66 citations · 247 across the 40 of their papers we have counts for
37 papers · 1 filter
Aligning Large Multimodal Models with Factually Augmented RLHF
Zhiqing Sun, Sheng Shen, Shengcao Cao +9
Large Multimodal Models (LMM) are built across modalities and the misalignment between two modalities can result in "hallucination", generating textual outputs that are not grounde…
Learning Lightweight Object Detectors via Multi-Teacher Progressive Distillation
Shengcao Cao, Mengtian Li, James Hays +3
Resource-constrained perception systems such as edge computing and vision-for-robotics require vision models to be both accurate and lightweight in computation and memory usage. Wh…
An Empirical Analysis of Range for 3D Object Detection
Neehar Peri, Mengtian Li, Benjamin Wilson +3
LiDAR-based 3D detection plays a vital role in autonomous navigation. Surprisingly, although autonomous vehicles (AVs) must detect both near-field objects (for collision avoidance)…
Revisiting Deformable Convolution for Depth Completion
Xinglong Sun, Jean Ponce, Yu-Xiong Wang
Depth completion, which aims to generate high-quality dense depth maps from sparse depth maps, has attracted increasing attention in recent years. Previous work usually employs RGB…
Generalized Open-World Semi-Supervised Object Detection
Garvita Allabadi, Ana Lucic, Siddarth Aananth +3
Traditional semi-supervised object detection methods assume a fixed set of object classes (in-distribution or ID classes) during training and deployment, which limits performance i…
Stochastic Multi-Person 3D Motion Forecasting
Sirui Xu, Yu-Xiong Wang, Liang-Yan Gui
This paper aims to deal with the ignored real-world complexities in prior work on human motion forecasting, emphasizing the social properties of multi-person motion, the diversity…
NeuralEditor: Editing Neural Radiance Fields via Manipulating Point Clouds
Jun-Kun Chen, Jipeng Lyu, Yu-Xiong Wang
This paper proposes NeuralEditor that enables neural radiance fields (NeRFs) natively editable for general shape editing tasks. Despite their impressive results on novel-view synth…
Contrastive Mean Teacher for Domain Adaptive Object Detectors
Shengcao Cao, Dhiraj Joshi, Liang-Yan Gui +1
Object detectors often suffer from the domain gap between training (source domain) and real-world applications (target domain). Mean-teacher self-training is a powerful paradigm in…
DualCross: Cross-Modality Cross-Domain Adaptation for Monocular BEV Perception
Yunze Man, Liang-Yan Gui, Yu-Xiong Wang
Closing the domain gap between training and deployment and incorporating multiple sensor modalities are two challenging yet critical topics for self-driving. Existing work only foc…
Standing Between Past and Future: Spatio-Temporal Modeling for Multi-Camera 3D Multi-Object Tracking
Ziqi Pang, Jie Li, Pavel Tokmakov +3
This work proposes an end-to-end multi-camera 3D multi-object tracking (MOT) framework. It emphasizes spatio-temporal continuity and integrates both past and future reasoning for t…
Object Discovery from Motion-Guided Tokens
Zhipeng Bao, Pavel Tokmakov, Yu-Xiong Wang +2
Object discovery -- separating objects from the background without manual labels -- is a fundamental open challenge in computer vision. Previous methods struggle to go beyond clust…
Diverse Human Motion Prediction Guided by Multi-Level Spatial-Temporal Anchors
Sirui Xu, Yu-Xiong Wang, Liang-Yan Gui
Predicting diverse human motions given a sequence of historical poses has received increasing attention. Despite rapid progress, existing work captures the multi-modal nature of hu…
Do Pre-trained Models Benefit Equally in Continual Learning?
Kuan-Ying Lee, Yuanyi Zhong, Yu-Xiong Wang
Existing work on continual learning (CL) is primarily devoted to developing algorithms for models trained from scratch. Despite their encouraging performance on contrived benchmark…
Continual Learning with Evolving Class Ontologies
Zhiqiu Lin, Deepak Pathak, Yu-Xiong Wang +2
Lifelong learners must recognize concept vocabularies that evolve over time. A common yet underexplored scenario is learning with class labels that continually refine/expand old cl…
PointTree: Transformation-Robust Point Cloud Encoder with Relaxed K-D Trees
Jun-Kun Chen, Yu-Xiong Wang
Being able to learn an effective semantic representation directly on raw point clouds has become a central topic in 3D understanding. Despite rapid progress, state-of-the-art encod…
Is Self-Supervised Learning More Robust Than Supervised Learning?
Yuanyi Zhong, Haoran Tang, Junkun Chen +2
Self-supervised contrastive learning is a powerful tool to learn visual representation without labels. Prior work has primarily focused on evaluating the recognition accuracy of va…
Beyond RGB: Scene-Property Synthesis with Neural Radiance Fields
Mingtong Zhang, Shuhong Zheng, Zhipeng Bao +2
Comprehensive 3D scene understanding, both geometrically and semantically, is important for real-world applications such as robot perception. Most of the existing work has focused…
Long-Tailed Recognition via Weight Balancing
Shaden Alshammari, Yu-Xiong Wang, Deva Ramanan +1
In the real open world, data tends to follow long-tailed class distributions, motivating the well-studied long-tailed recognition (LTR) problem. Naive training produces models that…
Discovering Objects that Can Move
Zhipeng Bao, Pavel Tokmakov, Allan Jabri +3
This paper studies the problem of object discovery -- separating objects from the background without manual labels. Existing approaches utilize appearance cues, such as color, text…
Embracing Single Stride 3D Object Detector with Sparse Transformer
Lue Fan, Ziqi Pang, Tianyuan Zhang +5
In LiDAR-based 3D object detection for autonomous driving, the ratio of the object size to input scene size is significantly smaller compared to 2D detection cases. Overlooking thi…
On the Importance of Firth Bias Reduction in Few-Shot Classification
Saba Ghaffari, Ehsan Saleh, David Forsyth +1
Learning accurate classifiers for novel categories from very few examples, known as few-shot image classification, is a challenging task in statistical machine learning and compute…
On the Importance of Distractors for Few-Shot Classification
Rajshekhar Das, Yu-Xiong Wang, JoséM. F. Moura
Few-shot classification aims at classifying categories of a novel task by learning from just a few (typically, 1 to 5) labelled examples. An effective approach to few-shot classifi…
Pixel Contrastive-Consistent Semi-Supervised Semantic Segmentation
Yuanyi Zhong, Bodi Yuan, Hong Wu +3
We present a novel semi-supervised semantic segmentation method which jointly achieves two desiderata of segmentation model regularities: the label-space consistency property betwe…
Generative Modeling for Multi-task Visual Learning
Zhipeng Bao, Martial Hebert, Yu-Xiong Wang
Generative modeling has recently shown great promise in computer vision, but it has mostly focused on synthesizing visually realistic images. In this paper, motivated by multi-task…