We study whether visual embedding models capture continuous, ordinal attributes along linear directions, which we term rank axes. We define a model as rankable for an attribute if projecting embeddings onto such an axis preserves the attribute's order. Across 7 popular encoders and 9 datasets with attributes like age, crowd count, head pose, aesthetics, and recency, we find that many embeddings are inherently rankable. Surprisingly, a small number of samples, or even just two extreme examples, often suffice to recover meaningful rank axes, without full-scale supervision. These findings open up new use cases for image ranking in vector databases and motivate further study into the structure and learning of rankable embeddings.

Here are the five models that we used, in increasing order of adversarialrobustness: = 0,0.5,1.0,3.0,5.0. Three ImageNet-trained vision transformer (ViT) models [47] were obtained from pytorch-image-models [48]. Note that the "imagenet1k" suffixinthe model names does not mean the model wasonly trained on ImageNet1K. Observation: A vision transformer (ViT-S) indeed shows higher error consistency with ResNet-50 than with BagNet-9 (see Table 1). Further insights could be gained by testing successively more constrained versions of the samebasemodel.

Clinical dataset labels are rarely certain as annotators disagree and confidence is not uniform across cases. Typical aggregation procedures, such as majority voting, obscure this variability. In simple experiments on medical imaging benchmarks, accounting for the confidence in binary labels significantly impacts model rankings. We therefore argue that machine-learning evaluations should explicitly account for annotation uncertainty using probabilistic metrics that directly operate on distributions. These metrics can be applied independently of the annotations' generating process, whether modeled by simple counting, subjective confidence ratings, or probabilistic response models. They are also computationally lightweight, as closed-form expressions have linear-time implementations once examples are sorted by model score. We thus urge the community to release raw annotations for datasets and to adopt uncertainty-aware evaluation so that performance estimates may better reflect clinical data.

Deep neural networks (DNNs) have demonstrated remarkable success in medical imaging, yet their real-world deployment remains challenging due to spurious correlations, where models can learn non-clinical features instead of meaningful medical patterns. Existing medical imaging datasets are not designed to systematically study this issue, largely due to restrictive licensing and limited supplementary patient data. To address this gap, we introduce SpurBreast, a curated breast MRI dataset that intentionally incorporates spurious correlations to evaluate their impact on model performance. Analyzing over 100 features involving patient, device, and imaging protocol, we identify two dominant spurious signals: magnetic field strength (a global feature influencing the entire image) and image orientation (a local feature affecting spatial alignment). Through controlled dataset splits, we demonstrate that DNNs can exploit these non-clinical signals, achieving high validation accuracy while failing to generalize to unbiased test data. Alongside these two datasets containing spurious correlations, we also provide benchmark datasets without spurious correlations, allowing researchers to systematically investigate clinically relevant and irrelevant features, uncertainty estimation, adversarial robustness, and generalization strategies.

Stimuli are visualized in Figures 7 and 8. Our Python library,"modelvshuman", to test and benchmark models against high-quality human These two models are referred to as ViT -L (14M) and ViT -B (14M) in the paper. Note that the "im-agenet1k" suffix in the model names does not mean the model was only trained on ImageNet1K. We then made two predictions which we test here. While this relationship is not perfect (e.g., the difference is small for silhouette Prior to the experiment, visual acuity was measured with a Snellen chart to ensure normal or corrected to normal vision. Our experiment was a standard perceptual experiment, for which no IRB approval was required.

Adversarial patch attacks threaten the reliability of modern vision models. We present PatchMap, the first spatially exhaustive benchmark of patch placement, built by evaluating over 1.5e8 forward passes on ImageNet validation images. PatchMap reveals systematic hot-spots where small patches (as little as 2% of the image) induce confident misclassifications and large drops in model confidence. To demonstrate its utility, we propose a simple segmentation guided placement heuristic that leverages off the shelf masks to identify vulnerable regions without any gradient queries. Across five architectures-including adversarially trained ResNet50, our method boosts attack success rates by 8 to 13 percentage points compared to random or fixed placements. We publicly release PatchMap and the code implementation. The full PatchMap bench (6.5B predictions, multiple backbones) will be released soon to further accelerate research on location-aware defenses and adaptive attacks.