Contributed Talk Sessions | Poster Sessions | All Posters | Search Papers

Poster Session A: Tuesday, August 12, 1:30 – 4:30 pm, de Brug & E‑Hall

Deep neural networks can learn generalizable same-different visual relations

Alexa R. Tartaglini¹, Sheridan Feucht², Michael A. Lepori³, Wai Keen Vong⁴, Charles Lovering⁵, Brenden Lake⁶, Ellie Pavlick³; ¹Stanford University, ²Northeastern University, ³Brown University, ⁴Facebook, ⁵Kensho, ⁶New York University

Presenter: Alexa R. Tartaglini

Although deep neural networks can achieve human-level performance on many object recognition benchmarks, prior work suggests that these same models fail to learn simple abstract relations, such as determining whether two objects are the same or different. Much of this prior work focuses on training convolutional neural networks to classify images of two same or two different abstract shapes, testing generalization on within-distribution stimuli. In this article, we comprehensively study whether deep neural networks can acquire and generalize same-different relations both within and out-of-distribution using a variety of architectures, forms of pretraining, and fine-tuning datasets. We find that certain pretrained transformers can learn a same-different relation that generalizes with near perfect accuracy to out-of-distribution stimuli. Furthermore, we find that fine-tuning on abstract shapes that lack texture or color provides the strongest out-of-distribution generalization. Our results suggest that, with the right approach, deep neural networks can learn generalizable same-different visual relations.

Topic Area: Visual Processing & Computational Vision

proceeding: Full Text on OpenReview