235 citations · 855 across the 36 of their papers we have counts for
39 papers
Towards Unified and Effective Domain Generalization
Yiyuan Zhang, Kaixiong Gong, Xiaohan Ding +4
We propose , a novel and fied framework for omain eneralization that is capable of significantly enhancing the out-of-distribu…
ImageBind-LLM: Multi-modality Instruction Tuning
Jiaming Han, Renrui Zhang, Wenqi Shao +14
We present ImageBind-LLM, a multi-modality instruction tuning method of large language models (LLMs) via ImageBind. Existing works mainly focus on language and image instruction tu…
Revisiting DETR Pre-training for Object Detection
Yan Ma, Weicong Liang, Bohan Chen +5
Motivated by the remarkable achievements of DETR-based approaches on COCO object detection and segmentation benchmarks, recent endeavors have been directed towards elevating their…
Meta-Transformer: A Unified Framework for Multimodal Learning
Yiyuan Zhang, Kaixiong Gong, Kaipeng Zhang +4
Multimodal learning aims to build models that can process and relate information from multiple modalities. Despite years of development in this field, it still remains challenging…
Space Engage: Collaborative Space Supervision for Contrastive-based Semi-Supervised Semantic Segmentation
Changqi Wang, Haoyu Xie, Yuhui Yuan +2
Semi-Supervised Semantic Segmentation (S4) aims to train a segmentation model with limited labeled images and a substantial volume of unlabeled images. To improve the robustness of…
3D Environment Modeling for Falsification and Beyond with Scenic 3.0
Eric Vin, Shun Kashiwa, Matthew Rhea +7
We present a major new version of Scenic, a probabilistic programming language for writing formal models of the environments of cyber-physical systems. Scenic has been successfully…
Beating Backdoor Attack at Its Own Game
Min Liu, Alberto Sangiovanni-Vincentelli, Xiangyu Yue
Deep neural networks (DNNs) are vulnerable to backdoor attack, which does not affect the network's performance on clean data but would manipulate the network behavior once a trigge…
LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model
Peng Gao, Jiaming Han, Renrui Zhang +9
How to efficiently transform large language models (LLMs) into instruction followers is recently a popular research direction, while training LLM for multi-modal reasoning remains…
Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models
Zangwei Zheng, Mingyuan Ma, Kai Wang +3
Continual learning (CL) can help pre-trained vision-language models efficiently adapt to new or under-trained data distributions without re-training. Nevertheless, during the conti…
Prompt Vision Transformer for Domain Generalization
Zangwei Zheng, Xiangyu Yue, Kai Wang +1
Though vision transformers (ViTs) have exhibited impressive ability for representation learning, we empirically find that they cannot generalize well to unseen domains with previou…
RankSeg: Adaptive Pixel Classification with Image Category Ranking for Segmentation
Haodi He, Yuhui Yuan, Xiangyu Yue +1
The segmentation task has traditionally been formulated as a complete-label pixel classification task to predict a class for each pixel from a fixed number of predefined semantic c…
3rd Place Solution for VisDA 2021 Challenge -- Universally Domain Adaptive Image Recognition
Haojin Liao, Xiaolin Song, Sicheng Zhao +7
The Visual Domain Adaptation (VisDA) 2021 Challenge calls for unsupervised domain adaptation (UDA) methods that can deal with both input distribution shift and label set variance b…
Multi-source Few-shot Domain Adaptation
Xiangyu Yue, Zangwei Zheng, Colorado Reed +3
Multi-source Domain Adaptation (MDA) aims to transfer predictive models from multiple, fully-labeled source domains to an unlabeled target domain. However, in many applications, re…
Conditional Synthetic Data Generation for Robust Machine Learning Applications with Limited Pandemic Data
Hari Prasanna Das, Ryan Tran, Japjot Singh +4
At the onset of a pandemic, such as COVID-19, data with proper labeling/attributes corresponding to the new disease might be unavailable or sparse. Machine L…
Scene-aware Learning Network for Radar Object Detection
Zangwei Zheng, Xiangyu Yue, Kurt Keutzer +1
Object detection is essential to safe autonomous or assisted driving. Previous works usually utilize RGB images or LiDAR point clouds to identify and localize multiple objects in s…
Image2Point: 3D Point-Cloud Understanding with 2D Image Pretrained Models
Chenfeng Xu, Shijia Yang, Tomer Galanti +7
3D point-clouds and 2D images are different visual representations of the physical world. While human vision can understand both representations, computer vision models designed fo…
Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation
Xiangyu Yue, Zangwei Zheng, Shanghang Zhang +4
Unsupervised Domain Adaptation (UDA) transfers predictive models from a fully-labeled source domain to an unlabeled target domain. In some applications, however, it is expensive ev…
Self-Supervised Pretraining Improves Self-Supervised Pretraining
Colorado J. Reed, Xiangyu Yue, Ani Nrusimha +9
While self-supervised pretraining has proven beneficial for many computer vision tasks, it requires expensive and lengthy computation, large amounts of data, and is sensitive to da…
A Customizable Dynamic Scenario Modeling and Data Generation Platform for Autonomous Driving
Jay Shenoy, Edward Kim, Xiangyu Yue +4
Safely interacting with humans is a significant challenge for autonomous driving. The performance of this interaction depends on machine learning-based modules of an autopilot, suc…
Emotional Semantics-Preserved and Feature-Aligned CycleGAN for Visual Emotion Adaptation
Sicheng Zhao, Xuanbai Chen, Xiangyu Yue +7
Thanks to large-scale labeled training data, deep neural networks (DNNs) have obtained remarkable success in many vision and multimedia tasks. However, because of the presence of d…
Curriculum CycleGAN for Textual Sentiment Domain Adaptation with Multiple Sources
Sicheng Zhao, Yang Xiao, Jiang Guo +5
Sentiment analysis of user-generated reviews or comments on products and services in social networks can help enterprises to analyze the feedback from customers and take correspond…
Scenic: A Language for Scenario Specification and Data Generation
Daniel J. Fremont, Edward Kim, Tommaso Dreossi +4
We propose a new probabilistic programming language for the design and analysis of cyber-physical systems, especially those based on machine learning. Specifically, we consider the…
Unsupervised Point Cloud Pre-Training via Occlusion Completion
Hanchen Wang, Qi Liu, Xiangyu Yue +2
We describe a simple pre-training approach for point clouds. It works in three steps: 1. Mask all points occluded in a camera view; 2. Learn an encoder-decoder model to reconstruct…
A Review of Single-Source Deep Unsupervised Visual Domain Adaptation
Sicheng Zhao, Xiangyu Yue, Shanghang Zhang +8
Large-scale labeled training datasets have enabled deep neural networks to excel across a wide range of benchmark vision tasks. However, in many applications, it is prohibitively e…