6.5k citations · 10.4k across the 118 of their papers we have counts for
68 papers · 1 filter
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…
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…
QD-BEV : Quantization-aware View-guided Distillation for Multi-view 3D Object Detection
Yifan Zhang, Zhen Dong, Huanrui Yang +6
Multi-view 3D detection based on BEV (bird-eye-view) has recently achieved significant improvements. However, the huge memory consumption of state-of-the-art models makes it hard t…
NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detection
Chenfeng Xu, Bichen Wu, Ji Hou +8
We present NeRF-Det, a novel method for indoor 3D detection with posed RGB images as input. Unlike existing indoor 3D detection methods that struggle to model scene geometry, our m…
Open-Vocabulary Point-Cloud Object Detection without 3D Annotation
Yuheng Lu, Chenfeng Xu, Xiaobao Wei +4
The goal of open-vocabulary detection is to identify novel objects based on arbitrary textual descriptions. In this paper, we address open-vocabulary 3D point-cloud detection by a…
SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object Detection
Yichen Xie, Chenfeng Xu, Marie-Julie Rakotosaona +5
By identifying four important components of existing LiDAR-camera 3D object detection methods (LiDAR and camera candidates, transformation, and fusion outputs), we observe that all…
Quadric Representations for LiDAR Odometry, Mapping and Localization
Chao Xia, Chenfeng Xu, Patrick Rim +5
Current LiDAR odometry, mapping and localization methods leverage point-wise representations of 3D scenes and achieve high accuracy in autonomous driving tasks. However, the space-…
Scaling Vision-Language Models with Sparse Mixture of Experts
Sheng Shen, Zhewei Yao, Chunyuan Li +3
The field of natural language processing (NLP) has made significant strides in recent years, particularly in the development of large-scale vision-language models (VLMs). These mod…
Multitask Vision-Language Prompt Tuning
Sheng Shen, Shijia Yang, Tianjun Zhang +4
Prompt Tuning, conditioning on task-specific learned prompt vectors, has emerged as a data-efficient and parameter-efficient method for adapting large pretrained vision-language mo…
CSQ: Growing Mixed-Precision Quantization Scheme with Bi-level Continuous Sparsification
Lirui Xiao, Huanrui Yang, Zhen Dong +3
Mixed-precision quantization has been widely applied on deep neural networks (DNNs) as it leads to significantly better efficiency-accuracy tradeoffs compared to uniform quantizati…
NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers
Yijiang Liu, Huanrui Yang, Zhen Dong +3
The complicated architecture and high training cost of vision transformers urge the exploration of post-training quantization. However, the heavy-tailed distribution of vision tran…
Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detection
Jinhyung Park, Chenfeng Xu, Shijia Yang +4
While recent camera-only 3D detection methods leverage multiple timesteps, the limited history they use significantly hampers the extent to which temporal fusion can improve object…
Analysis of Quantization on MLP-based Vision Models
Lingran Zhao, Zhen Dong, Kurt Keutzer
Quantization is wildly taken as a model compression technique, which obtains efficient models by converting floating-point weights and activations in the neural network into lower-…
Prior Knowledge-Guided Attention in Self-Supervised Vision Transformers
Kevin Miao, Akash Gokul, Raghav Singh +5
Recent trends in self-supervised representation learning have focused on removing inductive biases from training pipelines. However, inductive biases can be useful in settings when…
Open-Vocabulary 3D Detection via Image-level Class and Debiased Cross-modal Contrastive Learning
Yuheng Lu, Chenfeng Xu, Xiaobao Wei +4
Current point-cloud detection methods have difficulty detecting the open-vocabulary objects in the real world, due to their limited generalization capability. Moreover, it is extre…
The ArtBench Dataset: Benchmarking Generative Models with Artworks
Peiyuan Liao, Xiuyu Li, Xihui Liu +1
We introduce ArtBench-10, the first class-balanced, high-quality, cleanly annotated, and standardized dataset for benchmarking artwork generation. It comprises 60,000 images of art…
UnrealNAS: Can We Search Neural Architectures with Unreal Data?
Zhen Dong, Kaicheng Zhou, Guohao Li +5
Neural architecture search (NAS) has shown great success in the automatic design of deep neural networks (DNNs). However, the best way to use data to search network architectures i…
MTTrans: Cross-Domain Object Detection with Mean-Teacher Transformer
Jinze Yu, Jiaming Liu, Xiaobao Wei +7
Recently, DEtection TRansformer (DETR), an end-to-end object detection pipeline, has achieved promising performance. However, it requires large-scale labeled data and suffers from…
PreTraM: Self-Supervised Pre-training via Connecting Trajectory and Map
Chenfeng Xu, Tian Li, Chen Tang +5
Deep learning has recently achieved significant progress in trajectory forecasting. However, the scarcity of trajectory data inhibits the data-hungry deep-learning models from lear…
K-LITE: Learning Transferable Visual Models with External Knowledge
Sheng Shen, Chunyuan Li, Xiaowei Hu +11
The new generation of state-of-the-art computer vision systems are trained from natural language supervision, ranging from simple object category names to descriptive captions. Thi…
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…
How Much Can CLIP Benefit Vision-and-Language Tasks?
Sheng Shen, Liunian Harold Li, Hao Tan +5
Most existing Vision-and-Language (V&L) models rely on pre-trained visual encoders, using a relatively small set of manually-annotated data (as compared to web-crawled data), to pe…
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…
Affective Image Content Analysis: Two Decades Review and New Perspectives
Sicheng Zhao, Xingxu Yao, Jufeng Yang +5
Images can convey rich semantics and induce various emotions in viewers. Recently, with the rapid advancement of emotional intelligence and the explosive growth of visual data, ext…