b'Peter Vajda'

research

∙ 07/27/2023

NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detection

We present NeRF-Det, a novel method for indoor 3D detection with posed R...

0 Chenfeng Xu, et al. ∙

research

∙ 12/05/2022

INGeo: Accelerating Instant Neural Scene Reconstruction with Noisy Geometry Priors

We present a method that accelerates reconstruction of 3D scenes and obj...

4 Chaojian Li, et al. ∙

research

∙ 11/19/2022

A Practical Stereo Depth System for Smart Glasses

We present the design of a productionized end-to-end stereo depth sensin...

0 Jialiang Wang, et al. ∙

research

∙ 11/18/2022

Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention During Vision Transformer Inference

Vision Transformers (ViTs) have shown impressive performance but still r...

0 Haoran You, et al. ∙

research

∙ 11/16/2022

XRBench: An Extended Reality (XR) Machine Learning Benchmark Suite for the Metaverse

Real-time multi-model multi-task (MMMT) workloads, a new form of deep le...

0 Hyoukjun Kwon, et al. ∙

research

∙ 11/12/2022

3D-Aware Encoding for Style-based Neural Radiance Fields

We tackle the task of NeRF inversion for style-based neural radiance fie...

4 Yu-Jhe Li, et al. ∙

research

∙ 10/09/2022

Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP

Open-vocabulary semantic segmentation aims to segment an image into sema...

36 Feng Liang, et al. ∙

research

∙ 08/29/2022

Open-Set Semi-Supervised Object Detection

Recent developments for Semi-Supervised Object Detection (SSOD) have sho...

15 Yen-Cheng Liu, et al. ∙

research

∙ 12/17/2021

Data Efficient Language-supervised Zero-shot Recognition with Optimal Transport Distillation

Traditional computer vision models are trained to predict a fixed set of...

11 Bichen Wu, et al. ∙

research

∙ 11/19/2021

FBNetV5: Neural Architecture Search for Multiple Tasks in One Run

Neural Architecture Search (NAS) has been widely adopted to design accur...

10 Bichen Wu, et al. ∙

research

∙ 06/08/2021

Image2Point: 3D Point-Cloud Understanding with Pretrained 2D ConvNets

3D point-clouds and 2D images are different visual representations of th...

4 Chenfeng Xu, et al. ∙

research

∙ 04/18/2021

Data-Efficient Language-Supervised Zero-Shot Learning with Self-Distillation

Traditional computer vision models are trained to predict a fixed set of...

0 Ruizhe Cheng, et al. ∙

research

∙ 03/18/2021

You Only Group Once: Efficient Point-Cloud Processing with Token Representation and Relation Inference Module

3D point-cloud-based perception is a challenging but crucial computer vi...

0 Chenfeng Xu, et al. ∙

research

∙ 02/18/2021

Unbiased Teacher for Semi-Supervised Object Detection

Semi-supervised learning, i.e., training networks with both labeled and ...

15 Yen-Cheng Liu, et al. ∙

research

∙ 11/25/2020

FBWave: Efficient and Scalable Neural Vocoders for Streaming Text-To-Speech on the Edge

Nowadays more and more applications can benefit from edge-based text-to-...

0 Bichen Wu, et al. ∙

research

∙ 08/27/2020

One Shot 3D Photography

3D photography is a new medium that allows viewers to more fully experie...

10 Johannes Kopf, et al. ∙

research

∙ 07/17/2020

Geometric Correspondence Fields: Learned Differentiable Rendering for 3D Pose Refinement in the Wild

We present a novel 3D pose refinement approach based on differentiable r...

0 Alexander Grabner, et al. ∙

research

∙ 06/05/2020

Visual Transformers: Token-based Image Representation and Processing for Computer Vision

Computer vision has achieved great success using standardized image repr...

23 Bichen Wu, et al. ∙

research

∙ 06/03/2020

FBNetV3: Joint Architecture-Recipe Search using Neural Acquisition Function

Neural Architecture Search (NAS) yields state-of-the-art neural networks...

11 Xiaoliang Dai, et al. ∙

research

∙ 04/12/2020

FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions

Differentiable Neural Architecture Search (DNAS) has demonstrated great ...

17 Alvin Wan, et al. ∙

research

∙ 04/06/2020

Deep Space-Time Video Upsampling Networks

Video super-resolution (VSR) and frame interpolation (FI) are traditiona...

2 Jaeyeon Kang, et al. ∙

research

∙ 04/03/2020

SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation

LiDAR point-cloud segmentation is an important problem for many applicat...

4 Chenfeng Xu, et al. ∙

research

∙ 03/20/2020

Learning the Loss Functions in a Discriminative Space for Video Restoration

With more advanced deep network architectures and learning schemes such ...

16 Younghyun Jo, et al. ∙

research

∙ 07/16/2019

Efficient Segmentation: Learning Downsampling Near Semantic Boundaries

Many automated processes such as auto-piloting rely on a good semantic s...

1 Dmitrii Marin, et al. ∙

research

∙ 06/01/2019

Learning to Generate Grounded Image Captions without Localization Supervision

When generating a sentence description for an image, it frequently remai...

0 Chih-Yao Ma, et al. ∙

research

∙ 12/24/2018

Precision Highway for Ultra Low-Precision Quantization

Neural network quantization has an inherent problem called accumulated q...

0 Eunhyeok Park, et al. ∙

research

∙ 12/21/2018

ChamNet: Towards Efficient Network Design through Platform-Aware Model Adaptation

This paper proposes an efficient neural network (NN) architecture design...

0 Xiaoliang Dai, et al. ∙

research

∙ 12/09/2018

FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search

Designing accurate and efficient ConvNets for mobile devices is challeng...

0 Bichen Wu, et al. ∙

research

∙ 11/30/2018

Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Search

Recent work in network quantization has substantially reduced the time a...

0 Bichen Wu, et al. ∙

research

∙ 04/20/2018

Value-aware Quantization for Training and Inference of Neural Networks

We propose a novel value-aware quantization which applies aggressively r...

0 Eunhyeok Park, et al. ∙

research

∙ 07/15/2016

DSD: Dense-Sparse-Dense Training for Deep Neural Networks

Modern deep neural networks have a large number of parameters, making th...

0 Song Han, et al. ∙

Peter Vajda

Featured Co-authors