מפענחים גאומטריים ופרובביליסטיים של תרגומי מרחב

תקציר מקורי באנגליתarXiv:2509.11218v3 Announce Type: replace-cross Abstract: Spatial transformations such as rotation and scale obscure the morphological cues needed for accurate image classification. Careful consideration is required for reliable use in high stakes settings. A model should stay robust under such transformations, expose why a correction was applied, and signal when its input is ambiguous. While geometrically equivariant architectures provide a mathematically grounded solution, they often limit model flexibility through strict symmetry constraints and incur significant computational overhead. Spatial Transformer Networks (STNs) offer a data-driven, flexible alternative for learning pseudo-equivariances to affine transformations. However, STNs have historically been restricted to convolutional