MAPS provides 2618 validated 3D meshes and a controllable rendering pipeline to attribute vision model recognition failures to specific scene parameters, finding camera distance and elevation as the dominant failure factors across 20 tested models.
Benchmarking neural network robustness to common corruptions and perturbations.Proceedings of the International Conference on Learning Representations
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
dataset 1
citation-polarity summary
years
2026 7representative citing papers
HypCBM reformulates concept activations as geometric containment in hyperbolic space to produce sparse, hierarchy-aware signals that match Euclidean models trained on 20 times more data.
A human-centered OOD spectrum based on perceptual difficulty shows vision-language models align best with human errors across regimes, with CNNs stronger on near-OOD and ViTs on far-OOD.
Proposes meta-learning attack with priority-aware gradient alignment for sample-wise targeted attacks on TTA that maintain label distribution consistency with no-attack baseline.
Spatial Prediction pretext task learns spatial structure in self-supervised learning by regressing relative position and scale between image views, yielding more structured representations and better generalization.
On vein-recognition benchmarks, mixup-style augmentations win on clean accuracy but hurt calibration and adversarial robustness, while simple geometric transforms usually hurt performance.
StableVLA adds an Information Bottleneck Adapter to VLA models that improves robustness to visual corruptions by 30% on average with under 10M extra parameters and no extra data, even when using a much smaller backbone.
citing papers explorer
-
MAPS: A Synthetic Dataset for Probing Vision Models in a Controlled 3D Scene Space
MAPS provides 2618 validated 3D meshes and a controllable rendering pipeline to attribute vision model recognition failures to specific scene parameters, finding camera distance and elevation as the dominant failure factors across 20 tested models.
-
Hyperbolic Concept Bottleneck Models
HypCBM reformulates concept activations as geometric containment in hyperbolic space to produce sparse, hierarchy-aware signals that match Euclidean models trained on 20 times more data.
-
Do Machines Fail Like Humans? A Human-Centred Out-of-Distribution Spectrum for Mapping Error Alignment
A human-centered OOD spectrum based on perceptual difficulty shows vision-language models align best with human errors across regimes, with CNNs stronger on near-OOD and ViTs on far-OOD.
-
Sample-wise Targeted Adversarial Attacks on Test-time Adaptation
Proposes meta-learning attack with priority-aware gradient alignment for sample-wise targeted attacks on TTA that maintain label distribution consistency with no-attack baseline.
-
Learning to Perceive "Where": Spatial Pretext Tasks for Robust Self-Supervised Learning
Spatial Prediction pretext task learns spatial structure in self-supervised learning by regressing relative position and scale between image views, yielding more structured representations and better generalization.
-
AGVBench: A Reliability-Oriented Benchmark of Data Augmentation for Vein Recognition
On vein-recognition benchmarks, mixup-style augmentations win on clean accuracy but hurt calibration and adversarial robustness, while simple geometric transforms usually hurt performance.
-
StableVLA: Towards Robust Vision-Language-Action Models without Extra Data
StableVLA adds an Information Bottleneck Adapter to VLA models that improves robustness to visual corruptions by 30% on average with under 10M extra parameters and no extra data, even when using a much smaller backbone.