OpenAlex ·
Reachability Is Not Generalization: Understanding Verb--Noun Decomposition in Assembly Action Recognition
- Published
- Source
- OpenAlex
- Published in
- arXiv (Cornell University)
- DOI
- 10.48550/arxiv.2610.00064
- Original
- Read it at the publisher
- Topics
Abstract
Assembly actions are compositional: they combine a manipulation with a part or tool. In deployment, systems routinely encounter novel combinations of familiar components, yet an atomic action classifier assigns every unseen combination exactly zero probability by construction. The prevailing solution is verb--noun decomposition, which predicts components separately and recombines them to reach unseen actions. While widely adopted, how decomposition generalizes under compositional shift remains poorly understood. We present a systematic analysis of verb--noun decomposition across three assembly datasets (MECCANO, HAViD, and IMPACT). Although decomposition escapes the atomic ceiling, its generalization extends only partially beyond it. Unseen-composition performance remains strongly tied to the co-occurrence structure of the training data, indicating that much of the observed gain arises from interpolation within densely supported regions of the compositional space rather than from unconstrained recombination. Across datasets, failures consistently concentrate on the larger-vocabulary component, and IMPACT's verb-heavy vocabulary reverses the bottleneck from nouns to verbs. We further show that shared-encoder training introduces component entanglement, encouraging reliance on co-occurrence patterns that transfer poorly to unseen compositions and trailing independent recombination by up to $6.0\times$ in harmonic mean. Taken together, these findings explain why decomposition achieves only partial compositional generalization in practice. By identifying primitive support, vocabulary asymmetry, and component entanglement as connected sources of error, we provide a portable diagnostic framework for studying compositional recognition beyond aggregate accuracy. Code: https://github.com/hisalaheiyo/assembly.
The authors’ abstract, as arXiv lists it. arXiv’s listings, abstracts included, are free for anyone to reuse.
Read it on ReadSearch
Each opens after you create an account, and brings you back to this paper.
More in Artificial Intelligence
Large Language Models for HVAC Operations in Building Energy Systems: A Critical Review of Methods, Applications, and Deployment Readiness
FALCON-S: Fixed-wing ground-effect Aerodynamics Simulator and Flight Control Learning Suite
Newton Matching for Generative Modeling: A Unified Framework for Fine-Tuning and Sampling
Algorithmic Optimality Guarantees for Nonsmooth $H_\infty$ Output-Feedback Policy Search
Resilient Control Loops in Autonomous Vehicles Under Adversarial Jamming via Spectral Perception and Network-Layer Failover
Get the few papers worth your time in Artificial Intelligence every morning.
ReadSearch reads the new papers in your field each day and brings you the few worth reading, each with its key finding in a sentence.