Seeking Consistent Flat Minima for Better Domain Generalization via Refining Loss Landscapes
December 18, 2024 · Declared Dead · 🏛 Computer Vision and Pattern Recognition
"Paper promises code 'coming soon'"
Evidence collected by the PWNC Scanner
Authors
Aodi Li, Liansheng Zhuang, Xiao Long, Minghong Yao, Shafei Wang
arXiv ID
2412.13573
Category
cs.CV: Computer Vision
Cross-listed
cs.AI
Citations
6
Venue
Computer Vision and Pattern Recognition
Last Checked
1 month ago
Abstract
Domain generalization aims to learn a model from multiple training domains and generalize it to unseen test domains. Recent theory has shown that seeking the deep models, whose parameters lie in the flat minima of the loss landscape, can significantly reduce the out-of-domain generalization error. However, existing methods often neglect the consistency of loss landscapes in different domains, resulting in models that are not simultaneously in the optimal flat minima in all domains, which limits their generalization ability. To address this issue, this paper proposes an iterative Self-Feedback Training (SFT) framework to seek consistent flat minima that are shared across different domains by progressively refining loss landscapes during training. It alternatively generates a feedback signal by measuring the inconsistency of loss landscapes in different domains and refines these loss landscapes for greater consistency using this feedback signal. Benefiting from the consistency of the flat minima within these refined loss landscapes, our SFT helps achieve better out-of-domain generalization. Extensive experiments on DomainBed demonstrate superior performances of SFT when compared to state-of-the-art sharpness-aware methods and other prevalent DG baselines. On average across five DG benchmarks, SFT surpasses the sharpness-aware minimization by 2.6% with ResNet-50 and 1.5% with ViT-B/16, respectively. The code will be available soon.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
📜 Similar Papers
In the same crypt — Computer Vision
🌅
🌅
Old Age
🌅
🌅
Old Age
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
R.I.P.
👻
Ghosted
You Only Look Once: Unified, Real-Time Object Detection
🌅
🌅
Old Age
SSD: Single Shot MultiBox Detector
🌅
🌅
Old Age
Squeeze-and-Excitation Networks
R.I.P.
👻
Ghosted
Rethinking the Inception Architecture for Computer Vision
Died the same way — ⏳ Coming Soon™
R.I.P.
⏳
Coming Soon™
Exploring Simple Siamese Representation Learning
R.I.P.
⏳
Coming Soon™
An Analysis of Scale Invariance in Object Detection - SNIP
R.I.P.
⏳
Coming Soon™
Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection
R.I.P.
⏳
Coming Soon™