Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization
Dec 6, 2021
Speakers
Yusuke Iwasawa
Speaker · 0 followers
Yutaka Matsuo
Speaker · 0 followers
About
This paper presents a new algorithm for domain generalization (DG), test-time template adjuster (T3A), aiming to develop a model that performs well under conditions different to those of training conditions. Unlike existing methods that focus on training phase, our method focuses test phase, i.e., correcting its prediction by itself during test time. Specifically, T3A adjusts a trained linear classifier (the last layer of deep neural networks) with the following procedure: (1) compute a pseudo-prototype representation for each class using online unlabeled data augmented by the base classifier trained in the source domains, (2) and then classify each sample based on its distance to the pseudo-prototypes. T3A is back-propagation-free and modifies only the linear layer; therefore, the increase in computational cost during inference is negligible and avoids the catastrophic failure might caused by stochastic optimization. Despite its simplicity, T3A can leverage knowledge about the target domain by using off-the-shelf test-time data and improve performance. We tested our method on four domain generalization benchmarks, namely PACS, VLCS, OfficeHome, and TerraIncognita, along with various backbone networks including ResNet18, ResNet50, Big Transfer (BiT), Vision Transformers (ViT), and MLP-Mixer. The results show T3A stably improves performance on unseen domains across choices of backbone networks, and outperforms existing domain generalization methods.This paper presents a new algorithm for domain generalization (DG), test-time template adjuster (T3A), aiming to develop a model that performs well under conditions different to those of training conditions. Unlike existing methods that focus on training phase, our method focuses test phase, i.e., correcting its prediction by itself during test time. Specifically, T3A adjusts a trained linear classifier (the last layer of deep neural networks) with the following procedure: (1) compute a pseudo-p…
Organizer
NeurIPS 2021
Account · 1.9k followers
Categories
AI & Data Science
Category · 10.8k presentations
About NeurIPS 2021
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Drug Re-positioning via Text Augmented Knowledge Graph Embeddings
Watch later
Mian Zhong, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
CAFE: Catastrophic Data Leakage in Vertical Federated Learning
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Noise2Score: Tweedie’s Approach to Self-Supervised Image Denoising without Clean Images
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Proper Value Equivalence
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Conic Blackwell Algorithm: Parameter-Free Convex-Concave Saddle-Point Solving
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Machine Learning for Variance Reduction in Online Experiments
Watch later
Yongyi Guo, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%