arXiv AI
Complexity Induction: Compositional Generalization via Structured Label Distortion
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Aug 28
Complexity Induction: Compositional Generalization via Structured Training Distortion
The paper introduces "complexity induction," a method that distorts training data in a structured way to promote compositional generalization in a standard CNN without changing its architecture. Using synthetic images of colored geometric shapes, the authors encode classes as flat string labels (e.g., "red‑circle") and deliberately omit certain color‑shape combinations from training. Two distortion techniques—mixed labels (soft target distributions based on Jaccard similarity) and expanded dataset (false samples with incorrect labels)—both enable the model to predict unseen class combinations, with mixed labels leveraging the CNN’s embedding structure and expanded training improving embedding factorization. A control experiment with random false labels shows that the effect relies on the structured nature of the distortion rather than noise alone.
arXiv Machine Learning
Jul 7
Compositional Generalization Requires Linear, Orthogonal Representations in Vision Embedding Models
arXiv:2602. 24264v2 Announce Type: replace-cross Abstract: Compositional generalization, the ability to recognize familiar parts in novel contexts, is a defining property of intelligent systems.
arXiv Machine Learning
Jul 30
The Advantage of Fine-Grained Training
arXiv:2509. 05130v2 Announce Type: replace Abstract: In classification problems, models are trained to predict a class label based on the input data features.
arXiv Machine Learning
Jul 14
Random Label Prediction Heads for Studying Memorization in Deep Neural Networks
arXiv:2607. 11541v1 Announce Type: new Abstract: We introduce a straightforward yet effective method to empirically study memorization in deep neural networks for classification tasks.
arXiv Machine Learning
Sep 23
eXplaining to Learn (eX2L): Regularization Using Contrastive Visual Explanation Pairs for Distribution Shifts
The paper introduces eXplaining to Learn (eX2L), an interpretable framework that regularizes a classifier by penalizing similarity between Grad‑CAM maps of the main label classifier and a confounder classifier. This approach decorrelates confounding features from latent representations during training. On the Spawrious Many‑to‑Many Hard Challenge benchmark, eX2L outperforms the current state‑of‑the‑art by 5.49% in average accuracy and 10.90% in worst‑group accuracy, while also demonstrating functional domain invariance through explicit label‑nuisance decoupling.
arXiv AI
Jun 4
An Empirical Study of Data Scale, Model Complexity, and Input Modalities in Visual Generalization
arXiv:2606. 04409v1 Announce Type: cross Abstract: Modern deep neural networks usually have large parameter scales and nonlinear hierarchical structures, and they have achieved strong performance in computer vision.