From Spurious to Causal: Low-rank Orthogonal Subspace Intervention for Generalizable Face Forgery Detection

• URL: http://arxiv.org/abs/2601.11915v1
• Date: Sat, 17 Jan 2026 05:32:55 GMT
• Title: From Spurious to Causal: Low-rank Orthogonal Subspace Intervention for Generalizable Face Forgery Detection
• Abstract summary: forgery-irrelevant information are collectively termed spurious correlations factors.<n>We propose an intervention paradigm for representation space. Instead of tracking and blocking various instance-level spurious correlation one by one, we uniformly model them as a low-rank subspace.<n>Our method achieves state-of-the-art performance across several benchmarks, demonstrating excellent robustness and generalization.
• Score: 23.325152252327978
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The generalization problem remains a critical challenge in face forgery detection. Some researches have discovered that ``a backdoor path" in the representations from forgery-irrelevant information to labels induces biased learning, thereby hindering the generalization. In this paper, these forgery-irrelevant information are collectively termed spurious correlations factors. Previous methods predominantly focused on identifying concrete, specific spurious correlation and designing corresponding solutions to address them. However, spurious correlations arise from unobservable confounding factors, making it impractical to identify and address each one individually. To address this, we propose an intervention paradigm for representation space. Instead of tracking and blocking various instance-level spurious correlation one by one, we uniformly model them as a low-rank subspace and intervene in them. Specifically, we decompose spurious correlation features into a low-rank subspace via orthogonal low-rank projection, subsequently removing this subspace from the original representation and training its orthogonal complement to capture forgery-related features. This low-rank projection removal effectively eliminates spurious correlation factors, ensuring that classification decision is based on authentic forgery cues. With only 0.43M trainable parameters, our method achieves state-of-the-art performance across several benchmarks, demonstrating excellent robustness and generalization.

Related papers

• Dual-Branch Cross-Projection Debiasing through Diffusion-based Disentanglement [66.67463557274358]
  Foundation models trained on biased datasets often rely on spurious correlations between target labels and non-causal attributes.<n>We introduce Confidence-guided Concept Mining (CBCM) to identify reliable spurious attributes without attribute annotations.<n>We propose Dual-branch Cross-projection Debiasing (DCD), a prompt-tuning framework that separates target and spurious representations into two branches.
  arXiv  Detail & Related papers  (2026-06-23T05:28:47Z)
• Deconfounding Scores and Representation Learning for Causal Effect Estimation with Weak Overlap [75.41420283374737]
  Overlap is a key condition for causal treatment effect estimation.<n>We propose a class of feature representations called deconfounding scores.<n>We show that prognostic scores are overlap-optimal within this class.
  arXiv  Detail & Related papers  (2026-04-01T12:19:42Z)
• Generative Classifiers Avoid Shortcut Solutions [84.23247217037134]
  Discriminative approaches to classification often learn shortcuts that hold in-distribution but fail under minor distribution shift.<n>We show that generative classifiers can avoid this issue by modeling all features, both core and spurious, instead of mainly spurious ones.<n>We find that diffusion-based and autorerimigressive generative classifiers achieve state-of-the-art performance on five standard image and text distribution shift benchmarks.
  arXiv  Detail & Related papers  (2025-12-31T18:31:46Z)
• Let Samples Speak: Mitigating Spurious Correlation by Exploiting the Clusterness of Samples [11.727747752958436]
  Deep learning models often learn features that spuriously correlate with the class label during training but are irrelevant to the prediction task.<n>Existing methods typically address this issue by annotating potential spurious attributes, or filtering spurious features based on some empirical assumptions.<n>We propose a data-oriented approach to mitigate the spurious correlation in deep learning models.
  arXiv  Detail & Related papers  (2025-12-28T10:54:51Z)
• Accept-Reject Lasso [5.465098504510676]
  The Lasso method is known to exhibit instability in the presence of highly correlated features.<n>We introduce the Accept-Reject Lasso, a novel approach that resolves this dilemma.<n>ARL operationalizes an Accept-Reject framework through a fine-grained analysis of feature selection across data subsets.
  arXiv  Detail & Related papers  (2025-08-06T17:13:27Z)
• A Sparsity Principle for Partially Observable Causal Representation Learning [28.25303444099773]
  Causal representation learning aims at identifying high-level causal variables from perceptual data. We focus on learning from unpaired observations from a dataset with an instance-dependent partial observability pattern. We propose two methods for estimating the underlying causal variables by enforcing sparsity in the inferred representation.
  arXiv  Detail & Related papers  (2024-03-13T08:40:49Z)
• Causal Feature Selection via Transfer Entropy [59.999594949050596]
  Causal discovery aims to identify causal relationships between features with observational data. We introduce a new causal feature selection approach that relies on the forward and backward feature selection procedures. We provide theoretical guarantees on the regression and classification errors for both the exact and the finite-sample cases.
  arXiv  Detail & Related papers  (2023-10-17T08:04:45Z)
• FACTS: First Amplify Correlations and Then Slice to Discover Bias [17.244153084361102]
  Computer vision datasets frequently contain spurious correlations between task-relevant labels and (easy to learn) latent task-irrelevant attributes. Models trained on such datasets learn "shortcuts" and underperform on bias-conflicting slices of data where the correlation does not hold. We propose First Amplify Correlations and Then Slice to Discover Bias to inform downstream bias mitigation strategies.
  arXiv  Detail & Related papers  (2023-09-29T17:41:26Z)
• Nonparametric Identifiability of Causal Representations from Unknown Interventions [63.1354734978244]
  We study causal representation learning, the task of inferring latent causal variables and their causal relations from mixtures of the variables. Our goal is to identify both the ground truth latents and their causal graph up to a set of ambiguities which we show to be irresolvable from interventional data.
  arXiv  Detail & Related papers  (2023-06-01T10:51:58Z)
• Disentanglement of Correlated Factors via Hausdorff Factorized Support [53.23740352226391]
  We propose a relaxed disentanglement criterion - the Hausdorff Factorized Support (HFS) criterion - that encourages a factorized support, rather than a factorial distribution. We show that the use of HFS consistently facilitates disentanglement and recovery of ground-truth factors across a variety of correlation settings and benchmarks.
  arXiv  Detail & Related papers  (2022-10-13T20:46:42Z)
• Decorrelate Irrelevant, Purify Relevant: Overcome Textual Spurious Correlations from a Feature Perspective [47.10907370311025]
  Natural language understanding (NLU) models tend to rely on spurious correlations (emphi.e., dataset bias) to achieve high performance on in-distribution datasets but poor performance on out-of-distribution ones. Most of the existing debiasing methods often identify and weaken these samples with biased features. Down-weighting these samples obstructs the model in learning from the non-biased parts of these samples. We propose to eliminate spurious correlations in a fine-grained manner from a feature space perspective.
  arXiv  Detail & Related papers  (2022-02-16T13:23:14Z)
• Learning Causal Models Online [103.87959747047158]
  Predictive models can rely on spurious correlations in the data for making predictions. One solution for achieving strong generalization is to incorporate causal structures in the models. We propose an online algorithm that continually detects and removes spurious features.
  arXiv  Detail & Related papers  (2020-06-12T20:49:20Z)

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.