Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning
Keywords: Network Design, Optimization, Bias, Backbone, Transformer, Benchmark
TL;DR: This paper revisits the optimizing bias of network designs and optimizers of the previous decade by thoroughly benchmarking typical vision backbones and popular optimizers and providing interpretation and guidance.
Abstract: This paper delves into the interplay between vision backbones and optimizers, revealing an inter-dependent phenomenon termed backbone-optimizer coupling bias} (BOCB). Notably, canonical CNNs, such as VGG and ResNet, exhibit a marked co-dependency with SGD, while recent architectures, including ViTs and ConvNeXt, share a strong coupling with adaptive learning rate optimizers. We further show that strong BOCB may result in extra tuning efforts and poor generalization ability for pre-trained neural networks, substantially limiting their real-world applications. Through in-depth analysis and apples-to-apples comparisons, however, we surprisingly observed that certain types of network architecture could significantly mitigate BOCB, which might serve as practical takeaways for backbone design. We hope this work can inspire the community to rethink the long-held assumptions on backbones and optimizers, consider their interplay in future studies, and contribute to more robust vision systems. The source code and models are publicly available.
Supplementary Material: zip
Primary Area: optimization
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 2246
Loading