913 citations · 3.2k across the 60 of their papers we have counts for
61 papers
FB-BEV: BEV Representation from Forward-Backward View Transformations
Zhiqi Li, Zhiding Yu, Wenhai Wang +3
View Transformation Module (VTM), where transformations happen between multi-view image features and Bird-Eye-View (BEV) representation, is a crucial step in camera-based BEV perce…
FocalFormer3D : Focusing on Hard Instance for 3D Object Detection
Yilun Chen, Zhiding Yu, Yukang Chen +4
False negatives (FN) in 3D object detection, {\em e.g.}, missing predictions of pedestrians, vehicles, or other obstacles, can lead to potentially dangerous situations in autonomou…
FB-OCC: 3D Occupancy Prediction based on Forward-Backward View Transformation
Zhiqi Li, Zhiding Yu, David Austin +4
This technical report summarizes the winning solution for the 3D Occupancy Prediction Challenge, which is held in conjunction with the CVPR 2023 Workshop on End-to-End Autonomous D…
Differentially Private Video Activity Recognition
Zelun Luo, Yuliang Zou, Yijin Yang +6
In recent years, differential privacy has seen significant advancements in image classification; however, its application to video activity recognition remains under-explored. This…
Real-Time Radiance Fields for Single-Image Portrait View Synthesis
Alex Trevithick, Matthew Chan, Michael Stengel +7
We present a one-shot method to infer and render a photorealistic 3D representation from a single unposed image (e.g., face portrait) in real-time. Given a single RGB input, our im…
VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion
Yiming Li, Zhiding Yu, Christopher Choy +5
Humans can easily imagine the complete 3D geometry of occluded objects and scenes. This appealing ability is vital for recognition and understanding. To enable such capability in A…
Prismer: A Vision-Language Model with Multi-Task Experts
Shikun Liu, Linxi Fan, Edward Johns +3
Recent vision-language models have shown impressive multi-modal generation capabilities. However, typically they require training huge models on massive datasets. As a more scalabl…
Re-ViLM: Retrieval-Augmented Visual Language Model for Zero and Few-Shot Image Captioning
Zhuolin Yang, Wei Ping, Zihan Liu +13
Augmenting pretrained language models (LMs) with a vision encoder (e.g., Flamingo) has obtained the state-of-the-art results in image-to-text generation. However, these models stor…
Vision Transformers Are Good Mask Auto-Labelers
Shiyi Lan, Xitong Yang, Zhiding Yu +3
We propose Mask Auto-Labeler (MAL), a high-quality Transformer-based mask auto-labeling framework for instance segmentation using only box annotations. MAL takes box-cropped images…
1st Place Solution of The Robust Vision Challenge 2022 Semantic Segmentation Track
Junfei Xiao, Zhichao Xu, Shiyi Lan +3
This report describes the winning solution to the Robust Vision Challenge (RVC) semantic segmentation track at ECCV 2022. Our method adopts the FAN-B-Hybrid model as the encoder an…
Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models
Manli Shu, Weili Nie, De-An Huang +4
Pre-trained vision-language models (e.g., CLIP) have shown promising zero-shot generalization in many downstream tasks with properly designed text prompts. Instead of relying on ha…
PointDP: Diffusion-driven Purification against Adversarial Attacks on 3D Point Cloud Recognition
Jiachen Sun, Weili Nie, Zhiding Yu +2
3D Point cloud is becoming a critical data representation in many real-world applications like autonomous driving, robotics, and medical imaging. Although the success of deep learn…
MinVIS: A Minimal Video Instance Segmentation Framework without Video-based Training
De-An Huang, Zhiding Yu, Anima Anandkumar
We propose MinVIS, a minimal video instance segmentation (VIS) framework that achieves state-of-the-art VIS performance with neither video-based architectures nor training procedur…
How Much More Data Do I Need? Estimating Requirements for Downstream Tasks
Rafid Mahmood, James Lucas, David Acuna +6
Given a small training data set and a learning algorithm, how much more data is necessary to reach a target validation or test performance? This question is of critical importance…
Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for Human-Object Interactions
Huaizu Jiang, Xiaojian Ma, Weili Nie +4
A significant gap remains between today's visual pattern recognition models and human-level visual cognition especially when it comes to few-shot learning and compositional reasoni…
MBEV: Multi-Camera Joint 3D Detection and Segmentation with Unified Birds-Eye View Representation
Enze Xie, Zhiding Yu, Daquan Zhou +5
In this paper, we propose MBEV, a unified framework that jointly performs 3D object detection and map segmentation in the Birds Eye View~(BEV) space with multi-camera image inp…
Understanding The Robustness in Vision Transformers
Daquan Zhou, Zhiding Yu, Enze Xie +4
Recent studies show that Vision Transformers(ViTs) exhibit strong robustness against various corruptions. Although this property is partly attributed to the self-attention mechanis…
RelViT: Concept-guided Vision Transformer for Visual Relational Reasoning
Xiaojian Ma, Weili Nie, Zhiding Yu +5
Reasoning about visual relationships is central to how humans interpret the visual world. This task remains challenging for current deep learning algorithms since it requires addre…
CoordGAN: Self-Supervised Dense Correspondences Emerge from GANs
Jiteng Mu, Shalini De Mello, Zhiding Yu +4
Recent advances show that Generative Adversarial Networks (GANs) can synthesize images with smooth variations along semantically meaningful latent directions, such as pose, express…
FreeSOLO: Learning to Segment Objects without Annotations
Xinlong Wang, Zhiding Yu, Shalini De Mello +4
Instance segmentation is a fundamental vision task that aims to recognize and segment each object in an image. However, it requires costly annotations such as bounding boxes and se…
Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptions
Jiachen Sun, Qingzhao Zhang, Bhavya Kailkhura +3
Deep neural networks on 3D point cloud data have been widely used in the real world, especially in safety-critical applications. However, their robustness against corruptions is le…
AugMax: Adversarial Composition of Random Augmentations for Robust Training
Haotao Wang, Chaowei Xiao, Jean Kossaifi +3
Data augmentation is a simple yet effective way to improve the robustness of deep neural networks (DNNs). Diversity and hardness are two complementary dimensions of data augmentati…
Learning Contrastive Representation for Semantic Correspondence
Taihong Xiao, Sifei Liu, Shalini De Mello +3
Dense correspondence across semantically related images has been extensively studied, but still faces two challenges: 1) large variations in appearance, scale and pose exist even f…
Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformers
Zhiqi Li, Wenhai Wang, Enze Xie +5
Panoptic segmentation involves a combination of joint semantic segmentation and instance segmentation, where image contents are divided into two types: things and stuff. We present…