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:2608.21464v1 Announce Type: cross Abstract: We demonstrate that structured distortion of training data - which we term complexity induction - can induce compositional generalization in a standa...
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: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.
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:2505.09716v4 Announce Type: replace Abstract: Out-of-distribution (OOD) generalisation through composition requires a system to discover invariant properties from input-output associations and...
arXiv:2605. 00273v2 Announce Type: replace-cross Abstract: Text-to-image diffusion models achieve impressive visual fidelity, yet they remain unreliable in multi-object generation.
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:2411. 05698v3 Announce Type: replace-cross Abstract: Convolutional Neural Networks (CNNs) have shown remarkable performance in image classification.
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.
Over the past decade, deep neural networks (DNNs) have achieved remarkable success on complex machine-learning tasks, yet the theoretical foundations of their performance remain incomplete. From a statistical viewpoint, a natural question is: can DNNs attain feature-learning and prediction consistency comparable to that of classical models?
arXiv:2510.03075v4 Announce Type: replace-cross Abstract: Compositional generalization, the ability to generate novel combinations of known concepts, is a key ingredient for visual generative models....
The paper presents a tight generalization bound for deterministic neural networks that relies on the quality of their last hidden layer representations rather than traditional parameter-space metrics. By using a parameter‑free k‑nearest‑neighbor classifier to assess representation quality, the bound decomposes into three measurable components—local class geometry, decoder‑network agreement, and training stability—providing both a non‑vacuous certificate and a diagnostic tool for understanding generalization. Experiments show the bound achieves an 8.0‑percentage‑point gap to test error on CIFAR‑10 with ResNet‑18, yields the first non‑vacuous certificates on CIFAR‑100, and certifies 1.4 % on CIFAR‑10 and 23.1 % on 1,000‑class ImageNet using frozen DINOv2 representations.