Revealing the Galaxy-Halo Connection Through Machine Learning

Kavli Affiliate: Nickolay Y. Gnedin | First 5 Authors: Ryan Hausen, Brant E. Robertson, Hanjue Zhu, Nickolay Y. Gnedin, Piero Madau | Summary: Understanding the connections between galaxy stellar mass, star formation rate, and dark matter halo mass represents a key goal of the theory of galaxy formation. Cosmological simulations that include hydrodynamics, physical treatments […]


Continue.. Revealing the Galaxy-Halo Connection Through Machine Learning

Share With Thy Neighbors: Single-View Reconstruction by Cross-Instance Consistency

Kavli Affiliate: Matthew Fisher | First 5 Authors: Tom Monnier, Matthew Fisher, Alexei A. Efros, Mathieu Aubry, | Summary: Approaches to single-view reconstruction typically rely on viewpoint annotations, silhouettes, the absence of background, multiple views of the same instance, a template shape, or symmetry. We avoid all of these supervisions and hypotheses by leveraging explicitly […]


Continue.. Share With Thy Neighbors: Single-View Reconstruction by Cross-Instance Consistency

Share With Thy Neighbors: Single-View Reconstruction by Cross-Instance Consistency

Kavli Affiliate: Matthew Fisher | First 5 Authors: Tom Monnier, Matthew Fisher, Alexei A. Efros, Mathieu Aubry, | Summary: Approaches to single-view reconstruction typically rely on viewpoint annotations, silhouettes, the absence of background, multiple views of the same instance, a template shape, or symmetry. We avoid all of these supervisions and hypotheses by leveraging explicitly […]


Continue.. Share With Thy Neighbors: Single-View Reconstruction by Cross-Instance Consistency

WebFace260M: A Benchmark for Million-Scale Deep Face Recognition

Kavli Affiliate: Zheng Zhu | First 5 Authors: Zheng Zhu, Guan Huang, Jiankang Deng, Yun Ye, Junjie Huang | Summary: Face benchmarks empower the research community to train and evaluate high-performance face recognition systems. In this paper, we contribute a new million-scale recognition benchmark, containing uncurated 4M identities/260M faces (WebFace260M) and cleaned 2M identities/42M faces […]


Continue.. WebFace260M: A Benchmark for Million-Scale Deep Face Recognition

Universal three-state nematicity and magneto-optical Kerr effect in the charge density waves in AV$_3$Sb$_5$ (A=Cs, Rb, K)

Kavli Affiliate: Leon Balents | First 5 Authors: Yishuai Xu, Zhuoliang Ni, Yizhou Liu, Brenden R. Ortiz, Stephen D. Wilson | Summary: The kagome lattice provides a fascinating playground to study geometrical frustration, topology and strong correlations. The newly discovered kagome metals AV$_3$Sb$_5$ (A=K, Rb, Cs) exhibit various interesting phenomena including topological band structure and […]


Continue.. Universal three-state nematicity and magneto-optical Kerr effect in the charge density waves in AV$_3$Sb$_5$ (A=Cs, Rb, K)

Universal three-state nematicity and magneto-optical Kerr effect in the charge density waves in AV$_3$Sb$_5$ (A=Cs, Rb, K)

Kavli Affiliate: Leon Balents | First 5 Authors: Yishuai Xu, Zhuoliang Ni, Yizhou Liu, Brenden R. Ortiz, Stephen D. Wilson | Summary: The kagome lattice provides a fascinating playground to study geometrical frustration, topology and strong correlations. The newly discovered kagome metals AV$_3$Sb$_5$ (A=K, Rb, Cs) exhibit various interesting phenomena including topological band structure and […]


Continue.. Universal three-state nematicity and magneto-optical Kerr effect in the charge density waves in AV$_3$Sb$_5$ (A=Cs, Rb, K)

Learning to Purification for Unsupervised Person Re-identification

Kavli Affiliate: Xiang Zhang | First 5 Authors: Long Lan, Xiao Teng, Jing Zhang, Xiang Zhang, Dacheng Tao | Summary: Unsupervised person re-identification is a challenging and promising task in computer vision. Nowadays unsupervised person re-identification methods have achieved great progress by training with pseudo labels. However, how to purify feature and label noise is […]


Continue.. Learning to Purification for Unsupervised Person Re-identification

Multi-scale Knowledge Distillation for Unsupervised Person Re-Identification

Kavli Affiliate: Xiang Zhang | First 5 Authors: Long Lan, Xiao Teng, Haoang Chi, Xiang Zhang, | Summary: Unsupervised person re-identification is a challenging and promising task in the computer vision. Nowadays unsupervised person re-identification methods have achieved great improvements by training with pseudo labels. However, the appearance and label noise are less explicitly studied […]


Continue.. Multi-scale Knowledge Distillation for Unsupervised Person Re-Identification

Parametric Level-sets Enhanced To Improve Reconstruction (PaLEnTIR)

Kavli Affiliate: Eric Miller | First 5 Authors: Ege Ozsar, Misha Kilmer, Eric Miller, Eric de Sturler, Arvind Saibaba | Summary: We introduce PaLEnTIR, a significantly enhanced parametric level-set (PaLS) method addressing the restoration and reconstruction of piecewise constant objects. Our key contribution involves a unique PaLS formulation utilizing a single level-set function to restore […]


Continue.. Parametric Level-sets Enhanced To Improve Reconstruction (PaLEnTIR)