461 citations · 1.3k across the 28 of their papers we have counts for
34 papers
Unsupervised Domain Adaptation for Self-Driving from Past Traversal Features
Travis Zhang, Katie Luo, Cheng Perng Phoo +5
The rapid development of 3D object detection systems for self-driving cars has significantly improved accuracy. However, these systems struggle to generalize across diverse driving…
Doppelgangers: Learning to Disambiguate Images of Similar Structures
Ruojin Cai, Joseph Tung, Qianqian Wang +3
We consider the visual disambiguation task of determining whether a pair of visually similar images depict the same or distinct 3D surfaces (e.g., the same or opposite sides of a s…
RealFill: Reference-Driven Generation for Authentic Image Completion
Luming Tang, Nataniel Ruiz, Qinghao Chu +8
Recent advances in generative imagery have brought forth outpainting and inpainting models that can produce high-quality, plausible image content in unknown regions. However, the c…
Tracking Everything Everywhere All at Once
Qianqian Wang, Yen-Yu Chang, Ruojin Cai +4
We present a new test-time optimization method for estimating dense and long-range motion from a video sequence. Prior optical flow or particle video tracking algorithms typically…
Emergent Correspondence from Image Diffusion
Luming Tang, Menglin Jia, Qianqian Wang +2
Finding correspondences between images is a fundamental problem in computer vision. In this paper, we show that correspondence emerges in image diffusion models without any explici…
Distilling from Similar Tasks for Transfer Learning on a Budget
Kenneth Borup, Cheng Perng Phoo, Bharath Hariharan
We address the challenge of getting efficient yet accurate recognition systems with limited labels. While recognition models improve with model size and amount of data, many specia…
Unsupervised Adaptation from Repeated Traversals for Autonomous Driving
Yurong You, Cheng Perng Phoo, Katie Z Luo +5
For a self-driving car to operate reliably, its perceptual system must generalize to the end-user's environment -- ideally without additional annotation efforts. One potential solu…
Image-to-Image Translation for Autonomous Driving from Coarsely-Aligned Image Pairs
Youya Xia, Josephine Monica, Wei-Lun Chao +3
A self-driving car must be able to reliably handle adverse weather conditions (e.g., snowy) to operate safely. In this paper, we investigate the idea of turning sensor inputs (i.e.…
Ithaca365: Dataset and Driving Perception under Repeated and Challenging Weather Conditions
Carlos A. Diaz-Ruiz, Youya Xia, Yurong You +11
Advances in perception for self-driving cars have accelerated in recent years due to the availability of large-scale datasets, typically collected at specific locations and under n…
Diagnosing and Remedying Shot Sensitivity with Cosine Few-Shot Learners
Davis Wertheimer, Luming Tang, Bharath Hariharan
Few-shot recognition involves training an image classifier to distinguish novel concepts at test time using few examples (shot). Existing approaches generally assume that the shot…
Learning to Detect Mobile Objects from LiDAR Scans Without Labels
Yurong You, Katie Z Luo, Cheng Perng Phoo +5
Current 3D object detectors for autonomous driving are almost entirely trained on human-annotated data. Although of high quality, the generation of such data is laborious and costl…
Hindsight is 20/20: Leveraging Past Traversals to Aid 3D Perception
Yurong You, Katie Z Luo, Xiangyu Chen +6
Self-driving cars must detect vehicles, pedestrians, and other traffic participants accurately to operate safely. Small, far-away, or highly occluded objects are particularly chall…
Unsupervised Semantic Segmentation by Distilling Feature Correspondences
Mark Hamilton, Zhoutong Zhang, Bharath Hariharan +2
Unsupervised semantic segmentation aims to discover and localize semantically meaningful categories within image corpora without any form of annotation. To solve this task, algorit…
Visual Prompt Tuning
Menglin Jia, Luming Tang, Bor-Chun Chen +4
The current modus operandi in adapting pre-trained models involves updating all the backbone parameters, ie, full fine-tuning. This paper introduces Visual Prompt Tuning (VPT) as a…
Orientation-Discriminative Feature Representation for Decentralized Pedestrian Tracking
Vikram Shree, Carlos Diaz-Ruiz, Chang Liu +2
This paper focuses on the problem of decentralized pedestrian tracking using a sensor network. Traditional works on pedestrian tracking usually use a centralized framework, which b…
Field-Guide-Inspired Zero-Shot Learning
Utkarsh Mall, Bharath Hariharan, Kavita Bala
Modern recognition systems require large amounts of supervision to achieve accuracy. Adapting to new domains requires significant data from experts, which is onerous and can become…
Extreme Rotation Estimation using Dense Correlation Volumes
Ruojin Cai, Bharath Hariharan, Noah Snavely +1
We present a technique for estimating the relative 3D rotation of an RGB image pair in an extreme setting, where the images have little or no overlap. We observe that, even when im…
PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows
Guandao Yang, Xun Huang, Zekun Hao +3
As 3D point clouds become the representation of choice for multiple vision and graphics applications, the ability to synthesize or reconstruct high-resolution, high-fidelity point…
Few-Shot Learning with Localization in Realistic Settings
Davis Wertheimer, Bharath Hariharan
Traditional recognition methods typically require large, artificially-balanced training classes, while few-shot learning methods are tested on artificially small ones. In contrast…
Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving
Yan Wang, Wei-Lun Chao, Divyansh Garg +3
3D object detection is an essential task in autonomous driving. Recent techniques excel with highly accurate detection rates, provided the 3D input data is obtained from precise bu…
A Deep-Learning-Based Fashion Attributes Detection Model
Menglin Jia, Yichen Zhou, Mengyun Shi +1
Analyzing fashion attributes is essential in the fashion design process. Current fashion forecasting firms, such as WGSN utilizes information from all around the world (from fashio…
Deep Fundamental Matrix Estimation without Correspondences
Omid Poursaeed, Guandao Yang, Aditya Prakash +4
Estimating fundamental matrices is a classic problem in computer vision. Traditional methods rely heavily on the correctness of estimated key-point correspondences, which can be no…
Resource Aware Person Re-identification across Multiple Resolutions
Yan Wang, Lequn Wang, Yurong You +6
Not all people are equally easy to identify: color statistics might be enough for some cases while others might require careful reasoning about high- and low-level details. However…
Low-Shot Learning from Imaginary Data
Yu-Xiong Wang, Ross Girshick, Martial Hebert +1
Humans can quickly learn new visual concepts, perhaps because they can easily visualize or imagine what novel objects look like from different views. Incorporating this ability to…