PACS

Overview edit

Variants: PACS, PACS-StaQC-py, PACS-SO-DS, PACS-CoNaLa

Associated Benchmarks

This dataset is used in 5 benchmarks:

• Domain Adaptation - Metrics: Accuracy
• Unsupervised Domain Adaptation - Metrics: Average Accuracy
• Domain Generalization - Metrics: Average Accuracy
• Single-Source Domain Generalization - Metrics: Accuracy
• Source-Free Domain Adaptation - Metrics: Average Accuracy

Recent Benchmark Submissions

Research Papers

Recent papers with results on this dataset:

• Shuffle PatchMix Augmentation with Confidence-Margin Weighted Pseudo-Labels for Enhanced Source-Free Domain Adaptation (2025) -
• Effective Dual-Region Augmentation for Reduced Reliance on Large Amounts of Labeled Data (2025) -
• QT-DoG: Quantization-aware Training for Domain Generalization (2024) -
• Crafting Distribution Shifts for Validation and Training in Single Source Domain Generalization (2024) -
• Soft Prompt Generation for Domain Generalization (2024) -
• Rethinking Multi-domain Generalization with A General Learning Objective (2024) -
• Domain Generalization Using Large Pretrained Models with Mixture-of-Adapters (2023) -
• Towards Unified and Effective Domain Generalization (2023) -
• Leveraging Vision-Language Models for Improving Domain Generalization in Image Classification (2023) -
• A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidance (2023) -
• Weight Averaging Improves Knowledge Distillation under Domain Shift (2023) -
• PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization (2023) -
• Adversarial Bayesian Augmentation for Single-Source Domain Generalization (2023) -
• POEM: Polarization of Embeddings for Domain-Invariant Representations (2023) -
• Improved Test-Time Adaptation for Domain Generalization (2023) -
• Meta-causal Learning for Single Domain Generalization (2023) -
• VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue Distribution (2023) -
• Progressive Random Convolutions for Single Domain Generalization (2023) -
• Domain-aware Triplet loss in Domain Generalization (2023) -
• Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalization (2022) -