Learning to Look: Cognitive Attention Alignment with Vision-Language Models

Ryan Yang, Dipkamal Bhusal, Nidhi Rastogi

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 9 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Repositories linked to this paper

• ryanlyang/LearningToLook

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Convolutional Neural Networks (CNNs) frequently "cheat" by exploiting superficial correlations, raising concerns about whether they make predictions for the right reasons. Inspired by cognitive science, which highlights the role of attention in robust human perception, recent methods have sought to guide model attention using concept-based supervision and explanation regularization. However, these techniques depend on labor-intensive, expert-provided annotations, limiting their scalability. We propose a scalable framework that leverages vision-language models to automatically generate semantic attention maps using natural language prompts. By introducing an auxiliary loss that aligns CNN attention with these language-guided maps, our approach promotes more reliable and cognitively plausible decision-making without manual annotation. Experiments on challenging datasets, ColoredMNIST and DecoyMNIST, show that our method achieves stateof-the-art performance on ColorMNIST and remains competitive with annotationheavy baselines on DecoyMNIST, demonstrating improved generalization, reduced shortcut reliance, and model attention that better reflects human intuition. Our code is available at https://github.com/ryanlyang/LearningToLook/.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2509.21247")
get_code_for_paper("2509.21247")
have("2509.21247")

Connect an agent — have() is free.