2024
An Investigation on Hardware-Aware Vision Transformer Scaling.
ACM Trans. Embed. Comput. Syst., May, 2024
AVID: Any-Length Video Inpainting with Diffusion Model.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
Fairy: Fast Parallelized Instruction-Guided Video-to-Video Synthesis.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
Cache Me if You Can: Accelerating Diffusion Models through Block Caching.
,
,
,
,
,
,
,
,
,
,
,
,
,
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
ControlRoom3D: Room Generation Using Semantic Proxy Rooms.
,
,
,
,
,
,
,
,
,
,
,
,
,
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
MaskINT: Video Editing via Interpolative Non-autoregressive Masked Transformers.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis.
,
,
,
,
,
,
,
,
,
,
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
VideoSwap: Customized Video Subject Swapping with Interactive Semantic Point Correspondence.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
MixRT: Mixed Neural Representations For Real-Time NeRF Rendering.
Proceedings of the International Conference on 3D Vision, 2024
2023
Pruning Compact ConvNets for Efficient Inference.
CoRR, 2023
NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detection.
,
,
,
,
,
,
,
,
,
,
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023
Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023
Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023
2022
A Review of Single-Source Deep Unsupervised Visual Domain Adaptation.
,
,
,
,
,
,
,
,
,
,
IEEE Trans. Neural Networks Learn. Syst., 2022
Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention During Vision Transformer Inference.
CoRR, 2022
3D-Aware Encoding for Style-based Neural Radiance Fields.
CoRR, 2022
Data Efficient Language-Supervised Zero-Shot Recognition with Optimal Transport Distillation.
Proceedings of the Tenth International Conference on Learning Representations, 2022
Image2Point: 3D Point-Cloud Understanding with 2D Image Pretrained Models.
Proceedings of the Computer Vision - ECCV 2022, 2022
INGeo: Accelerating Instant Neural Scene Reconstruction with Noisy Geometry Priors.
Proceedings of the Computer Vision - ECCV 2022 Workshops, 2022
Cross-Domain Adaptive Teacher for Object Detection.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022
2021
A Fistful of Words: Learning Transferable Visual Models from Bag-of-Words Supervision.
CoRR, 2021
Data Efficient Language-supervised Zero-shot Recognition with Optimal Transport Distillation.
CoRR, 2021
Cross-Domain Object Detection via Adaptive Self-Training.
CoRR, 2021
FBNetV5: Neural Architecture Search for Multiple Tasks in One Run.
CoRR, 2021
Differentiable NAS Framework and Application to Ads CTR Prediction.
CoRR, 2021
Image2Point: 3D Point-Cloud Understanding with Pretrained 2D ConvNets.
CoRR, 2021
Improving Context-Based Meta-Reinforcement Learning with Self-Supervised Trajectory Contrastive Learning.
CoRR, 2021
You Only Group Once: Efficient Point-Cloud Processing with Token Representation and Relation Inference Module.
Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2021
Unbiased Teacher for Semi-Supervised Object Detection.
Proceedings of the 9th International Conference on Learning Representations, 2021
Visual Transformers: Where Do Transformers Really Belong in Vision Models?
Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021
CoDeNet: Efficient Deployment of Input-Adaptive Object Detection on Embedded FPGAs.
Proceedings of the FPGA '21: The 2021 ACM/SIGDA International Symposium on Field Programmable Gate Arrays, Virtual Event, USA, February 28, 2021
FP-NAS: Fast Probabilistic Neural Architecture Search.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021
Rethinking the Self-Attention in Vision Transformers.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2021
FBNetV3: Joint Architecture-Recipe Search Using Predictor Pretraining.
,
,
,
,
,
,
,
,
,
,
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021
Data-Efficient Language-Supervised Zero-Shot Learning With Self-Distillation.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2021
ePointDA: An End-to-End Simulation-to-Real Domain Adaptation Framework for LiDAR Point Cloud Segmentation.
Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021
2020
FBWave: Efficient and Scalable Neural Vocoders for Streaming Text-To-Speech on the Edge.
CoRR, 2020
CoDeNet: Algorithm-hardware Co-design for Deformable Convolution.
CoRR, 2020
Visual Transformers: Token-based Image Representation and Processing for Computer Vision.
CoRR, 2020
FBNetV3: Joint Architecture-Recipe Search using Neural Acquisition Function.
,
,
,
,
,
,
,
,
,
,
CoRR, 2020
SqueezeWave: Extremely Lightweight Vocoders for On-device Speech Synthesis.
CoRR, 2020
SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation.
Proceedings of the Computer Vision - ECCV 2020, 2020
FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions.
,
,
,
,
,
,
,
,
,
,
,
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020
2019
Co-design of deep neural nets and neural net accelerators for embedded vision applications.
IBM J. Res. Dev., 2019
Domain-Aware Dynamic Networks.
CoRR, 2019
Efficient Deep Neural Networks.
CoRR, 2019
Algorithm-hardware Co-design for Deformable Convolution.
Proceedings of the Fifth Workshop on Energy Efficient Machine Learning and Cognitive Computing, 2019
LATTE: Accelerating LiDAR Point Cloud Annotation via Sensor Fusion, One-Click Annotation, and Tracking.
Proceedings of the 2019 IEEE Intelligent Transportation Systems Conference, 2019
SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud.
Proceedings of the International Conference on Robotics and Automation, 2019
Synetgy: Algorithm-hardware Co-design for ConvNet Accelerators on Embedded FPGAs.
,
,
,
,
,
,
,
,
,
,
Proceedings of the 2019 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays, 2019
FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019
ChamNet: Towards Efficient Network Design Through Platform-Aware Model Adaptation.
,
,
,
,
,
,
,
,
,
,
,
,
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019
2018
Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Search.
CoRR, 2018
Unsupervised Domain Adaptation: from Simulation Engine to the RealWorld.
CoRR, 2018
A LiDAR Point Cloud Generator: from a Virtual World to Autonomous Driving.
Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval, 2018
SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud.
Proceedings of the 2018 IEEE International Conference on Robotics and Automation, 2018
Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions.
Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018
SqueezeNext: Hardware-Aware Neural Network Design.
Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2018
2017
Shallow Networks for High-accuracy Road Object-detection.
Proceedings of the 3rd International Conference on Vehicle Technology and Intelligent Transport Systems, 2017
SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real-Time Object Detection for Autonomous Driving.
Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2017
2015
Poster: MAPP: The Berkeley Model and Algorithm Prototyping Platform.
Proceedings of the 37th IEEE/ACM International Conference on Software Engineering, 2015
MAPP: The Berkeley Model and Algorithm Prototyping Platform.
Proceedings of the 2015 IEEE Custom Integrated Circuits Conference, 2015
2014
Efficient per-element distortion contribution analysis via Harmonic Balance adjoints.
Proceedings of the IEEE 2014 Custom Integrated Circuits Conference, 2014
2013
Time-domain segmentation based massively parallel simulation for ADCs.
Proceedings of the 50th Annual Design Automation Conference 2013, 2013