no code implementations • 24 Apr 2024 • Zhiqiang Tang, Haoyang Fang, Su Zhou, Taojiannan Yang, Zihan Zhong, Tony Hu, Katrin Kirchhoff, George Karypis
AutoGluon-Multimodal (AutoMM) is introduced as an open-source AutoML library designed specifically for multimodal learning.
1 code implementation • 11 Apr 2024 • Ming Li, Taojiannan Yang, Huafeng Kuang, Jie Wu, Zhaoning Wang, Xuefeng Xiao, Chen Chen
To this end, we propose ControlNet++, a novel approach that improves controllable generation by explicitly optimizing pixel-level cycle consistency between generated images and conditional controls.
1 code implementation • ICCV 2023 • Andong Deng, Taojiannan Yang, Chen Chen
The goal of building a benchmark (suite of datasets) is to provide a unified protocol for fair evaluation and thus facilitate the evolution of a specific area.
1 code implementation • 6 Feb 2023 • Taojiannan Yang, Yi Zhu, Yusheng Xie, Aston Zhang, Chen Chen, Mu Li
Recent vision transformer based video models mostly follow the ``image pre-training then finetuning" paradigm and have achieved great success on multiple video benchmarks.
Ranked #2 on Action Recognition on Diving-48 (using extra training data)
no code implementations • 17 Nov 2022 • Andong Deng, Taojiannan Yang, Chen Chen, Qian Chen, Leslie Neely, Sakiko Oyama
In such cases, automatic recognition systems based on computer vision and machine learning (in particular deep learning) technology can alleviate this issue to a large extent.
1 code implementation • 16 Nov 2022 • Taojiannan Yang, Linjie Yang, Xiaojie Jin, Chen Chen
In this paper, we revisit these training-free metrics and find that: (1) the number of parameters (\#Param), which is the most straightforward training-free metric, is overlooked in previous works but is surprisingly effective, (2) recent training-free metrics largely rely on the \#Param information to rank networks.
no code implementations • 4 Oct 2022 • Guangyu Sun, Umar Khalid, Matias Mendieta, Taojiannan Yang, Chen Chen
Recently, the use of small pre-trained models has been shown effective in federated learning optimization and improving convergence.
1 code implementation • CVPR 2023 • Ce Zheng, Matias Mendieta, Taojiannan Yang, Guo-Jun Qi, Chen Chen
Recently, vision transformers have shown great success in a set of human reconstruction tasks such as 2D human pose estimation (2D HPE), 3D human pose estimation (3D HPE), and human mesh reconstruction (HMR) tasks.
Ranked #29 on 3D Human Pose Estimation on 3DPW
1 code implementation • CVPR 2022 • Matias Mendieta, Taojiannan Yang, Pu Wang, Minwoo Lee, Zhengming Ding, Chen Chen
To alleviate this issue, many FL algorithms focus on mitigating the effects of data heterogeneity across clients by introducing a variety of proximal terms, some incurring considerable compute and/or memory overheads, to restrain local updates with respect to the global model.
1 code implementation • 16 May 2021 • Yu Shen, Sijie Zhu, Taojiannan Yang, Chen Chen, Delu Pan, Jianyu Chen, Liang Xiao, Qian Du
With a pair of pre- and post-disaster satellite images, building damage assessment aims at predicting the extent of damage to buildings.
Ranked #2 on 2D Semantic Segmentation on xBD
1 code implementation • 14 May 2021 • Taojiannan Yang, Sijie Zhu, Matias Mendieta, Pu Wang, Ravikumar Balakrishnan, Minwoo Lee, Tao Han, Mubarak Shah, Chen Chen
MutualNet is a general training methodology that can be applied to various network structures (e. g., 2D networks: MobileNets, ResNet, 3D networks: SlowFast, X3D) and various tasks (e. g., image classification, object detection, segmentation, and action recognition), and is demonstrated to achieve consistent improvements on a variety of datasets.
3 code implementations • ICCV 2021 • Ce Zheng, Sijie Zhu, Matias Mendieta, Taojiannan Yang, Chen Chen, Zhengming Ding
Transformer architectures have become the model of choice in natural language processing and are now being introduced into computer vision tasks such as image classification, object detection, and semantic segmentation.
Ranked #13 on Monocular 3D Human Pose Estimation on Human3.6M
1 code implementation • 18 Mar 2021 • Weiping Yu, Sijie Zhu, Taojiannan Yang, Chen Chen
Unlike most recent works that focused on applying active learning for image classification, we propose an effective Consistency-based Active Learning method for object Detection (CALD), which fully explores the consistency between original and augmented data.
1 code implementation • 24 Dec 2020 • Ce Zheng, Wenhan Wu, Chen Chen, Taojiannan Yang, Sijie Zhu, Ju Shen, Nasser Kehtarnavaz, Mubarak Shah
Furthermore, 2D and 3D human pose estimation datasets and evaluation metrics are included.
1 code implementation • CVPR 2021 • Sijie Zhu, Taojiannan Yang, Chen Chen
In this paper, we redefine this problem with a more realistic assumption that the query image can be arbitrary in the area of interest and the reference images are captured before the queries emerge.
no code implementations • 24 Nov 2020 • Sijie Zhu, Taojiannan Yang, Matias Mendieta, Chen Chen
Even under the same computational constraints, the performance of our adaptive networks can be significantly boosted over the baseline counterparts by the mutual training along three dimensions.
1 code implementation • 7 Nov 2020 • Weiping Yu, Taojiannan Yang, Chen Chen
To this end, we rethink long-tailed object detection in UAV images and propose the Dual Sampler and Head detection Network (DSHNet), which is the first work that aims to resolve long-tail distribution in UAV images.
no code implementations • 27 Oct 2020 • Yu Shen, Sijie Zhu, Taojiannan Yang, Chen Chen
Fast and effective responses are required when a natural disaster (e. g., earthquake, hurricane, etc.)
Ranked #3 on 2D Semantic Segmentation on xBD
1 code implementation • NeurIPS 2020 • Taojiannan Yang, Sijie Zhu, Chen Chen
The key idea is utilizing randomly transformed training samples to regularize a set of sub-networks, which are originated by sampling the width of the original network, in the training process.
no code implementations • 23 May 2020 • Sijie Zhu, Taojiannan Yang, Chen Chen
Street-to-aerial image geo-localization, which matches a query street-view image to the GPS-tagged aerial images in a reference set, has attracted increasing attention recently.
1 code implementation • 12 Apr 2020 • Changlin Li, Taojiannan Yang, Sijie Zhu, Chen Chen, Shanyue Guan
Specifically, we propose a Density-Map guided object detection Network (DMNet), which is inspired from the observation that the object density map of an image presents how objects distribute in terms of the pixel intensity of the map.
1 code implementation • 27 Sep 2019 • Sijie Zhu, Taojiannan Yang, Chen Chen
This work explores the visual explanation for deep metric learning and its applications.
2 code implementations • ECCV 2020 • Taojiannan Yang, Sijie Zhu, Chen Chen, Shen Yan, Mi Zhang, Andrew Willis
We propose the width-resolution mutual learning method (MutualNet) to train a network that is executable at dynamic resource constraints to achieve adaptive accuracy-efficiency trade-offs at runtime.
no code implementations • 25 Sep 2019 • Taojiannan Yang, Sijie Zhu, Yan Shen, Mi Zhang, Andrew Willis, Chen Chen
We propose a framework to mutually learn from different input resolutions and network widths.