Zero-Shot Test-Time Canonicalization using Out-of-Distribution Scoring

• URL: http://arxiv.org/abs/2606.24178v1
• Date: Tue, 23 Jun 2026 06:00:33 GMT
• Title: Zero-Shot Test-Time Canonicalization using Out-of-Distribution Scoring
• Abstract summary: Pretrained vision models often misclassify inputs that are rotated, scaled, or sheared.<n>Test-time canonicalization instead leaves the input untouched.<n>We develop a gated mechanism that transforms an input only when its OOD score indicates this is needed.
• Score: 4.454031533784339
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Pretrained vision models often misclassify inputs that are rotated, scaled, or sheared, even though these affine transformations leave the object class unchanged. Robustness is usually restored either by building equivariance into the architecture or by retraining with augmentation, both of which require changing or retraining the model. Test-time canonicalization instead leaves the classifier untouched. It undoes the transformation of each input, mapping it to a canonical form near the training distribution before classification. Existing canonicalizers, however, rely on a narrow set of logit-based energy scores and bespoke search procedures, leaving the design space of scoring functions and optimizers unexplored. We reframe canonicalization as out-of-distribution (OOD) detection, which lets any OOD score serve as the energy minimized over transformations. Across benchmarks ranging from handwritten characters and sketches to natural images and 3D point clouds, we systematically evaluate around twenty OOD scores and nine search algorithms, finding that distance-based scores paired with random search and local refinement perform best overall. Because canonicalizing an already-aligned input can hurt accuracy, we add a gated mechanism that transforms an input only when its OOD score indicates this is needed, preserving most in-distribution accuracy while retaining the robustness gains on transformed inputs. Code is available at github.com/johschm/its.

Related papers

• Robust Canonicalization through Bootstrapped Data Re-Alignment [5.437226012505534]
  Fine-grained visual classification tasks, such as insect and bird identification, demand sensitivity to subtle visual cues.<n>We propose a bootstrapping algorithm that iteratively re-aligns training samples by reducing variance.<n>We show that our method consistently outperforms equivariant, and canonicalization baselines while performing on par with augmentation.
  arXiv  Detail & Related papers  (2025-10-09T13:05:20Z)
• Network Inversion for Uncertainty-Aware Out-of-Distribution Detection [2.6733991338938026]
  Out-of-distribution (OOD) detection and uncertainty estimation are critical components for building safe machine learning systems.<n>We propose a novel framework that combines network inversion with classifier training to address both OOD detection and uncertainty estimation.<n>Our approach is scalable, interpretable, and does not require access to external OOD datasets or post-hoc calibration techniques.
  arXiv  Detail & Related papers  (2025-05-29T13:53:52Z)
• PseudoNeg-MAE: Self-Supervised Point Cloud Learning using Conditional Pseudo-Negative Embeddings [55.55445978692678]
  PseudoNeg-MAE enhances global feature representation of point cloud masked autoencoders by making them both discriminative and sensitive to transformations.<n>We propose a novel loss that explicitly penalizes invariant collapse, enabling the network to capture richer transformation cues while preserving discriminative representations.
  arXiv  Detail & Related papers  (2024-09-24T07:57:21Z)
• Rethinking Classifier Re-Training in Long-Tailed Recognition: A Simple Logits Retargeting Approach [102.0769560460338]
  We develop a simple logits approach (LORT) without the requirement of prior knowledge of the number of samples per class. Our method achieves state-of-the-art performance on various imbalanced datasets, including CIFAR100-LT, ImageNet-LT, and iNaturalist 2018.
  arXiv  Detail & Related papers  (2024-03-01T03:27:08Z)
• Robust Outlier Rejection for 3D Registration with Variational Bayes [70.98659381852787]
  We develop a novel variational non-local network-based outlier rejection framework for robust alignment. We propose a voting-based inlier searching strategy to cluster the high-quality hypothetical inliers for transformation estimation.
  arXiv  Detail & Related papers  (2023-04-04T03:48:56Z)
• READ: Aggregating Reconstruction Error into Out-of-distribution Detection [5.069442437365223]
  Deep neural networks are known to be overconfident for abnormal data. We propose READ (Reconstruction Error Aggregated Detector) to unify inconsistencies from classifier and autoencoder. Our method reduces the average FPR@95TPR by up to 9.8% compared with previous state-of-the-art OOD detection algorithms.
  arXiv  Detail & Related papers  (2022-06-15T11:30:41Z)
• Locally Aware Piecewise Transformation Fields for 3D Human Mesh Registration [67.69257782645789]
  We propose piecewise transformation fields that learn 3D translation vectors to map any query point in posed space to its correspond position in rest-pose space. We show that fitting parametric models with poses by our network results in much better registration quality, especially for extreme poses.
  arXiv  Detail & Related papers  (2021-04-16T15:16:09Z)
• Pose Recognition with Cascade Transformers [31.7059023190426]
  We present a regression-based pose recognition method using Transformers. Heatmap-based and regression-based methods achieve higher accuracy but are subject to various designs. In the experiments, we report competitive results for pose recognition when compared with the competing regression-based methods.
  arXiv  Detail & Related papers  (2021-04-14T17:00:22Z)
• Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection [85.53263670166304]
  One-stage detector basically formulates object detection as dense classification and localization. Recent trend for one-stage detectors is to introduce an individual prediction branch to estimate the quality of localization. This paper delves into the representations of the above three fundamental elements: quality estimation, classification and localization.
  arXiv  Detail & Related papers  (2020-06-08T07:24:33Z)
• Pre-training Is (Almost) All You Need: An Application to Commonsense Reasoning [61.32992639292889]
  Fine-tuning of pre-trained transformer models has become the standard approach for solving common NLP tasks. We introduce a new scoring method that casts a plausibility ranking task in a full-text format. We show that our method provides a much more stable training phase across random restarts.
  arXiv  Detail & Related papers  (2020-04-29T10:54:40Z)

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.