Test-Time Modification: Inverse Domain Transformation for Robust Perception

• URL: http://arxiv.org/abs/2512.13454v1
• Date: Mon, 15 Dec 2025 15:51:30 GMT
• Title: Test-Time Modification: Inverse Domain Transformation for Robust Perception
• Authors: Arpit Jadon, Joshua Niemeijer, Yuki M. Asano,
• Abstract summary: Generative foundation models contain broad visual knowledge and can produce diverse image variations.<n>We propose an alternative: using diffusion models at test time to map target images back to the source distribution where the downstream model was trained.<n>This approach requires only a source domain description, preserves the task model, and eliminates large-scale synthetic data generation.
• Score: 29.29601766599788
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generative foundation models contain broad visual knowledge and can produce diverse image variations, making them particularly promising for advancing domain generalization tasks. While they can be used for training data augmentation, synthesizing comprehensive target-domain variations remains slow, expensive, and incomplete. We propose an alternative: using diffusion models at test time to map target images back to the source distribution where the downstream model was trained. This approach requires only a source domain description, preserves the task model, and eliminates large-scale synthetic data generation. We demonstrate consistent improvements across segmentation, detection, and classification tasks under challenging environmental shifts in real-to-real domain generalization scenarios with unknown target distributions. Our analysis spans multiple generative and downstream models, including an ensemble variant for enhanced robustness. The method achieves substantial relative gains: 137% on BDD100K-Night, 68% on ImageNet-R, and 62% on DarkZurich.

Related papers

• Prompt-Free Conditional Diffusion for Multi-object Image Augmentation [45.92182911052815]
  We propose a prompt-free conditional diffusion framework for multi-object image augmentation.<n>Specifically, we introduce a local-global semantic fusion strategy to extract semantics from images to replace text.<n>We also design a reward model based counting loss to assist the traditional reconstruction loss for model training.
  arXiv  Detail & Related papers  (2025-07-08T16:27:48Z)
• Anti-Forgetting Adaptation for Unsupervised Person Re-identification [87.0061997256388]
  We propose a Dual-level Joint Adaptation and Anti-forgetting framework.<n>It incrementally adapts a model to new domains without forgetting source domain and each adapted target domain.<n>Our proposed method significantly improves the anti-forgetting, generalization and backward-compatible ability of an unsupervised person ReID model.
  arXiv  Detail & Related papers  (2024-11-22T03:05:06Z)
• Open-Set Deepfake Detection: A Parameter-Efficient Adaptation Method with Forgery Style Mixture [81.93945602120453]
  We introduce an approach that is both general and parameter-efficient for face forgery detection.<n>We design a forgery-style mixture formulation that augments the diversity of forgery source domains.<n>We show that the designed model achieves state-of-the-art generalizability with significantly reduced trainable parameters.
  arXiv  Detail & Related papers  (2024-08-23T01:53:36Z)
• Domain Generalized Recaptured Screen Image Identification Using SWIN Transformer [1.024113475677323]
  We propose a cascaded data augmentation and SWIN transformer domain generalization framework (DAST-DG) A feature generator is trained to make authentic images from various domains indistinguishable. This process is then applied to recaptured images, creating a dual adversarial learning setup.
  arXiv  Detail & Related papers  (2024-07-24T11:22:02Z)
• FDS: Feedback-guided Domain Synthesis with Multi-Source Conditional Diffusion Models for Domain Generalization [19.0284321951354]
  Domain Generalization techniques aim to enhance model robustness by simulating novel data distributions during training.<n>We propose FDS, Feedback-guided Domain Synthesis, a novel strategy that employs diffusion models to synthesize novel, pseudo-domains.<n>Our evaluations demonstrate that this methodology sets new benchmarks in domain generalization performance across a range of challenging datasets.
  arXiv  Detail & Related papers  (2024-07-04T02:45:29Z)
• Reliable Source Approximation: Source-Free Unsupervised Domain Adaptation for Vestibular Schwannoma MRI Segmentation [38.529892690603006]
  Source-Free Unsupervised Domain Adaptation (SFUDA) has recently become a focus in the medical image domain adaptation. We propose Reliable Source Approximation (RSA), which can generate source-like and structure-preserved images from the target domain. RSA consistently improves domain adaptation performance over other state-of-the-art SFUDA methods.
  arXiv  Detail & Related papers  (2024-05-25T07:29:09Z)
• Improving Diversity in Zero-Shot GAN Adaptation with Semantic Variations [61.132408427908175]
  zero-shot GAN adaptation aims to reuse well-trained generators to synthesize images of an unseen target domain. With only a single representative text feature instead of real images, the synthesized images gradually lose diversity. We propose a novel method to find semantic variations of the target text in the CLIP space.
  arXiv  Detail & Related papers  (2023-08-21T08:12:28Z)
• Consistency Regularization for Generalizable Source-free Domain Adaptation [62.654883736925456]
  Source-free domain adaptation (SFDA) aims to adapt a well-trained source model to an unlabelled target domain without accessing the source dataset. Existing SFDA methods ONLY assess their adapted models on the target training set, neglecting the data from unseen but identically distributed testing sets. We propose a consistency regularization framework to develop a more generalizable SFDA method.
  arXiv  Detail & Related papers  (2023-08-03T07:45:53Z)
• Target-Aware Generative Augmentations for Single-Shot Adaptation [21.840653627684855]
  We propose a new approach to adapting models from a source domain to a target domain. SiSTA fine-tunes a generative model from the source domain using a single-shot target, and then employs novel sampling strategies for curating synthetic target data. We find that SiSTA produces significantly improved generalization over existing baselines in face detection and multi-class object recognition.
  arXiv  Detail & Related papers  (2023-05-22T17:46:26Z)
• Few-shot Image Generation with Elastic Weight Consolidation [53.556446614013105]
  Few-shot image generation seeks to generate more data of a given domain, with only few available training examples. We adapt a pretrained model, without introducing any additional parameters, to the few examples of the target domain. We demonstrate the effectiveness of our algorithm by generating high-quality results of different target domains.
  arXiv  Detail & Related papers  (2020-12-04T18:57:13Z)
• Diversity inducing Information Bottleneck in Model Ensembles [73.80615604822435]
  In this paper, we target the problem of generating effective ensembles of neural networks by encouraging diversity in prediction. We explicitly optimize a diversity inducing adversarial loss for learning latent variables and thereby obtain diversity in the output predictions necessary for modeling multi-modal data. Compared to the most competitive baselines, we show significant improvements in classification accuracy, under a shift in the data distribution.
  arXiv  Detail & Related papers  (2020-03-10T03:10:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.