paper-with-me

홈 › Papers

ClusT3: Information Invariant Test-Time Training

2023-10-18 · ICCV 2023 1 · Gustavo A. Vargas Hakim, David Osowiechi, Mehrdad Noori, Milad Cheraghalikhani, Ismail Ben Ayed, Christian Desrosiers

Deep Learning models have shown remarkable performance in a broad range of vision tasks. However, they are often vulnerable against domain shifts at test-time. Test-time training (TTT) methods have been developed in an attempt to mitigate these vulnerabilities, where a secondary task is solved at training time simultaneously with the main task, to be later used as an self-supervised proxy task at test-time. In this work, we propose a novel unsupervised TTT technique based on the maximization of Mutual Information between multi-scale feature maps and a discrete latent representation, which can be integrated to the standard training as an auxiliary clustering task. Experimental results demonstrate competitive classification performance on different popular test-time adaptation benchmarks.

📄 PDF Abstract BibTeX arXiv:2310.12345

Code (1)

dosowiechi/clust3 공식 구현 pytorch

Tasks

Test-time Adaptation

Similar Papers 제목 키워드 기반

Learning Invariant Representations of Graph Neural Networks via Cluster Generalization

2024-03-06 · NeurIPS 2023 11 · Donglin Xia, Xiao Wang, Nian Liu, Chuan Shi

Graph neural networks (GNNs) have become increasingly popular in modeling graph-structured data due to their ability to learn node representations by aggregating local structure information. However, it is widely acknowl…

Data-driven Cloud Clustering via a Rotationally Invariant Autoencoder

2021-03-08 · Takuya Kurihana, Elisabeth Moyer, Rebecca Willett, Davis Gilton 외

Advanced satellite-born remote sensing instruments produce high-resolution multi-spectral data for much of the globe at a daily cadence. These datasets open up the possibility of improved understanding of cloud dynamics …

Clustering

Out-of-Context Misinformation Detection via Variational Domain-Invariant Learning with Test-Time Training

2025-11-13 · Xi Yang, Han Zhang, Zhijian Lin, Yibiao Hu 외 arxiv

Out-of-context misinformation (OOC) is a low-cost form of misinformation in news reports, which refers to place authentic images into out-of-context or fabricated image-text pairings. This problem has attracted significa…

Domain Adaptation

Deep Multiview Clustering by Contrasting Cluster Assignments

2023-04-21 · ICCV 2023 1 · Jie Chen, Hua Mao, Wai Lok Woo, Xi Peng

Multiview clustering (MVC) aims to reveal the underlying structure of multiview data by categorizing data samples into clusters. Deep learning-based methods exhibit strong feature learning capabilities on large-scale dat…

ClusteringContrastive LearningMultiview Clustering

Manipulating Medical Image Translation with Manifold Disentanglement

2020-11-27 · Siyu Liu, Jason A. Dowling, Craig Engstrom, Peter B. Greer 외

Medical image translation (e.g. CT to MR) is a challenging task as it requires I) faithful translation of domain-invariant features (e.g. shape information of anatomical structures) and II) realistic synthesis of target-…

DisentanglementGenerative Adversarial NetworkTranslation