Picture for Francisco Massa

Francisco Massa

DINOv2: Learning Robust Visual Features without Supervision

Add code
Apr 14, 2023
Viaarxiv icon

Hybrid Transformers for Music Source Separation

Add code
Nov 15, 2022
Viaarxiv icon

Training data-efficient image transformers & distillation through attention

Add code
Jan 15, 2021
Figure 1 for Training data-efficient image transformers & distillation through attention
Figure 2 for Training data-efficient image transformers & distillation through attention
Figure 3 for Training data-efficient image transformers & distillation through attention
Figure 4 for Training data-efficient image transformers & distillation through attention
Viaarxiv icon

End-to-End Object Detection with Transformers

Add code
May 28, 2020
Figure 1 for End-to-End Object Detection with Transformers
Figure 2 for End-to-End Object Detection with Transformers
Figure 3 for End-to-End Object Detection with Transformers
Figure 4 for End-to-End Object Detection with Transformers
Viaarxiv icon

PyTorch: An Imperative Style, High-Performance Deep Learning Library

Add code
Dec 03, 2019
Figure 1 for PyTorch: An Imperative Style, High-Performance Deep Learning Library
Figure 2 for PyTorch: An Imperative Style, High-Performance Deep Learning Library
Figure 3 for PyTorch: An Imperative Style, High-Performance Deep Learning Library
Viaarxiv icon

MLPerf Inference Benchmark

Add code
Nov 06, 2019
Figure 1 for MLPerf Inference Benchmark
Figure 2 for MLPerf Inference Benchmark
Figure 3 for MLPerf Inference Benchmark
Figure 4 for MLPerf Inference Benchmark
Viaarxiv icon

Frame Interpolation with Multi-Scale Deep Loss Functions and Generative Adversarial Networks

Add code
Nov 16, 2017
Figure 1 for Frame Interpolation with Multi-Scale Deep Loss Functions and Generative Adversarial Networks
Figure 2 for Frame Interpolation with Multi-Scale Deep Loss Functions and Generative Adversarial Networks
Figure 3 for Frame Interpolation with Multi-Scale Deep Loss Functions and Generative Adversarial Networks
Figure 4 for Frame Interpolation with Multi-Scale Deep Loss Functions and Generative Adversarial Networks
Viaarxiv icon

Crafting a multi-task CNN for viewpoint estimation

Add code
Sep 13, 2016
Figure 1 for Crafting a multi-task CNN for viewpoint estimation
Figure 2 for Crafting a multi-task CNN for viewpoint estimation
Figure 3 for Crafting a multi-task CNN for viewpoint estimation
Figure 4 for Crafting a multi-task CNN for viewpoint estimation
Viaarxiv icon

Deep Exemplar 2D-3D Detection by Adapting from Real to Rendered Views

Add code
Apr 18, 2016
Figure 1 for Deep Exemplar 2D-3D Detection by Adapting from Real to Rendered Views
Figure 2 for Deep Exemplar 2D-3D Detection by Adapting from Real to Rendered Views
Figure 3 for Deep Exemplar 2D-3D Detection by Adapting from Real to Rendered Views
Figure 4 for Deep Exemplar 2D-3D Detection by Adapting from Real to Rendered Views
Viaarxiv icon

Convolutional Neural Networks for joint object detection and pose estimation: A comparative study

Add code
Feb 28, 2015
Figure 1 for Convolutional Neural Networks for joint object detection and pose estimation: A comparative study
Figure 2 for Convolutional Neural Networks for joint object detection and pose estimation: A comparative study
Figure 3 for Convolutional Neural Networks for joint object detection and pose estimation: A comparative study
Figure 4 for Convolutional Neural Networks for joint object detection and pose estimation: A comparative study
Viaarxiv icon