b'Adrian Bulat'

research

∙ 04/04/2023

Black Box Few-Shot Adaptation for Vision-Language models

Vision-Language (V-L) models trained with contrastive learning to align ...

0 Yassine Ouali, et al. ∙

research

∙ 10/10/2022

FS-DETR: Few-Shot DEtection TRansformer with prompting and without re-training

This paper is on Few-Shot Object Detection (FSOD), where given a few tem...

14 Adrian Bulat, et al. ∙

research

∙ 10/05/2022

Variational prompt tuning improves generalization of vision-language models

Prompt tuning provides an efficient mechanism to adapt large vision-lang...

3 Mohammad Mahdi Derakhshani, et al. ∙

research

∙ 10/03/2022

Language-Aware Soft Prompting for Vision Language Foundation Models

This paper is on soft prompt learning for Vision & Language (V L) mode...

0 Adrian Bulat, et al. ∙

research

∙ 09/29/2022

REST: REtrieve Self-Train for generative action recognition

This work is on training a generative action/video recognition model who...

0 Adrian Bulat, et al. ∙

research

∙ 08/23/2022

Efficient Attention-free Video Shift Transformers

This paper tackles the problem of efficient video recognition. In this a...

0 Adrian Bulat, et al. ∙

research

∙ 06/16/2022

iBoot: Image-bootstrapped Self-Supervised Video Representation Learning

Learning visual representations through self-supervision is an extremely...

0 Fatemeh Saleh, et al. ∙

research

∙ 05/13/2022

Knowledge Distillation Meets Open-Set Semi-Supervised Learning

Existing knowledge distillation methods mostly focus on distillation of ...

13 Jing Yang, et al. ∙

research

∙ 05/06/2022

EdgeViTs: Competing Light-weight CNNs on Mobile Devices with Vision Transformers

Self-attention based models such as vision transformers (ViTs) have emer...

18 Junting Pan, et al. ∙

research

∙ 11/03/2021

Subpixel Heatmap Regression for Facial Landmark Localization

Deep Learning models based on heatmap regression have revolutionized the...

0 Adrian Bulat, et al. ∙

research

∙ 10/26/2021

Defensive Tensorization

We propose defensive tensorization, an adversarial defence technique tha...

4 Adrian Bulat, et al. ∙

research

∙ 10/06/2021

SAIC_Cambridge-HuPBA-FBK Submission to the EPIC-Kitchens-100 Action Recognition Challenge 2021

This report presents the technical details of our submission to the EPIC...

0 Swathikiran Sudhakaran, et al. ∙

research

∙ 06/10/2021

Space-time Mixing Attention for Video Transformer

This paper is on video recognition using Transformers. Very recent attem...

0 Adrian Bulat, et al. ∙

research

∙ 03/31/2021

Bit-Mixer: Mixed-precision networks with runtime bit-width selection

Mixed-precision networks allow for a variable bit-width quantization for...

0 Adrian Bulat, et al. ∙

research

∙ 03/30/2021

Pre-training strategies and datasets for facial representation learning

What is the best way to learn a universal face representation? Recent wo...

0 Adrian Bulat, et al. ∙

research

∙ 02/08/2021

Improving memory banks for unsupervised learning with large mini-batch, consistency and hard negative mining

An important component of unsupervised learning by instance-based discri...

0 Adrian Bulat, et al. ∙

research

∙ 11/03/2020

Semi-supervised Facial Action Unit Intensity Estimation with Contrastive Learning

This paper tackles the challenging problem of estimating the intensity o...

0 Enrique Sanchez, et al. ∙

research

∙ 10/07/2020

High-Capacity Expert Binary Networks

Network binarization is a promising hardware-aware direction for creatin...

0 Adrian Bulat, et al. ∙

research

∙ 04/14/2020

A Transfer Learning approach to Heatmap Regression for Action Unit intensity estimation

Action Units (AUs) are geometrically-based atomic facial muscle movement...

12 Ioanna Ntinou, et al. ∙

research

∙ 03/25/2020

Training Binary Neural Networks with Real-to-Binary Convolutions

This paper shows how to train binary networks to within a few percent po...

9 Brais Martinez, et al. ∙

research

∙ 03/09/2020

Knowledge distillation via adaptive instance normalization

This paper addresses the problem of model compression via knowledge dist...

17 Jing Yang, et al. ∙

research

∙ 03/03/2020

BATS: Binary ArchitecTure Search

This paper proposes Binary ArchitecTure Search (BATS), a framework that ...

31 Adrian Bulat, et al. ∙

research

∙ 02/25/2020

Toward fast and accurate human pose estimation via soft-gated skip connections

This paper is on highly accurate and highly efficient human pose estimat...

0 Adrian Bulat, et al. ∙

research

∙ 11/14/2019

Towards Pose-invariant Lip-Reading

Lip-reading models have been significantly improved recently thanks to p...

19 Shiyang Cheng, et al. ∙

research

∙ 09/30/2019

XNOR-Net++: Improved Binary Neural Networks

This paper proposes an improved training algorithm for binary neural net...

0 Adrian Bulat, et al. ∙

research

∙ 06/14/2019

Efficient N-Dimensional Convolutions via Higher-Order Factorization

With the unprecedented success of deep convolutional neural networks cam...

3 Jean Kossaifi, et al. ∙

research

∙ 04/16/2019

Matrix and tensor decompositions for training binary neural networks

This paper is on improving the training of binary neural networks in whi...

6 Adrian Bulat, et al. ∙

research

∙ 04/12/2019

Incremental multi-domain learning with network latent tensor factorization

The prominence of deep learning, large amount of annotated data and incr...

8 Adrian Bulat, et al. ∙

research

∙ 04/11/2019

Improved training of binary networks for human pose estimation and image recognition

Big neural networks trained on large datasets have advanced the state-of...

4 Adrian Bulat, et al. ∙

research

∙ 04/04/2019

T-Net: Parametrizing Fully Convolutional Nets with a Single High-Order Tensor

Recent findings indicate that over-parametrization, while crucial for su...

16 Jean Kossaifi, et al. ∙

research

∙ 08/14/2018

Hierarchical binary CNNs for landmark localization with limited resources

Our goal is to design architectures that retain the groundbreaking perfo...

8 Adrian Bulat, et al. ∙

research

∙ 07/30/2018

To learn image super-resolution, use a GAN to learn how to do image degradation first

This paper is on image and face super-resolution. The vast majority of p...

6 Adrian Bulat, et al. ∙

research

∙ 12/07/2017

Super-FAN: Integrated facial landmark localization and super-resolution of real-world low resolution faces in arbitrary poses with GANs

This paper addresses two challenging tasks: improving the quality of rea...

0 Adrian Bulat, et al. ∙

research

∙ 03/22/2017

Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression

3D face reconstruction is a fundamental Computer Vision problem of extra...

0 Aaron S. Jackson, et al. ∙

research

∙ 03/21/2017

How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)

This paper investigates how far a very deep neural network is from attai...

0 Adrian Bulat, et al. ∙

research

∙ 03/02/2017

Binarized Convolutional Landmark Localizers for Human Pose Estimation and Face Alignment with Limited Resources

Our goal is to design architectures that retain the groundbreaking perfo...

0 Adrian Bulat, et al. ∙

research

∙ 09/29/2016

Two-stage Convolutional Part Heatmap Regression for the 1st 3D Face Alignment in the Wild (3DFAW) Challenge

This paper describes our submission to the 1st 3D Face Alignment in the ...

0 Adrian Bulat, et al. ∙

research

∙ 09/06/2016

Human pose estimation via Convolutional Part Heatmap Regression

This paper is on human pose estimation using Convolutional Neural Networ...

0 Adrian Bulat, et al. ∙

Adrian Bulat

Featured Co-authors