Visual analogy: Deep learning versus compositional models
Is analogical reasoning a task that must be learned to solve from scratch by applying deep learning models to massive numbers of reasoning problems? Or are analogies solved by computing similarities between structured representations of analogs? We address this question by comparing human performance on visual analogies created using images of familiar three-dimensional objects (cars and their subregions) with the performance of alternative computational models. Human reasoners achieved above-chance accuracy for all problem types, but made more errors in several conditions (e.g., when relevant subregions were occluded). We compared human performance to that of two recent deep learning models (Siamese Network and Relation Network) directly trained to solve these analogy problems, as well as to that of a compositional model that assesses relational similarity between part-based representations. The compositional model based on part representations, but not the deep learning models, generated qualitative performance similar to that of human reasoners.
Code (0)
등록된 구현이 없습니다.
Tasks
Deep LearningRelation NetworkVisual AnalogiesSimilar Papers 제목 키워드 기반
Compositional Transduction with Latent Analogies for Offline Goal-Conditioned Reinforcement Learning
Compositional generalization is essential for reaching unseen goals under novel contextual variations in offline goal-conditioned reinforcement learning (GCRL), where a generalist goal-reaching agent must be learned from…
Reinforcement LearningWhat Analogies Reveal about Word Vectors and their Compositionality
Analogy completion via vector arithmetic has become a common means of demonstrating the compositionality of word embeddings. Previous work have shown that this strategy works more reliably for certain types of analogical…
Semantic Textual SimilarityWord EmbeddingsIm-Promptu: In-Context Composition from Image Prompts
Large language models are few-shot learners that can solve diverse tasks from a handful of demonstrations. This implicit understanding of tasks suggests that the attention mechanisms over word tokens may play a role in a…
Image GenerationMeta-LearningViRel: Unsupervised Visual Relations Discovery with Graph-level Analogy
Visual relations form the basis of understanding our compositional world, as relationships between visual objects capture key information in a scene. It is then advantageous to learn relations automatically from the data…
RelationRelation ClassificationIs analogy enough to draw novel adjective-noun inferences?
Recent work (Ross et al., 2025, 2024) has argued that the ability of humans and LLMs respectively to generalize to novel adjective-noun combinations shows that they each have access to a compositional mechanism to determ…