no code implementations • 25 May 2024 • Hong-Shuo Chen, Yao Zhu, Suya You, Azad M. Madni, C. -C. Jay Kuo
Remarkably, our models are trained without backpropagation and achieve the best performance with fewer than 20G Multiply-Accumulate Operations (MACs).
no code implementations • 10 Apr 2024 • Shijie Zhou, Zhiwen Fan, Dejia Xu, Haoran Chang, Pradyumna Chari, Tejas Bharadwaj, Suya You, Zhangyang Wang, Achuta Kadambi
This point cloud serves as the initial state for the centroids of 3D Gaussians.
no code implementations • 6 Dec 2023 • Shijie Zhou, Haoran Chang, Sicheng Jiang, Zhiwen Fan, Zehao Zhu, Dejia Xu, Pradyumna Chari, Suya You, Zhangyang Wang, Achuta Kadambi
In this work, we go one step further: in addition to radiance field rendering, we enable 3D Gaussian splatting on arbitrary-dimension semantic features via 2D foundation model distillation.
no code implementations • 5 Nov 2023 • Zifan Yu, Erfan Bank Tavakoli, Meida Chen, Suya You, Raghuveer Rao, Sanjeev Agarwal, Fengbo Ren
The area of Video Camouflaged Object Detection (VCOD) presents unique challenges in the field of computer vision due to texture similarities between target objects and their surroundings, as well as irregular motion patterns caused by both objects and camera movement.
1 code implementation • 16 Oct 2023 • Raphael Ruschel, A. S. M. Iftekhar, B. S. Manjunath, Suya You
The increasing complexity of modern deep neural network models and the expanding sizes of datasets necessitate the development of optimized and scalable training methods.
no code implementations • 8 Oct 2023 • Ganning Zhao, Wenhui Cui, Suya You, C. -C. Jay Kuo
Unsupervised image-to-image (I2I) translation learns cross-domain image mapping that transfers input from the source domain to output in the target domain while preserving its semantics.
no code implementations • 16 Sep 2023 • Zhiruo Zhou, Suya You, C. -C. Jay Kuo
The labeling cost and the huge computational complexity hinder their applications on edge devices.
1 code implementation • ICCV 2023 • Cody Simons, Dripta S. Raychaudhuri, Sk Miraj Ahmed, Suya You, Konstantinos Karydis, Amit K. Roy-Chowdhury
In this work, we relax both of these assumptions by addressing the problem of adapting a set of models trained independently on uni-modal data to a target domain consisting of unlabeled multi-modal data, without having access to the original source dataset.
no code implementations • 25 Apr 2023 • Ganning Zhao, Tingwei Shen, Suya You, C. -C. Jay Kuo
Ensuring the realism of computer-generated synthetic images is crucial to deep neural network (DNN) training.
no code implementations • 24 Apr 2023 • Tingwei Shen, Ganning Zhao, Suya You
Synthetic-to-real data translation using generative adversarial learning has achieved significant success in improving synthetic data.
no code implementations • 16 Feb 2023 • Zifan Yu, Meida Chen, Zhikang Zhang, Suya You, Raghuveer Rao, Sanjeev Agarwal, Fengbo Ren
Uncertain points are sampled from coarse semantic segmentation results of 2D image segmentation where uncertain points are located close to the object boundaries in the 2D range image representation and 3D spherical projection background points.
no code implementations • 16 Feb 2023 • Zifan Yu, Suya You, Fengbo Ren
Frequency-domain learning draws attention due to its superior tradeoff between inference accuracy and input data size.
no code implementations • 18 Jan 2023 • A S M Iftekhar, Raphael Ruschel, Satish Kumar, Suya You, B. S. Manjunath
Scene-graph generation involves creating a structural representation of the relationships between objects in a scene by predicting subject-object-relation triplets from input data.
no code implementations • CVPR 2023 • Zhen Wang, Shijie Zhou, Jeong Joon Park, Despoina Paschalidou, Suya You, Gordon Wetzstein, Leonidas Guibas, Achuta Kadambi
One school of thought is to encode a latent vector for each point (point latents).
no code implementations • 8 Nov 2022 • Ganning Zhao, Vasileios Magoulianitis, Suya You, C. -C. Jay Kuo
Despite prolific work on evaluating generative models, little research has been done on the quality evaluation of an individual generated sample.
no code implementations • 8 Nov 2022 • Zhikang Zhang, Zifan Yu, Suya You, Raghuveer Rao, Sanjeev Agarwal, Fengbo Ren
Motivated by the increasing application of low-resolution LiDAR recently, we target the problem of low-resolution LiDAR-camera calibration in this work.
no code implementations • 15 Jul 2022 • Zhiruo Zhou, Hongyu Fu, Suya You, C. -C. Jay Kuo
Supervised and unsupervised deep trackers that rely on deep learning technologies are popular in recent years.
1 code implementation • 22 Jun 2022 • Yunhao Ba, Howard Zhang, Ethan Yang, Akira Suzuki, Arnold Pfahnl, Chethan Chinder Chandrappa, Celso de Melo, Suya You, Stefano Soatto, Alex Wong, Achuta Kadambi
We propose a large-scale dataset of real-world rainy and clean image pairs and a method to remove degradations, induced by rain streaks and rain accumulation, from the image.
no code implementations • 30 Apr 2022 • Hong-Shuo Chen, Shuowen Hu, Suya You, C. -C. Jay Kuo
Second, for discriminant features selection, DefakeHop uses an unsupervised approach while DefakeHop++ adopts a more effective approach with supervision, called the Discriminant Feature Test (DFT).
no code implementations • 15 Nov 2021 • Zhiruo Zhou, Hongyu Fu, Suya You, C. -C. Jay Kuo
Based on the experimental results, we compare pros and cons of supervised and unsupervised trackers and provide a new perspective to understand the performance gap between supervised and unsupervised methods, which is the third contribution of this work.
no code implementations • 19 Oct 2021 • Hong-Shuo Chen, Kaitai Zhang, Shuowen Hu, Suya You, C. -C. Jay Kuo
A robust fake satellite image detection method, called Geo-DefakeHop, is proposed in this work.
no code implementations • 7 Oct 2021 • Vibashan VS, Domenick Poster, Suya You, Shuowen Hu, Vishal M. Patel
Though thermal cameras are widely used for military applications and increasingly for commercial applications, there is a lack of robust algorithms to robustly exploit the thermal imagery due to the limited availability of labeled thermal data.
no code implementations • 5 Oct 2021 • Zhiruo Zhou, Hongyu Fu, Suya You, Christoph C. Borel-Donohue, C. -C. Jay Kuo
An unsupervised online object tracking method that exploits both foreground and background correlations is proposed and named UHP-SOT (Unsupervised High-Performance Single Object Tracker) in this work.
1 code implementation • 2 Aug 2021 • A S M Iftekhar, Satish Kumar, R. Austin McEver, Suya You, B. S. Manjunath
For detecting HOI, it is important to utilize relative spatial configurations and object semantics to find salient spatial regions of images that highlight the interactions between human object pairs.
no code implementations • 31 Mar 2021 • Jiesi Hu, Ganning Zhao, Suya You, C. C. Jay Kuo
Our goal is to develop stable, accurate, and robust semantic scene understanding methods for wide-area scene perception and understanding, especially in challenging outdoor environments.
no code implementations • 27 Mar 2021 • Ganning Zhao, Jiesi Hu, Suya You, C. -C. Jay Kuo
Current perception systems often carry multimodal imagers and sensors such as 2D cameras and 3D LiDAR sensors.
1 code implementation • 11 Mar 2021 • Hong-Shuo Chen, Mozhdeh Rouhsedaghat, Hamza Ghani, Shuowen Hu, Suya You, C. -C. Jay Kuo
A light-weight high-performance Deepfake detection method, called DefakeHop, is proposed in this work.
no code implementations • 23 Nov 2020 • Mozhdeh Rouhsedaghat, Yifan Wang, Shuowen Hu, Suya You, C. -C. Jay Kuo
A non-parametric low-resolution face recognition model for resource-constrained environments with limited networking and computing is proposed in this work.
no code implementations • 15 Oct 2020 • Ruiyuan Lin, Suya You, Raghuveer Rao, C. -C. Jay Kuo
Through the construction, a one-to-one correspondence between the approximation of an MLP and that of a piecewise low-order polynomial is established.
no code implementations • 9 Sep 2020 • Ruiyuan Lin, Zhiruo Zhou, Suya You, Raghuveer Rao, C. -C. Jay Kuo
Besides input layer $l_{in}$ and output layer $l_{out}$, the MLP of interest consists of two intermediate layers, $l_1$ and $l_2$.
no code implementations • 18 Jul 2020 • Mozhdeh Rouhsedaghat, Yifan Wang, Xiou Ge, Shuowen Hu, Suya You, C. -C. Jay Kuo
For gray-scale face images of resolution $32 \times 32$ in the LFW and the CMU Multi-PIE datasets, FaceHop achieves correct gender classification rates of 94. 63% and 95. 12% with model sizes of 16. 9K and 17. 6K parameters, respectively.
no code implementations • 13 Feb 2020 • Zifan Yu, Suya You
In this report, we propose a two-dimensional CCA(canonical correlation analysis) framework to fuse monocular images and corresponding predicted depth images for basic computer vision tasks like image classification and object detection.
no code implementations • 8 Feb 2020 • Yueru Chen, Mozhdeh Rouhsedaghat, Suya You, Raghuveer Rao, C. -C. Jay Kuo
In PixelHop++, one can control the learning model size of fine-granularity, offering a flexible tradeoff between the model size and the classification performance.
1 code implementation • NeurIPS 2019 • Yiqi Zhong, Cho-Ying Wu, Suya You, Ulrich Neumann
Such a transformation enables CFCNet to predict features and reconstruct data of missing depth measurements according to their corresponding, transformed RGB features.
no code implementations • 25 Feb 2019 • Abinaya Manimaran, Thiyagarajan Ramanathan, Suya You, C-C Jay Kuo
In this work, we study the power of Saak features as an effort towards interpretable deep learning.
no code implementations • 7 Feb 2019 • Thiyagarajan Ramanathan, Abinaya Manimaran, Suya You, C-C Jay Kuo
This work investigates the robustness of Saak transform against adversarial attacks towards high performance image classification.
no code implementations • 23 Jan 2018 • Qiangui Huang, Kevin Zhou, Suya You, Ulrich Neumann
Specifically, we introduce a "try-and-learn" algorithm to train pruning agents that remove unnecessary CNN filters in a data-driven way.
1 code implementation • ICCV 2017 • Weiyue Wang, Qiangui Huang, Suya You, Chao Yang, Ulrich Neumann
The 3D-ED-GAN is a 3D convolutional neural network trained with a generative adversarial paradigm to fill missing 3D data in low-resolution.
no code implementations • 22 Nov 2016 • Qiangui Huang, Weiyue Wang, Kevin Zhou, Suya You, Ulrich Neumann
A novel neural network architecture is built for scene labeling tasks where one of the variants of the new RNN unit, Gated Recurrent Unit with Explicit Long-range Conditioning (GRU-ELC), is used to model multi scale contextual dependencies in images.