Timezone: »

Finding Differences Between Transformers and ConvNets Using Counterfactual Simulation Testing
Nataniel Ruiz · Sarah Bargal · Cihang Xie · Kate Saenko · Stan Sclaroff

Wed Nov 30 09:00 AM -- 11:00 AM (PST) @ Hall J #929

Modern deep neural networks tend to be evaluated on static test sets. One shortcoming of this is the fact that these deep neural networks cannot be easily evaluated for robustness issues with respect to specific scene variations. For example, it is hard to study the robustness of these networks to variations of object scale, object pose, scene lighting and 3D occlusions. The main reason is that collecting real datasets with fine-grained naturalistic variations of sufficient scale can be extremely time-consuming and expensive. In this work, we present Counterfactual Simulation Testing, a counterfactual framework that allows us to study the robustness of neural networks with respect to some of these naturalistic variations by building realistic synthetic scenes that allow us to ask counterfactual questions to the models, ultimately providing answers to questions such as "Would your classification still be correct if the object were viewed from the top?" or "Would your classification still be correct if the object were partially occluded by another object?". Our method allows for a fair comparison of the robustness of recently released, state-of-the-art Convolutional Neural Networks and Vision Transformers, with respect to these naturalistic variations. We find evidence that ConvNext is more robust to pose and scale variations than Swin, that ConvNext generalizes better to our simulated domain and that Swin handles partial occlusion better than ConvNext. We also find that robustness for all networks improves with network scale and with data scale and variety. We release the Naturalistic Variation Object Dataset (NVD), a large simulated dataset of 272k images of everyday objects with naturalistic variations such as object pose, scale, viewpoint, lighting and occlusions. Project page: https://counterfactualsimulation.github.io

Author Information

Nataniel Ruiz (Boston University)
Sarah Bargal (Boston University)
Cihang Xie ( University of California, Santa Cruz)
Kate Saenko (Boston University & MIT-IBM Watson AI Lab, IBM Research)
Kate Saenko

Kate is an AI Research Scientist at FAIR, Meta and a Full Professor of Computer Science at Boston University (currently on leave) where she leads the Computer Vision and Learning Group. Kate received a PhD in EECS from MIT and did postdoctoral training at UC Berkeley and Harvard. Her research interests are in Artificial Intelligence with a focus on out-of-distribution learning, dataset bias, domain adaptation, vision and language understanding, and other topics in deep learning. Past academic positions Consulting professor at the MIT-IBM Watson AI Lab 2019-2022. Assistant Professor, Computer Science Department at UMass Lowell Postdoctoral Researcher, International Computer Science Institute Visiting Scholar, UC Berkeley EECS Visiting Postdoctoral Fellow, SEAS, Harvard University

Stan Sclaroff (Boston University)

More from the Same Authors