Alert button
Picture for Adrian Weller

Adrian Weller

Alert button

Iterative Teaching by Label Synthesis

Oct 27, 2021
Weiyang Liu, Zhen Liu, Hanchen Wang, Liam Paull, Bernhard Schölkopf, Adrian Weller

Figure 1 for Iterative Teaching by Label Synthesis
Figure 2 for Iterative Teaching by Label Synthesis
Figure 3 for Iterative Teaching by Label Synthesis
Figure 4 for Iterative Teaching by Label Synthesis
Viaarxiv icon

Hybrid Random Features

Oct 13, 2021
Krzysztof Choromanski, Haoxian Chen, Han Lin, Yuanzhe Ma, Arijit Sehanobish, Deepali Jain, Michael S Ryoo, Jake Varley, Andy Zeng, Valerii Likhosherstov, Dmitry Kalashnikov, Vikas Sindhwani, Adrian Weller

Figure 1 for Hybrid Random Features
Figure 2 for Hybrid Random Features
Figure 3 for Hybrid Random Features
Figure 4 for Hybrid Random Features
Viaarxiv icon

SphereFace Revived: Unifying Hyperspherical Face Recognition

Sep 12, 2021
Weiyang Liu, Yandong Wen, Bhiksha Raj, Rita Singh, Adrian Weller

Figure 1 for SphereFace Revived: Unifying Hyperspherical Face Recognition
Figure 2 for SphereFace Revived: Unifying Hyperspherical Face Recognition
Figure 3 for SphereFace Revived: Unifying Hyperspherical Face Recognition
Figure 4 for SphereFace Revived: Unifying Hyperspherical Face Recognition
Viaarxiv icon

SphereFace2: Binary Classification is All You Need for Deep Face Recognition

Aug 03, 2021
Yandong Wen, Weiyang Liu, Adrian Weller, Bhiksha Raj, Rita Singh

Figure 1 for SphereFace2: Binary Classification is All You Need for Deep Face Recognition
Figure 2 for SphereFace2: Binary Classification is All You Need for Deep Face Recognition
Figure 3 for SphereFace2: Binary Classification is All You Need for Deep Face Recognition
Figure 4 for SphereFace2: Binary Classification is All You Need for Deep Face Recognition
Viaarxiv icon

DIVINE: Diverse Influential Training Points for Data Visualization and Model Refinement

Jul 13, 2021
Umang Bhatt, Isabel Chien, Muhammad Bilal Zafar, Adrian Weller

Figure 1 for DIVINE: Diverse Influential Training Points for Data Visualization and Model Refinement
Figure 2 for DIVINE: Diverse Influential Training Points for Data Visualization and Model Refinement
Figure 3 for DIVINE: Diverse Influential Training Points for Data Visualization and Model Refinement
Figure 4 for DIVINE: Diverse Influential Training Points for Data Visualization and Model Refinement
Viaarxiv icon

Debiasing a First-order Heuristic for Approximate Bi-level Optimization

Jun 08, 2021
Valerii Likhosherstov, Xingyou Song, Krzysztof Choromanski, Jared Davis, Adrian Weller

Figure 1 for Debiasing a First-order Heuristic for Approximate Bi-level Optimization
Figure 2 for Debiasing a First-order Heuristic for Approximate Bi-level Optimization
Figure 3 for Debiasing a First-order Heuristic for Approximate Bi-level Optimization
Figure 4 for Debiasing a First-order Heuristic for Approximate Bi-level Optimization
Viaarxiv icon

On the Expressive Power of Self-Attention Matrices

Jun 08, 2021
Valerii Likhosherstov, Krzysztof Choromanski, Adrian Weller

Figure 1 for On the Expressive Power of Self-Attention Matrices
Figure 2 for On the Expressive Power of Self-Attention Matrices
Figure 3 for On the Expressive Power of Self-Attention Matrices
Figure 4 for On the Expressive Power of Self-Attention Matrices
Viaarxiv icon

Do Concept Bottleneck Models Learn as Intended?

May 10, 2021
Andrei Margeloiu, Matthew Ashman, Umang Bhatt, Yanzhi Chen, Mateja Jamnik, Adrian Weller

Figure 1 for Do Concept Bottleneck Models Learn as Intended?
Figure 2 for Do Concept Bottleneck Models Learn as Intended?
Figure 3 for Do Concept Bottleneck Models Learn as Intended?
Figure 4 for Do Concept Bottleneck Models Learn as Intended?
Viaarxiv icon