1 code implementation • 8 Jan 2024 • Youbing Hu, Yun Cheng, Anqi Lu, Zhiqiang Cao, Dawei Wei, Jie Liu, Zhijun Li
To address this, we present the Localization and Focus Vision Transformer (LF-ViT).
1 code implementation • 28 Jun 2023 • Paul Pu Liang, Yiwei Lyu, Xiang Fan, Arav Agarwal, Yun Cheng, Louis-Philippe Morency, Ruslan Salakhutdinov
Learning multimodal representations involves integrating information from multiple heterogeneous sources of data.
1 code implementation • 7 Jun 2023 • Paul Pu Liang, Chun Kai Ling, Yun Cheng, Alex Obolenskiy, Yudong Liu, Rohan Pandey, Alex Wilf, Louis-Philippe Morency, Ruslan Salakhutdinov
We propose two lower bounds based on the amount of shared information between modalities and the disagreement between separately trained unimodal classifiers, and derive an upper bound through connections to approximate algorithms for min-entropy couplings.
1 code implementation • 7 Jun 2023 • Paul Pu Liang, Yun Cheng, Ruslan Salakhutdinov, Louis-Philippe Morency
In order to perform multimodal fusion of heterogeneous signals, we need to understand their interactions: how each modality individually provides information useful for a task and how this information changes in the presence of other modalities.
1 code implementation • 11 Apr 2023 • Xue-Jing Luo, Shuo Wang, Zongwei Wu, Christos Sakaridis, Yun Cheng, Deng-Ping Fan, Luc van Gool
Specifically, we leverage the latent diffusion model to synthesize salient objects in camouflaged scenes, while using the zero-shot image classification ability of the Contrastive Language-Image Pre-training (CLIP) model to prevent synthesis failures and ensure the synthesized object aligns with the input prompt.
1 code implementation • NeurIPS 2023 • Paul Pu Liang, Yun Cheng, Xiang Fan, Chun Kai Ling, Suzanne Nie, Richard Chen, Zihao Deng, Nicholas Allen, Randy Auerbach, Faisal Mahmood, Ruslan Salakhutdinov, Louis-Philippe Morency
The recent explosion of interest in multimodal applications has resulted in a wide selection of datasets and methods for representing and integrating information from different modalities.
no code implementations • 20 Feb 2023 • Jing Xu, Shuo Wang, Na Ying, Xiao Xiao, Jiang Zhang, Yun Cheng, Zhiling Jin, Gangfeng Zhang
Previous GCNs-based methods usually require providing spatial correlation graph structure of observation sites in advance.
2 code implementations • 15 Jul 2021 • Paul Pu Liang, Yiwei Lyu, Xiang Fan, Zetian Wu, Yun Cheng, Jason Wu, Leslie Chen, Peter Wu, Michelle A. Lee, Yuke Zhu, Ruslan Salakhutdinov, Louis-Philippe Morency
In order to accelerate progress towards understudied modalities and tasks while ensuring real-world robustness, we release MultiBench, a systematic and unified large-scale benchmark spanning 15 datasets, 10 modalities, 20 prediction tasks, and 6 research areas.
1 code implementation • Proceedings of the 42nd ACM SIGPLAN International Conference on Programming Language Design and Implementation 2021 • Jie Zhao, Bojie Li, Wang Nie, Zhen Geng, Renwei Zhang, Xiong Gao, Bin Cheng, Chen Wu, Yun Cheng, Zheng Li, Peng Di, Kun Zhang, Xuefeng Jin
Existing tensor compilers have proven their effectiveness in deploying deep neural networks on general-purpose hardware like CPU and GPU, but optimizing for neural processing units (NPUs) is still challenging due to the heterogeneous compute units and complicated memory hierarchy.
no code implementations • 21 Jan 2021 • Shaofeng Duan, Yun Cheng, Wei Xia, Yuanyuan Yang, Fengfeng Qi, Tianwei Tang, Yanfeng Guo, Dong Qian, Dao Xiang, Jie Zhang, Wentao Zhang
Exotic phenomenon can be achieved in quantum materials by confining electronic states into two dimensions.
Strongly Correlated Electrons Materials Science Superconductivity
1 code implementation • 19 Nov 2020 • Johanna Einsiedler, Yun Cheng, Franz Papst, Olga Saukh
In this work, we estimate pollution reduction over the lockdown period by using the measurements from ground air pollution monitoring stations, training a long-term prediction model and comparing its predictions to measured values over the lockdown month. We show that our models achieve state-of-the-art performance on the data from air pollution measurement stations in Switzerland and in China: evaluate up to -15. 8% / +34. 4% change in NO2 / PM10 in Zurich; -35. 3 % / -3. 5 % and -42. 4 % / -34. 7 % in NO2 / PM2. 5 in Beijing and Wuhan respectively.
1 code implementation • CVPR 2020 • Zhongnan Qu, Zimu Zhou, Yun Cheng, Lothar Thiele
We investigate the compression of deep neural networks by quantizing their weights and activations into multiple binary bases, known as multi-bit networks (MBNs), which accelerate the inference and reduce the storage for the deployment on low-resource mobile and embedded platforms.