepfake Attribution via Confidence-Aware Asymmetric Learning](https://mlsanity.com/paper/2512.12667/) (2025)
- [Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation](https://mlsanity.com/paper/2506.19022/) (2025)
- [A Medical Multimodal Diagnostic Framework Integrating Vision-Language Models and Logic Tree Reasoning](https://mlsanity.com/paper/2512.21583/) (2025)
- [Deep Multi-Manifold Transformation Based Multivariate Time Series Fault Detection](https://mlsanity.com/paper/2405.16258/) (2024)
- [PCaM: A Progressive Focus Attention-Based Information Fusion Method for Improving Vision Transformer Domain Adaptation](https://mlsanity.com/paper/2506.17232/) (2025)
- [HDTree: Generative Modeling of Cellular Hierarchies for Robust Lineage Inference](https://mlsanity.com/paper/2506.23287/) (2025)
- [Learning through Creation: A Hash-Free Framework for On-the-Fly Category Discovery](https://mlsanity.com/paper/2603.13858/) (2026)
- [Revisiting Cross-Attention Mechanisms: Leveraging Beneficial Noise for Domain-Adaptive Learning](https://mlsanity.com/paper/2603.17474/) (2026)
- [PACO: Proxy-Task Alignment and Online Calibration for On-the-Fly Category Discovery](https://mlsanity.com/paper/2604.11484/) (2026)
- [The Devil Is in Gradient Entanglement: Energy-Aware Gradient Coordinator for Robust Generalized Category Discovery](https://mlsanity.com/paper/2604.14176/) (2026)
- [Virtual Category-Guided Continual Generalized Category Discovery](https://mlsanity.com/paper/2607.04984/) (2026)

## Abstract (arXiv)

Unsupervised domain adaptation (UDA) has proven to be highly effective in transferring knowledge from a label-rich source domain to a label-scarce target domain. However, the presence of additional novel categories in the target domain has led to the development of open-set domain adaptation (ODA) and universal domain adaptation (UNDA). Existing ODA and UNDA methods treat all novel categories as a single, unified unknown class and attempt to detect it during training. However, we found that domain variance can lead to more significant view-noise in unsupervised data augmentation, which affects the effectiveness of contrastive learning (CL) and causes the model to be overconfident in novel category discovery. To address these issues, a framework named Soft-contrastive All-in-one Network (SAN) is proposed for ODA and UNDA tasks. SAN includes a novel data-augmentation-based soft contrastive learning (SCL) loss to fine-tune the backbone for feature transfer and a more human-intuitive classifier to improve new class discovery capability. The SCL loss weakens the adverse effects of the data augmentation view-noise problem which is amplified in domain transfer tasks. The All-in-One (AIO) classifier overcomes the overconfidence problem of current mainstream closed-set and open-set classifiers. Visualization and ablation experiments demonstrate the effectiveness of the proposed innovations. Furthermore, extensive experiment results on ODA and UNDA show that SAN outperforms existing state-of-the-art methods.