9.7k citations · 26.5k across the 43 of their papers we have counts for
55 papers
MOFI: Learning Image Representations from Noisy Entity Annotated Images
Wentao Wu, Aleksei Timofeev, Chen Chen +8
We present MOFI, Manifold OF Images, a new vision foundation model designed to learn image representations from noisy entity annotated images. MOFI differs from previous work in tw…
On Robustness in Multimodal Learning
Brandon McKinzie, Joseph Cheng, Vaishaal Shankar +3
Multimodal learning is defined as learning over multiple heterogeneous input modalities such as video, audio, and text. In this work, we are concerned with understanding how models…
STAIR: Learning Sparse Text and Image Representation in Grounded Tokens
Chen Chen, Bowen Zhang, Liangliang Cao +7
Image and text retrieval is one of the foundational tasks in the vision and language domain with multiple real-world applications. State-of-the-art approaches, e.g. CLIP, ALIGN, re…
PseudoAugment: Learning to Use Unlabeled Data for Data Augmentation in Point Clouds
Zhaoqi Leng, Shuyang Cheng, Benjamin Caine +5
Data augmentation is an important technique to improve data efficiency and save labeling cost for 3D detection in point clouds. Yet, existing augmentation policies have so far been…
Perceptual Grouping in Contrastive Vision-Language Models
Kanchana Ranasinghe, Brandon McKinzie, Sachin Ravi +3
Recent advances in zero-shot image recognition suggest that vision-language models learn generic visual representations with a high degree of semantic information that may be arbit…
Soft Calibration Objectives for Neural Networks
Archit Karandikar, Nicholas Cain, Dustin Tran +4
Optimal decision making requires that classifiers produce uncertainty estimates consistent with their empirical accuracy. However, deep neural networks are often under- or over-con…
Scene Transformer: A unified architecture for predicting multiple agent trajectories
Jiquan Ngiam, Benjamin Caine, Vijay Vasudevan +11
Predicting the motion of multiple agents is necessary for planning in dynamic environments. This task is challenging for autonomous driving since agents (e.g. vehicles and pedestri…
Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset
Scott Ettinger, Shuyang Cheng, Benjamin Caine +15
As autonomous driving systems mature, motion forecasting has received increasing attention as a critical requirement for planning. Of particular importance are interactive situatio…
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…
Pseudo-labeling for Scalable 3D Object Detection
Benjamin Caine, Rebecca Roelofs, Vijay Vasudevan +4
To safely deploy autonomous vehicles, onboard perception systems must work reliably at high accuracy across a diverse set of environments and geographies. One of the most common te…
Scaling Local Self-Attention for Parameter Efficient Visual Backbones
Ashish Vaswani, Prajit Ramachandran, Aravind Srinivas +3
Self-attention has the promise of improving computer vision systems due to parameter-independent scaling of receptive fields and content-dependent interactions, in contrast to para…
Scalable Scene Flow from Point Clouds in the Real World
Philipp Jund, Chris Sweeney, Nichola Abdo +2
Autonomous vehicles operate in highly dynamic environments necessitating an accurate assessment of which aspects of a scene are moving and where they are moving to. A popular appro…
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…
Mitigating Bias in Calibration Error Estimation
Rebecca Roelofs, Nicholas Cain, Jonathon Shlens +1
For an AI system to be reliable, the confidence it expresses in its decisions must match its accuracy. To assess the degree of match, examples are typically binned by confidence an…
Streaming Object Detection for 3-D Point Clouds
Wei Han, Zhengdong Zhang, Benjamin Caine +7
Autonomous vehicles operate in a dynamic environment, where the speed with which a vehicle can perceive and react impacts the safety and efficacy of the system. LiDAR provides a pr…
Naive-Student: Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation
Liang-Chieh Chen, Raphael Gontijo Lopes, Bowen Cheng +5
Supervised learning in large discriminative models is a mainstay for modern computer vision. Such an approach necessitates investing in large-scale human-annotated datasets for ach…
Improving 3D Object Detection through Progressive Population Based Augmentation
Shuyang Cheng, Zhaoqi Leng, Ekin Dogus Cubuk +10
Data augmentation has been widely adopted for object detection in 3D point clouds. However, all previous related efforts have focused on manually designing specific data augmentati…
Revisiting Spatial Invariance with Low-Rank Local Connectivity
Gamaleldin F. Elsayed, Prajit Ramachandran, Jonathon Shlens +1
Convolutional neural networks are among the most successful architectures in deep learning with this success at least partially attributable to the efficacy of spatial invariance a…
Scalability in Perception for Autonomous Driving: Waymo Open Dataset
Pei Sun, Henrik Kretzschmar, Xerxes Dotiwalla +22
The research community has increasing interest in autonomous driving research, despite the resource intensity of obtaining representative real world data. Existing self-driving dat…
RandAugment: Practical automated data augmentation with a reduced search space
Ekin D. Cubuk, Barret Zoph, Jonathon Shlens +1
Recent work has shown that data augmentation has the potential to significantly improve the generalization of deep learning models. Recently, automated augmentation strategies have…
StarNet: Targeted Computation for Object Detection in Point Clouds
Jiquan Ngiam, Benjamin Caine, Wei Han +10
Detecting objects from LiDAR point clouds is an important component of self-driving car technology as LiDAR provides high resolution spatial information. Previous work on point-clo…
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…
Stand-Alone Self-Attention in Vision Models
Prajit Ramachandran, Niki Parmar, Ashish Vaswani +3
Convolutions are a fundamental building block of modern computer vision systems. Recent approaches have argued for going beyond convolutions in order to capture long-range dependen…
Visual Wake Words Dataset
Aakanksha Chowdhery, Pete Warden, Jonathon Shlens +2
The emergence of Internet of Things (IoT) applications requires intelligence on the edge. Microcontrollers provide a low-cost compute platform to deploy intelligent IoT application…