Evaluating Test-Time Adaptation For Facial Expression Recognition Under Natural Cross-Dataset Distribution Shifts

• URL: http://arxiv.org/abs/2603.19994v1
• Date: Fri, 20 Mar 2026 14:44:25 GMT
• Title: Evaluating Test-Time Adaptation For Facial Expression Recognition Under Natural Cross-Dataset Distribution Shifts
• Abstract summary: We present the first evaluation of TTA methods for FER under natural domain shifts.<n>We show TTA can boost FER performance under natural shifts by up to 11.34%.<n>Our cross-dataset analysis shows that TTA effectiveness is governed by the distributional distance and the severity of the natural shift across domains.
• Score: 31.836571033956684
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep learning models often struggle under natural distribution shifts, a common challenge in real-world deployments. Test-Time Adaptation (TTA) addresses this by adapting models during inference without labeled source data. We present the first evaluation of TTA methods for FER under natural domain shifts, performing cross-dataset experiments with widely used FER datasets. This moves beyond synthetic corruptions to examine real-world shifts caused by differing collection protocols, annotation standards, and demographics. Results show TTA can boost FER performance under natural shifts by up to 11.34\%. Entropy minimization methods such as TENT and SAR perform best when the target distribution is clean. In contrast, prototype adjustment methods like T3A excel under larger distributional distance scenarios. Finally, feature alignment methods such as SHOT deliver the largest gains when the target distribution is noisier than our source. Our cross-dataset analysis shows that TTA effectiveness is governed by the distributional distance and the severity of the natural shift across domains.

Related papers

• Fully Test-time Adaptation for Tabular Data [48.67303250592189]
  We propose the Fully Test-time Adaptation for Tabular data, which enables FTTA methods to robustly optimize the label distribution of predictions.<n>We conduct comprehensive experiments on six benchmark datasets, which are evaluated using three metrics.
  arXiv  Detail & Related papers  (2024-12-14T15:49:53Z)
• Distribution Alignment for Fully Test-Time Adaptation with Dynamic Online Data Streams [19.921480334048756]
  Test-Time Adaptation (TTA) enables adaptation and inference in test data streams with domain shifts from the source. We propose a novel Distribution Alignment loss for TTA. We surpass existing methods in non-i.i.d. scenarios and maintain competitive performance under the ideal i.i.d. assumption.
  arXiv  Detail & Related papers  (2024-07-16T19:33:23Z)
• Everything to the Synthetic: Diffusion-driven Test-time Adaptation via Synthetic-Domain Alignment [81.78901060731269]
  Test-time adaptation (TTA) aims to improve the performance of source-domain pre-trained models on previously unseen, shifted target domains.<n>Traditional TTA methods primarily adapt model weights based on target data streams, making model performance sensitive to the amount and order of target data.<n>The recently proposed diffusion-driven TTA methods mitigate this by adapting model inputs instead of weights, where an unconditional diffusion model, trained on the source domain, transforms target-domain data into a synthetic domain that is expected to approximate the source domain.
  arXiv  Detail & Related papers  (2024-06-06T17:39:09Z)
• Unified Entropy Optimization for Open-Set Test-Time Adaptation [40.111891407629]
  Test-time adaptation (TTA) aims at adapting a model pre-trained on the labeled source domain to the unlabeled target domain. Many state-of-the-art closed-set TTA methods perform poorly when applied to open-set scenarios. We propose a simple but effective framework called unified entropy optimization (UniEnt)
  arXiv  Detail & Related papers  (2024-04-09T07:08:00Z)
• Test-Time Adaptation Induces Stronger Accuracy and Agreement-on-the-Line [65.14099135546594]
  Recent test-time adaptation (TTA) methods drastically strengthen the ACL and AGL trends in models, even in shifts where models showed very weak correlations before. Our results show that by combining TTA with AGL-based estimation methods, we can estimate the OOD performance of models with high precision for a broader set of distribution shifts.
  arXiv  Detail & Related papers  (2023-10-07T23:21:25Z)
• pSTarC: Pseudo Source Guided Target Clustering for Fully Test-Time Adaptation [15.621092104244003]
  Test Time Adaptation (TTA) is a pivotal concept in machine learning, enabling models to perform well in real-world scenarios. We propose a novel approach called pseudo Source guided Target Clustering (pSTarC) addressing the relatively unexplored area of TTA under real-world domain shifts.
  arXiv  Detail & Related papers  (2023-09-02T07:13:47Z)
• Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuning [73.75282761503581]
  We propose DiffTPT, which leverages pre-trained diffusion models to generate diverse and informative new data. Our experiments on test datasets with distribution shifts and unseen categories demonstrate that DiffTPT improves the zero-shot accuracy by an average of 5.13%.
  arXiv  Detail & Related papers  (2023-08-11T09:36:31Z)
• CAFA: Class-Aware Feature Alignment for Test-Time Adaptation [50.26963784271912]
  Test-time adaptation (TTA) aims to address this challenge by adapting a model to unlabeled data at test time. We propose a simple yet effective feature alignment loss, termed as Class-Aware Feature Alignment (CAFA), which simultaneously encourages a model to learn target representations in a class-discriminative manner.
  arXiv  Detail & Related papers  (2022-06-01T03:02:07Z)
• Covariance-aware Feature Alignment with Pre-computed Source Statistics for Test-time Adaptation to Multiple Image Corruptions [11.859913430860335]
  Real-world image recognition systems often face corrupted input images, which cause distribution shifts and degrade the performance of models. Test-time adaptation (TTA) is one of the settings that can address this problem. We propose a novel TTA method named Covariance-Aware Feature alignment (CAFe) to address the distribution gap during testing.
  arXiv  Detail & Related papers  (2022-04-28T02:50:43Z)
• Listen, Adapt, Better WER: Source-free Single-utterance Test-time Adaptation for Automatic Speech Recognition [65.84978547406753]
  Test-time Adaptation aims to adapt the model trained on source domains to yield better predictions for test samples. Single-Utterance Test-time Adaptation (SUTA) is the first TTA study in speech area to our best knowledge.
  arXiv  Detail & Related papers  (2022-03-27T06:38:39Z)
• Leveraging Unlabeled Data to Predict Out-of-Distribution Performance [63.740181251997306]
  Real-world machine learning deployments are characterized by mismatches between the source (training) and target (test) distributions. In this work, we investigate methods for predicting the target domain accuracy using only labeled source data and unlabeled target data. We propose Average Thresholded Confidence (ATC), a practical method that learns a threshold on the model's confidence, predicting accuracy as the fraction of unlabeled examples.
  arXiv  Detail & Related papers  (2022-01-11T23:01:12Z)

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.