1.6k citations · 4.8k across the 20 of their papers we have counts for
24 papers
Learning to See before Learning to Act: Visual Pre-training for Manipulation
Lin Yen-Chen, Andy Zeng, Shuran Song +2
Does having visual priors (e.g. the ability to detect objects) facilitate learning to perform vision-based manipulation (e.g. picking up objects)? We study this problem under the f…
SITTA: Single Image Texture Translation for Data Augmentation
Boyi Li, Yin Cui, Tsung-Yi Lin +1
Recent advances in data augmentation enable one to translate images by learning the mapping between a source domain and a target domain. Existing methods tend to learn the distribu…
Revisiting ResNets: Improved Training and Scaling Strategies
Irwan Bello, William Fedus, Xianzhi Du +5
Novel computer vision architectures monopolize the spotlight, but the impact of the model architecture is often conflated with simultaneous changes to training methodology and scal…
Bottleneck Transformers for Visual Recognition
Aravind Srinivas, Tsung-Yi Lin, Niki Parmar +3
We present BoTNet, a conceptually simple yet powerful backbone architecture that incorporates self-attention for multiple computer vision tasks including image classification, obje…
Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation
Golnaz Ghiasi, Yin Cui, Aravind Srinivas +5
Building instance segmentation models that are data-efficient and can handle rare object categories is an important challenge in computer vision. Leveraging data augmentations is a…
INeRF: Inverting Neural Radiance Fields for Pose Estimation
Lin Yen-Chen, Pete Florence, Jonathan T. Barron +3
We present iNeRF, a framework that performs mesh-free pose estimation by "inverting" a Neural RadianceField (NeRF). NeRFs have been shown to be remarkably effective for the task of…
Efficient Scale-Permuted Backbone with Learned Resource Distribution
Xianzhi Du, Tsung-Yi Lin, Pengchong Jin +4
Recently, SpineNet has demonstrated promising results on object detection and image classification over ResNet model. However, it is unclear if the improvement adds up when combini…
SoDA: Multi-Object Tracking with Soft Data Association
Wei-Chih Hung, Henrik Kretzschmar, Tsung-Yi Lin +4
Robust multi-object tracking (MOT) is a prerequisite fora safe deployment of self-driving cars. Tracking objects, however, remains a highly challenging problem, especially in clutt…
Mask2CAD: 3D Shape Prediction by Learning to Segment and Retrieve
Weicheng Kuo, Anelia Angelova, Tsung-Yi Lin +1
Object recognition has seen significant progress in the image domain, with focus primarily on 2D perception. We propose to leverage existing large-scale datasets of 3D models to un…
Rethinking Pre-training and Self-training
Barret Zoph, Golnaz Ghiasi, Tsung-Yi Lin +4
Pre-training is a dominant paradigm in computer vision. For example, supervised ImageNet pre-training is commonly used to initialize the backbones of object detection and segmentat…
Improving Semantic Segmentation through Spatio-Temporal Consistency Learned from Videos
Ankita Pasad, Ariel Gordon, Tsung-Yi Lin +1
We leverage unsupervised learning of depth, egomotion, and camera intrinsics to improve the performance of single-image semantic segmentation, by enforcing 3D-geometric and tempora…
SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization
Xianzhi Du, Tsung-Yi Lin, Pengchong Jin +5
Convolutional neural networks typically encode an input image into a series of intermediate features with decreasing resolutions. While this structure is suited to classification t…
MnasFPN: Learning Latency-aware Pyramid Architecture for Object Detection on Mobile Devices
Bo Chen, Golnaz Ghiasi, Hanxiao Liu +4
Despite the blooming success of architecture search for vision tasks in resource-constrained environments, the design of on-device object detection architectures have mostly been m…
Learning Data Augmentation Strategies for Object Detection
Barret Zoph, Ekin D. Cubuk, Golnaz Ghiasi +3
Data augmentation is a critical component of training deep learning models. Although data augmentation has been shown to significantly improve image classification, its potential h…
NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection
Golnaz Ghiasi, Tsung-Yi Lin, Ruoming Pang +1
Current state-of-the-art convolutional architectures for object detection are manually designed. Here we aim to learn a better architecture of feature pyramid network for object de…
ShapeMask: Learning to Segment Novel Objects by Refining Shape Priors
Weicheng Kuo, Anelia Angelova, Jitendra Malik +1
Instance segmentation aims to detect and segment individual objects in a scene. Most existing methods rely on precise mask annotations of every category. However, it is difficult a…
Class-Balanced Loss Based on Effective Number of Samples
Yin Cui, Menglin Jia, Tsung-Yi Lin +2
With the rapid increase of large-scale, real-world datasets, it becomes critical to address the problem of long-tailed data distribution (i.e., a few classes account for most of th…
DropBlock: A regularization method for convolutional networks
Golnaz Ghiasi, Tsung-Yi Lin, Quoc V. Le
Deep neural networks often work well when they are over-parameterized and trained with a massive amount of noise and regularization, such as weight decay and dropout. Although drop…
Focal Loss for Dense Object Detection
Tsung-Yi Lin, Priya Goyal, Ross Girshick +2
The highest accuracy object detectors to date are based on a two-stage approach popularized by R-CNN, where a classifier is applied to a sparse set of candidate object locations. I…
Feature Pyramid Networks for Object Detection
Tsung-Yi Lin, Piotr Dollár, Ross Girshick +3
Feature pyramids are a basic component in recognition systems for detecting objects at different scales. But recent deep learning object detectors have avoided pyramid representati…
A MultiPath Network for Object Detection
Sergey Zagoruyko, Adam Lerer, Tsung-Yi Lin +4
The recent COCO object detection dataset presents several new challenges for object detection. In particular, it contains objects at a broad range of scales, less prototypical imag…
Learning to Refine Object Segments
Pedro O. Pinheiro, Tsung-Yi Lin, Ronan Collobert +1
Object segmentation requires both object-level information and low-level pixel data. This presents a challenge for feedforward networks: lower layers in convolutional nets capture…
Microsoft COCO Captions: Data Collection and Evaluation Server
Xinlei Chen, Hao Fang, Tsung-Yi Lin +4
In this paper we describe the Microsoft COCO Caption dataset and evaluation server. When completed, the dataset will contain over one and a half million captions describing over 33…
Microsoft COCO: Common Objects in Context
Tsung-Yi Lin, Michael Maire, Serge Belongie +7
We present a new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question…