no code implementations • 3 Apr 2024 • Cheng Zhao, Su Sun, Ruoyu Wang, Yuliang Guo, Jun-Jun Wan, Zhou Huang, Xinyu Huang, Yingjie Victor Chen, Liu Ren
Most 3D Gaussian Splatting (3D-GS) based methods for urban scenes initialize 3D Gaussians directly with 3D LiDAR points, which not only underutilizes LiDAR data capabilities but also overlooks the potential advantages of fusing LiDAR with camera data.
no code implementations • 3 Apr 2024 • Su Sun, Cheng Zhao, Yuliang Guo, Ruoyu Wang, Xinyu Huang, Yingjie Victor Chen, Liu Ren
The 3D Inpainter with abstract representation at coarse levels is trained offline using various scenes to complete occluded surfaces.
1 code implementation • 29 Mar 2024 • Abhinav Kumar, Yuliang Guo, Xinyu Huang, Liu Ren, Xiaoming Liu
We argue that the cause of failure is the sensitivity of depth regression losses to noise of larger objects.
3D Object Detection 3D Object Detection From Monocular Images +3
no code implementations • 27 Mar 2024 • Xin Ye, Feng Tao, Abhirup Mallik, Burhaneddin Yaman, Liu Ren
Recently, large pretrained models have gained significant attention as zero-shot reward models for tasks specified with desired linguistic goals.
no code implementations • 23 Mar 2024 • Yuliang Guo, Abhinav Kumar, Cheng Zhao, Ruoyu Wang, Xinyu Huang, Liu Ren
Monocular 3D reconstruction for categorical objects heavily relies on accurately perceiving each object's pose.
no code implementations • 13 Mar 2024 • Chenbin Pan, Burhaneddin Yaman, Senem Velipasalar, Liu Ren
Autonomous driving stands as a pivotal domain in computer vision, shaping the future of transportation.
2 code implementations • 10 Mar 2024 • Thang Doan, Sima Behpour, Xin Li, Wenbin He, Liang Gou, Liu Ren
Few-shot Class-Incremental Learning (FSCIL) poses the challenge of retaining prior knowledge while learning from limited new data streams, all without overfitting.
no code implementations • 12 Jan 2024 • Xiwei Xuan, Jorge Piazentin Ono, Liang Gou, Kwan-Liu Ma, Liu Ren
Data slice-finding is an emerging technique for evaluating machine learning models.
no code implementations • 10 Jan 2024 • Chenbin Pan, Burhaneddin Yaman, Tommaso Nesti, Abhirup Mallik, Alessandro G Allievi, Senem Velipasalar, Liu Ren
Autonomous driving is a complex and challenging task that aims at safe motion planning through scene understanding and reasoning.
1 code implementation • NeurIPS 2023 • Yunhao Ge, Hong-Xing Yu, Cheng Zhao, Yuliang Guo, Xinyu Huang, Liu Ren, Laurent Itti, Jiajun Wu
A major challenge in monocular 3D object detection is the limited diversity and quantity of objects in real datasets.
no code implementations • 6 Nov 2023 • Jinbin Huang, Wenbin He, Liang Gou, Liu Ren, Chris Bryan
Deep learning models are widely used in critical applications, highlighting the need for pre-deployment model understanding and improvement.
no code implementations • 9 Aug 2023 • Shubhang Bhatnagar, Sharath Gopal, Narendra Ahuja, Liu Ren
We demonstrate the performance of our method on the LD-ConGR long-distance dataset where it outperforms previous state-of-the-art methods on recognition accuracy and compute efficiency.
2 code implementations • 25 Jun 2023 • Thang Doan, Xin Li, Sima Behpour, Wenbin He, Liang Gou, Liu Ren
We argue that this contextual information should already be embedded within the known classes.
no code implementations • 1 May 2023 • Wenbin He, Suphanut Jamonnak, Liang Gou, Liu Ren
To further improve the pixel embeddings and enable language-driven semantic segmentation, we design two types of consistency guided by vision-language models: 1) embedding consistency, aligning our pixel embeddings to the joint feature space of a pre-trained vision-language model, CLIP; and 2) semantic consistency, forcing our model to make the same predictions as CLIP over a set of carefully designed target classes with both known and unknown prototypes.
no code implementations • CVPR 2023 • Wenbin He, Suphanut Jamonnak, Liang Gou, Liu Ren
To further improve the pixel embeddings and enable language-driven semantic segmentation, we design two types of consistency guided by vision-language models: 1) embedding consistency, aligning our pixel embeddings to the joint feature space of a pre-trained vision-language model, CLIP; and 2) semantic consistency, forcing our model to make the same predictions as CLIP over a set of carefully designed target classes with both known and unknown prototypes.
no code implementations • 25 Mar 2022 • Wenbin He, William Surmeier, Arvind Kumar Shekar, Liang Gou, Liu Ren
In this work, we propose a self-supervised pixel representation learning method for semantic segmentation by using visual concepts (i. e., groups of pixels with semantic meanings, such as parts, objects, and scenes) extracted from images.
1 code implementation • CVPR 2022 • Yuyan Li, Yuliang Guo, Zhixin Yan, Xinyu Huang, Ye Duan, Liu Ren
In this paper, we propose a 360 monocular depth estimation pipeline, OmniFusion, to tackle the spherical distortion issue.
Ranked #6 on Depth Estimation on Stanford2D3D Panoramic
no code implementations • 18 Feb 2022 • Huan Song, Zeng Dai, Panpan Xu, Liu Ren
GraphQ provides a visual query interface with a query editor and a multi-scale visualization of the results, as well as a user feedback mechanism for refining the results with additional constraints.
no code implementations • 2 Feb 2022 • Yuyan Li, Zhixin Yan, Ye Duan, Liu Ren
In this paper, we propose a novel, model-agnostic, two-stage pipeline for omnidirectional monocular depth estimation.
Ranked #13 on Depth Estimation on Stanford2D3D Panoramic
no code implementations • 3 Jan 2022 • Arvind Kumar Shekar, Laureen Lake, Liang Gou, Liu Ren
It is on this space we estimate the novelty of the test samples.
no code implementations • 19 May 2021 • Sascha Hornauer, Ke Li, Stella X. Yu, Shabnam Ghaffarzadegan, Liu Ren
Recent progress in network-based audio event classification has shown the benefit of pre-training models on visual data such as ImageNet.
no code implementations • 1 Jan 2021 • Nanxiang Li, Shabnam Ghaffarzadegan, Liu Ren
We show both theoretically and experimentally, the VAE ensemble objective encourages the linear transformations connecting the VAEs to be trivial transformations, aligning the latent representations of different models to be "alike".
no code implementations • 27 Sep 2020 • Liang Gou, Lincan Zou, Nanxiang Li, Michael Hofmann, Arvind Kumar Shekar, Axel Wendt, Liu Ren
In this work, we propose a visual analytics system, VATLD, equipped with a disentangled representation learning and semantic adversarial learning, to assess, understand, and improve the accuracy and robustness of traffic light detectors in autonomous driving applications.
1 code implementation • 12 Jul 2020 • Bilal Alsallakh, Zhixin Yan, Shabnam Ghaffarzadegan, Zeng Dai, Liu Ren
We propose a measure to compute class similarity in large-scale classification based on prediction scores.
1 code implementation • 3 Jan 2020 • Shen Yan, Huan Song, Nanxiang Li, Lincan Zou, Liu Ren
Unsupervised domain adaptation studies the problem of utilizing a relevant source domain with abundant labels to build predictive modeling for an unannotated target domain.
Ranked #49 on Domain Generalization on PACS
no code implementations • ICLR 2020 • Nanxiang Li, Shabnam Ghaffarzadegan, Liu Ren
Recent advancements in unsupervised disentangled representation learning focus on extending the variational autoencoder (VAE) with an augmented objective function to balance the trade-off between disentanglement and reconstruction.
1 code implementation • 23 Nov 2019 • Kaiqiang Song, Bingqing Wang, Zhe Feng, Liu Ren, Fei Liu
In this paper, we present a neural summarization model that, by learning from single human abstracts, can produce a broad spectrum of summaries ranging from purely extractive to highly generative ones.
Ranked #12 on Text Summarization on GigaWord
2 code implementations • 23 Jul 2019 • Yao Ming, Panpan Xu, Huamin Qu, Liu Ren
The prediction is obtained by comparing the inputs to a few prototypes, which are exemplar cases in the problem domain.
no code implementations • 10 May 2019 • Takanori Fujiwara, Jia-Kai Chou, Shilpika, Panpan Xu, Liu Ren, Kwan-Liu Ma
We enhance an existing incremental PCA method in several ways to ensure its usability for visualizing streaming multidimensional data.
no code implementations • 17 Oct 2017 • Bilal Alsallakh, Amin Jourabloo, Mao Ye, Xiaoming Liu, Liu Ren
We present visual-analytics methods to reveal and analyze this hierarchy of similar classes in relation with CNN-internal data.
no code implementations • ICCV 2017 • Amin Jourabloo, Mao Ye, Xiaoming Liu, Liu Ren
Face alignment has witnessed substantial progress in the last decade.
Ranked #12 on Facial Landmark Detection on 300W