1 code implementation • ECCV 2020 • Chung-Sheng Lai, Zunzhi You, Ching-Chun Huang, Yi-Hsuan Tsai, Wei-Chen Chiu
Vision perception is one of the most important components for a computer or robot to understand the surrounding scene and achieve autonomous applications.
no code implementations • 15 Apr 2024 • Tsung-Han Chou, Brian Wang, Wei-Chen Chiu, Jun-Cheng Chen
Class agnostic counting (CAC) is a vision task that can be used to count the total occurrence number of any given reference objects in the query image.
no code implementations • 13 Apr 2024 • Bor-Shiun Wang, Chien-Yi Wang, Wei-Chen Chiu
Addressing this gap, we introduce the Multi-Level Concept Prototypes Classifier (MCPNet), an inherently interpretable model.
no code implementations • 12 Mar 2024 • Hsin-Ju Lin, Tsu-Chun Chung, Ching-Chun Hsiao, Pin-Yu Chen, Wei-Chen Chiu, Ching-Chun Huang
Text detection is frequently used in vision-based mobile robots when they need to interpret texts in their surroundings to perform a given task.
1 code implementation • 20 Feb 2024 • Bo-Yu Cheng, Wei-Chen Chiu, Yu-Lun Liu
In this paper, we propose an algorithm that allows joint refinement of camera pose and scene geometry represented by decomposed low-rank tensor, using only 2D images as supervision.
1 code implementation • 26 Oct 2023 • You-Ming Chang, Chen Yeh, Wei-Chen Chiu, Ning Yu
We formulate deepfake detection as a visual question answering problem, and tune soft prompts for InstructBLIP to distinguish a query image is real or fake.
no code implementations • 3 Oct 2023 • Sheng-Chi Huang, Wei-Chen Chiu
Lastly, as the optical flow maps under different geometric augmentations actually exhibit distinct characteristics, an auxiliary classifier which trains to identify the type of augmentation from the appearance of the flow map is utilized to further enhance the learning of the optical flow estimator.
no code implementations • 22 Sep 2023 • Chia-Hao Kao, Yi-Hsin Chen, Cheng Chien, Wei-Chen Chiu, Wen-Hsiao Peng
This paper presents a Transformer-based image compression system that allows for a variable image quality objective according to the user's preference.
no code implementations • 22 Sep 2023 • Zhi-Yi Chin, Chieh-Ming Jiang, Ching-Chun Huang, Pin-Yu Chen, Wei-Chen Chiu
While image data starts to enjoy the simple-but-effective self-supervised learning scheme built upon masking and self-reconstruction objective thanks to the introduction of tokenization procedure and vision transformer backbone, convolutional neural networks as another important and widely-adopted architecture for image data, though having contrastive-learning techniques to drive the self-supervised learning, still face the difficulty of leveraging such straightforward and general masking operation to benefit their learning process significantly.
1 code implementation • 12 Sep 2023 • Zhi-Yi Chin, Chieh-Ming Jiang, Ching-Chun Huang, Pin-Yu Chen, Wei-Chen Chiu
In this work, we propose Prompting4Debugging (P4D) as a debugging and red-teaming tool that automatically finds problematic prompts for diffusion models to test the reliability of a deployed safety mechanism.
1 code implementation • ICCV 2023 • Yi-Hsin Chen, Ying-Chieh Weng, Chia-Hao Kao, Cheng Chien, Wei-Chen Chiu, Wen-Hsiao Peng
This work aims for transferring a Transformer-based image compression codec from human perception to machine perception without fine-tuning the codec.
1 code implementation • 18 May 2023 • Chia-Hao Kao, Ying-Chieh Weng, Yi-Hsin Chen, Wei-Chen Chiu, Wen-Hsiao Peng
Our prompt generation networks generate content-adaptive tokens according to the input image, an ROI mask, and a rate parameter.
1 code implementation • CVPR 2023 • Yi-Lun Lee, Yi-Hsuan Tsai, Wei-Chen Chiu, Chen-Yu Lee
In this paper, we tackle two challenges in multimodal learning for visual recognition: 1) when missing-modality occurs either during training or testing in real-world situations; and 2) when the computation resources are not available to finetune on heavy transformer models.
no code implementations • 10 Nov 2022 • Sheng-Feng Yu, Wei-Chen Chiu
Online continual learning (OCL) aims to enable model learning from a non-stationary data stream to continuously acquire new knowledge as well as retain the learnt one, under the constraints of having limited system size and computational cost, in which the main challenge comes from the "catastrophic forgetting" issue -- the inability to well remember the learnt knowledge while learning the new ones.
1 code implementation • 19 Sep 2022 • Yu-Ting Yen, Chia-Ni Lu, Wei-Chen Chiu, Yi-Hsuan Tsai
In this paper, we develop a domain adaptation framework via generating reliable pseudo ground truths of depth from real data to provide direct supervisions.
1 code implementation • 7 Sep 2022 • Fu-En Wang, Yu-Hsuan Yeh, Yi-Hsuan Tsai, Wei-Chen Chiu, Min Sun
Thus, state-of-the-art frameworks for monocular 360 depth estimation such as bi-projection fusion in BiFuse are proposed.
Ranked #12 on Depth Estimation on Stanford2D3D Panoramic
no code implementations • 26 Aug 2022 • Shin-I Cheng, Yu-Jie Chen, Wei-Chen Chiu, Hung-Yu Tseng, Hsin-Ying Lee
Generating images from hand-drawings is a crucial and fundamental task in content creation.
no code implementations • 27 Jul 2022 • Yu-Jie Chen, Shin-I Cheng, Wei-Chen Chiu, Hung-Yu Tseng, Hsin-Ying Lee
For example, it provides style variability for image generation and extension, and equips image-to-image translation with further extension capabilities.
no code implementations • 9 Jan 2022 • Meng-Shiun Tsai, Pei-Ze Chiang, Yi-Hsuan Tsai, Wei-Chen Chiu
Self-supervised learning on point clouds has gained a lot of attention recently, since it addresses the label-efficiency and domain-gap problems on point cloud tasks.
no code implementations • 28 Nov 2021 • Yu-Hsuan Li, Tzu-Yin Chao, Ching-Chun Huang, Pin-Yu Chen, Wei-Chen Chiu
Basically, given only a small set of detectors that are learned to recognize some manually annotated attributes (i. e., the seen attributes), we aim to synthesize the detectors of novel attributes in a zero-shot learning manner.
1 code implementation • 3 Oct 2021 • Chiu-Chou Lin, Wei-Chen Chiu, I-Chen Wu
In this paper, we propose the first metric for video game playstyles directly from the game observations and actions, without any prior specification on the playstyle in the target game.
1 code implementation • ICCV 2021 • Zunzhi You, Yi-Hsuan Tsai, Wei-Chen Chiu, Guanbin Li
Based on our observations, we quantify the interpretability of a deep MDE network by the depth selectivity of its hidden units.
1 code implementation • ICCV 2021 • Jia-Ren Chang, Yong-Sheng Chen, Wei-Chen Chiu
The main idea of the facial motion cycle-consistency is that, given a face with expression, we can perform de-expression to a neutral face via the removal of facial motion and further perform re-expression to reconstruct back to the original face.
1 code implementation • ICLR 2022 • Chia-Hsiang Kao, Wei-Chen Chiu, Pin-Yu Chen
Model-agnostic meta-learning (MAML) is one of the most popular and widely adopted meta-learning algorithms, achieving remarkable success in various learning problems.
no code implementations • CVPR 2021 • Fu-En Wang, Yu-Hsuan Yeh, Min Sun, Wei-Chen Chiu, Yi-Hsuan Tsai
Although significant progress has been made in room layout estimation, most methods aim to reduce the loss in the 2D pixel coordinate rather than exploiting the room structure in the 3D space.
no code implementations • 29 May 2021 • Wei-Jan Ko, Hui-Yu Huang, Yu-Liang Kuo, Chen-Yi Chiu, Li-Heng Wang, Wei-Chen Chiu
In this paper we propose a novel point cloud generator that is able to reconstruct and generate 3D point clouds composed of semantic parts.
no code implementations • 27 May 2021 • Pei-Ze Chiang, Meng-Shiun Tsai, Hung-Yu Tseng, Wei-Sheng Lai, Wei-Chen Chiu
Our framework consists of two components: an implicit representation of the 3D scene with the neural radiance fields model, and a hypernetwork to transfer the style information into the scene representation.
1 code implementation • 22 Apr 2021 • Bolivar Solarte, Chin-Hsuan Wu, Kuan-Wei Lu, Min Sun, Wei-Chen Chiu, Yi-Hsuan Tsai
This paper presents a novel preconditioning strategy for the classic 8-point algorithm (8-PA) for estimating an essential matrix from 360-FoV images (i. e., equirectangular images) in spherical projection.
1 code implementation • 1 Apr 2021 • Fu-En Wang, Yu-Hsuan Yeh, Min Sun, Wei-Chen Chiu, Yi-Hsuan Tsai
Although significant progress has been made in room layout estimation, most methods aim to reduce the loss in the 2D pixel coordinate rather than exploiting the room structure in the 3D space.
3D Room Layouts From A Single RGB Panorama Depth Estimation +2
1 code implementation • CVPR 2021 • Chia-Ni Lu, Ya-Chu Chang, Wei-Chen Chiu
In this paper we propose a new problem scenario in image processing, wide-range image blending, which aims to smoothly merge two different input photos into a panorama by generating novel image content for the intermediate region between them.
no code implementations • 25 Feb 2021 • Chun-Chih Teng, Pin-Yu Chen, Wei-Chen Chiu
We propose a Paired Few-shot GAN (PFS-GAN) model for learning generators with sufficient source data and a few target data.
1 code implementation • Winter Conference on Applications of Computer Vision (WACV) 2021 • Min-Yuan Tseng, Yen-Chung Chen, Yi-Lun Lee, Wei-Sheng Lai, Yi-Hsuan Tsai, Wei-Chen Chiu
Our method is based on an important observation that: even the direct cascade of prior research in spatial and temporal super-resolution can achieve the spatiotemporal upsampling, changing orders for combining them would lead to results with a complementary property.
no code implementations • 28 Dec 2020 • Li-Wei Chen, Wei-Chen Chiu, Chin-Tien Wu
We propose a spectral analysis to investigate the correlations among the resolution of the down sampled grid, the loss function and the accuracy of the SSNNs.
1 code implementation • 15 Dec 2020 • Cheng-Hsun Lei, Yi-Hsin Chen, Wen-Hsiao Peng, Wei-Chen Chiu
In this paper, we address the problem of distillation-based class-incremental learning with a single head.
no code implementations • 7 Jul 2020 • Rogan Morrow, Wei-Chen Chiu
There exist many forms of deep latent variable models, such as the variational autoencoder and adversarial autoencoder.
no code implementations • 12 Apr 2020 • Rogan Morrow, Wei-Chen Chiu
Recently proposed normalizing flow models such as Glow have been shown to be able to generate high quality, high dimensional images with relatively fast sampling speed.
1 code implementation • 30 Mar 2020 • Fu-En Wang, Yu-Hsuan Yeh, Min Sun, Wei-Chen Chiu, Yi-Hsuan Tsai
Inferring the information of 3D layout from a single equirectangular panorama is crucial for numerous applications of virtual reality or robotics (e. g., scene understanding and navigation).
1 code implementation • 11 Nov 2019 • Ning-Hsu Wang, Bolivar Solarte, Yi-Hsuan Tsai, Wei-Chen Chiu, Min Sun
Recently, end-to-end trainable deep neural networks have significantly improved stereo depth estimation for perspective images.
1 code implementation • CVPR 2019 • Hsueh-Ying Lai, Yi-Hsuan Tsai, Wei-Chen Chiu
In this paper, we propose a single and principled network to jointly learn spatiotemporal correspondence for stereo matching and flow estimation, with a newly designed geometric connection as the unsupervised signal for temporally adjacent stereo pairs.
1 code implementation • 5 Apr 2019 • Tsun-Hsuan Wang, Hou-Ning Hu, Chieh Hubert Lin, Yi-Hsuan Tsai, Wei-Chen Chiu, Min Sun
The complementary characteristics of active and passive depth sensing techniques motivate the fusion of the Li-DAR sensor and stereo camera for improved depth perception.
1 code implementation • CVPR 2019 • Wei-Lun Chang, Hui-Po Wang, Wen-Hsiao Peng, Wei-Chen Chiu
In this paper we tackle the problem of unsupervised domain adaptation for the task of semantic segmentation, where we attempt to transfer the knowledge learned upon synthetic datasets with ground-truth labels to real-world images without any annotation.
Ranked #25 on Image-to-Image Translation on SYNTHIA-to-Cityscapes
2 code implementations • 20 Dec 2018 • Tsun-Hsuan Wang, Fu-En Wang, Juan-Ting Lin, Yi-Hsuan Tsai, Wei-Chen Chiu, Min Sun
We propose a novel plug-and-play (PnP) module for improving depth prediction with taking arbitrary patterns of sparse depths as input.
2 code implementations • 10 Dec 2018 • Hung-Yu Chen, I-Sheng Fang, Wei-Chen Chiu
Style transfer has been widely applied to give real-world images a new artistic look.
no code implementations • ECCV 2018 • Hsuan-I Ho, Wei-Chen Chiu, Yu-Chiang Frank Wang
Video highlight or summarization is among interesting topics in computer vision, which benefits a variety of applications like viewing, searching, or storage.
no code implementations • ECCV 2018 • Hsuan-I Ho, Wei-Chen Chiu, Yu-Chiang Frank Wang
Video highlight or summarization is among interesting topics in computer vision, which benefits a variety of applications like viewing, searching, or storage.
no code implementations • CVPR 2018 • Yen-Cheng Liu, Yu-Ying Yeh, Tzu-Chien Fu, Sheng-De Wang, Wei-Chen Chiu, Yu-Chiang Frank Wang
While representation learning aims to derive interpretable features for describing visual data, representation disentanglement further results in such features so that particular image attributes can be identified and manipulated.
no code implementations • 3 Sep 2016 • Wei-Chen Chiu, Fabio Galasso, Mario Fritz
Are we ready to segment consumer stereo videos?
1 code implementation • CVPR 2017 • Yang He, Wei-Chen Chiu, Margret Keuper, Mario Fritz
The proposed network produces a high quality segmentation of a single image by leveraging information from additional views of the same scene.
Ranked #96 on Semantic Segmentation on NYU Depth v2
no code implementations • ICCV 2015 • Wei-Chen Chiu, Mario Fritz
The Histogram of Oriented Gradient (HOG) descriptor has led to many advances in computer vision over the last decade and is still part of many state of the art approaches.
no code implementations • CVPR 2013 • Wei-Chen Chiu, Mario Fritz
This is a clear mismatch to the challenges that we are facing with videos from online resources or consumer videos.