no code implementations • 2 Apr 2024 • Sicheng Li, Hao Li, Yiyi Liao, Lu Yu
The emergence of Neural Radiance Fields (NeRF) has greatly impacted 3D scene modeling and novel-view synthesis.
no code implementations • 30 Mar 2024 • Muhammad Asif Ali, ZhengPing Li, Shu Yang, Keyuan Cheng, Yang Cao, Tianhao Huang, Lijie Hu, Lu Yu, Di Wang
Large language models (LLMs) have shown exceptional abilities for multiple different natural language processing tasks.
no code implementations • 30 Mar 2024 • Keyuan Cheng, Gang Lin, Haoyang Fei, Yuxuan zhai, Lu Yu, Muhammad Asif Ali, Lijie Hu, Di Wang
Multi-hop question answering (MQA) under knowledge editing (KE) has garnered significant attention in the era of large language models.
no code implementations • 22 Feb 2024 • Lu Yu, Arnak Dalalyan
We explore the sampling problem within the framework where parallel evaluations of the gradient of the log-density are feasible.
no code implementations • 17 Feb 2024 • Shu Yang, Muhammad Asif Ali, Lu Yu, Lijie Hu, Di Wang
The increasing significance of large models and their multi-modal variants in societal information processing has ignited debates on social safety and ethics.
no code implementations • 6 Feb 2024 • Zhixuan Chu, Yan Wang, Feng Zhu, Lu Yu, Longfei Li, Jinjie Gu
The advent of large language models (LLMs) such as ChatGPT, PaLM, and GPT-4 has catalyzed remarkable advances in natural language processing, demonstrating human-like language fluency and reasoning capacities.
no code implementations • 21 Jan 2024 • Yukun Zuo, Hantao Yao, Lu Yu, Liansheng Zhuang, Changsheng Xu
Nonetheless, these learnable prompts tend to concentrate on the discriminatory knowledge of the current task while ignoring past task knowledge, leading to that learnable prompts still suffering from catastrophic forgetting.
1 code implementation • 20 Dec 2023 • Jiang-Tian Zhai, Xialei Liu, Lu Yu, Ming-Ming Cheng
Considering this challenge, we propose a novel framework of fine-grained knowledge selection and restoration.
no code implementations • journal 2023 • WuJie Zhou, Shaohua Dong, Meixin Fang, Lu Yu
Color–thermal (RGB-T) urban scene parsing has recently attracted widespread interest.
Ranked #5 on Thermal Image Segmentation on PST900
no code implementations • ICCV 2023 • Xinya Chen, Jiaxin Huang, Yanrui Bin, Lu Yu, Yiyi Liao
Unsupervised learning of 3D-aware generative adversarial networks has lately made much progress.
no code implementations • 15 Jun 2023 • Lu Yu, Wei Xiang, Kang Han
To address this challenge, we propose the Edit-DiffNeRF framework, which is composed of a frozen diffusion model, a proposed delta module to edit the latent semantic space of the diffusion model, and a NeRF.
no code implementations • 14 Jun 2023 • Lu Yu, Avetik Karagulyan, Arnak Dalalyan
To provide a more thorough explanation of our method for establishing the computable upper bound, we conduct an analysis of the midpoint discretization for the vanilla Langevin process.
1 code implementation • 25 May 2023 • Hantao Yao, Lu Yu, Jifei Luo, Changsheng Xu
In this paper, we propose a novel Identity Knowledge Evolution (IKE) framework for CIOR, consisting of the Identity Knowledge Association (IKA), Identity Knowledge Distillation (IKD), and Identity Knowledge Update (IKU).
no code implementations • 28 Apr 2023 • Lu Yu, Malvina Nikandrou, Jiali Jin, Verena Rieser
In this paper, we propose a quality-agnostic framework to improve the performance and robustness of image captioning models for visually impaired people.
no code implementations • 11 Mar 2023 • Xingyu Liu, Alex Leonardi, Lu Yu, Chris Gilmer-Hill, Matthew Leavitt, Jonathan Frankle
We find that augmenting future runs with KD from previous runs dramatically reduces the time necessary to train these models, even taking into account the overhead of KD.
1 code implementation • CVPR 2023 • Lu Yu, Wei Xiang
Recent studies have proposed to prune transformers in an unexplainable manner, which overlook the relationship between internal units of the model and the target class, thereby leading to inferior performance.
no code implementations • 13 Feb 2023 • Feng Zhu, Mingjie Zhong, Xinxing Yang, Longfei Li, Lu Yu, Tiehua Zhang, Jun Zhou, Chaochao Chen, Fei Wu, Guanfeng Liu, Yan Wang
In recommendation scenarios, there are two long-standing challenges, i. e., selection bias and data sparsity, which lead to a significant drop in prediction accuracy for both Click-Through Rate (CTR) and post-click Conversion Rate (CVR) tasks.
no code implementations • CVPR 2023 • Sicheng Li, Hao Li, Yue Wang, Yiyi Liao, Lu Yu
Neural Radiance Fields (NeRF) have demonstrated superior novel view synthesis performance but are slow at rendering.
1 code implementation • 8 Nov 2022 • Alessandro Suglia, José Lopes, Emanuele Bastianelli, Andrea Vanzo, Shubham Agarwal, Malvina Nikandrou, Lu Yu, Ioannis Konstas, Verena Rieser
As the course of a game is unpredictable, so are commentaries, which makes them a unique resource to investigate dynamic language grounding.
no code implementations • journal 2022 • Shaohua Dong, WuJie Zhou, Xiaohong Qian, Lu Yu
RGB-T (red–green–blue and thermal) scene parsing has recently drawn considerable research attention.
Ranked #9 on Thermal Image Segmentation on PST900
no code implementations • 30 Sep 2022 • Mavina Nikandrou, Lu Yu, Alessandro Suglia, Ioannis Konstas, Verena Rieser
We first propose three plausible task formulations and demonstrate their impact on the performance of continual learning algorithms.
1 code implementation • 28 Jul 2022 • Taicheng Guo, Lu Yu, Basem Shihada, Xiangliang Zhang
Second, the user preference over these topics is transferable across different platforms.
no code implementations • 12 Jul 2022 • Lu Yu, Wei Xiang, Juan Fang, Yi-Ping Phoebe Chen, Lianhua Chi
To close these crucial gaps, we propose a novel vision transformer dubbed the eXplainable Vision Transformer (eX-ViT), an intrinsically interpretable transformer model that is able to jointly discover robust interpretable features and perform the prediction.
no code implementations • 6 Jul 2022 • Lu Yu, Verena Rieser
This study is the first to investigate the robustness of visually grounded dialog models towards textual attacks.
no code implementations • 28 May 2022 • Heming Sun, Lu Yu, Jiro Katto
Learned image compression (LIC) has reached a comparable coding gain with traditional hand-crafted methods such as VVC intra.
no code implementations • journal 2022 • WuJie Zhou, Shaohua Dong, Jingsheng Lei, Lu Yu
To improve the fusion of multimodal features and the segmentation accuracy, we propose a multitask-aware network (MTANet) with hierarchical multimodal fusion (multiscale fusion strategy) for RGB-T urban scene understanding.
Ranked #10 on Thermal Image Segmentation on PST900
no code implementations • 23 Feb 2022 • Nuri Mert Vural, Lu Yu, Krishnakumar Balasubramanian, Stanislav Volgushev, Murat A. Erdogdu
We study stochastic convex optimization under infinite noise variance.
no code implementations • 5 Jan 2022 • Lu Yu, Jiaying Gu, Stanislav Volgushev
Consider a panel data setting where repeated observations on individuals are available.
1 code implementation • 30 Dec 2021 • Alex Gomez-Villa, Bartlomiej Twardowski, Lu Yu, Andrew D. Bagdanov, Joost Van de Weijer
Recent self-supervised learning methods are able to learn high-quality image representations and are closing the gap with supervised approaches.
no code implementations • 17 Nov 2021 • Heming Sun, Lu Yu, Jiro Katto
To our best knowledge, this is the first work to give a complete analysis on the coding gain and the memory cost for a quantized LIC network, which validates the feasibility of the hardware implementation.
no code implementations • ICLR 2022 • Yaxing Wang, Joost Van de Weijer, Lu Yu, Shangling Jui
Therefore, we investigate knowledge distillation to transfer knowledge from a high-quality unconditioned generative model (e. g., StyleGAN) to a conditioned synthetic image generation modules in a variety of systems.
no code implementations • 29 Sep 2021 • Lu Yu, Shichao Pei, Chuxu Zhang, Xiangliang Zhang
Pairwise ranking models have been widely used to address various problems, such as recommendation.
1 code implementation • 5 Aug 2021 • Heming Sun, Lu Yu, Jiro Katto
As far as we know, this is the first work to explore a fully NM based framework for intra prediction, and we reach a better coding gain with a lower complexity compared with the previous work.
no code implementations • 28 Jul 2021 • Zhigao Fang, JiaQi Zhang, Lu Yu, Yin Zhao
Additionally, we utilize some typical and frequently used objective quality metrics to evaluate the coding methods in the experiment as comparison.
no code implementations • 6 Dec 2020 • Lu Yu, Xialei Liu, Joost Van de Weijer
In class-incremental semantic segmentation, we have no access to the labeled data of previous tasks.
Class-Incremental Semantic Segmentation Incremental Learning
1 code implementation • NeurIPS 2020 • Yaxing Wang, Lu Yu, Joost Van de Weijer
To enable the training of deep I2I models on small datasets, we propose a novel transfer learning method, that transfers knowledge from pre-trained GANs.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Chuxu Zhang, Lu Yu, Mandana Saebi, Meng Jiang, Nitesh Chawla
Multi-hop relation reasoning over knowledge base is to generate effective and interpretable relation prediction through reasoning paths.
1 code implementation • 16 Sep 2020 • Bianjiang Yang, Zi Hui, Haoji Hu, Xinyi Hu, Lu Yu
Although the facial makeup transfer network has achieved high-quality performance in generating perceptually pleasing makeup images, its capability is still restricted by the massive computation and storage of the network architecture.
no code implementations • 2 Sep 2020 • Lu Yu, Shichao Pei, Lizhong Ding, Jun Zhou, Longfei Li, Chuxu Zhang, Xiangliang Zhang
This paper studies learning node representations with graph neural networks (GNNs) for unsupervised scenario.
no code implementations • NeurIPS 2021 • Lu Yu, Krishnakumar Balasubramanian, Stanislav Volgushev, Murat A. Erdogdu
Structured non-convex learning problems, for which critical points have favorable statistical properties, arise frequently in statistical machine learning.
no code implementations • 19 May 2020 • Lu Yu, Shichao Pei, Chuxu Zhang, Shangsong Liang, Xiao Bai, Nitesh Chawla, Xiangliang Zhang
Pairwise ranking models have been widely used to address recommendation problems.
2 code implementations • CVPR 2020 • Lu Yu, Bartłomiej Twardowski, Xialei Liu, Luis Herranz, Kai Wang, Yongmei Cheng, Shangling Jui, Joost Van de Weijer
The vast majority of methods have studied this scenario for classification networks, where for each new task the classification layer of the network must be augmented with additional weights to make room for the newly added classes.
1 code implementation • 8 Jul 2019 • Lu Yu, Tobias Kaufmann, Johannes Lederer
The increasing availability of data has generated unprecedented prospects for network analyses in many biological fields, such as neuroscience (e. g., brain networks), genomics (e. g., gene-gene interaction networks), and ecology (e. g., species interaction networks).
Methodology Quantitative Methods Applications
1 code implementation • CVPR 2019 • Lu Yu, Vacit Oguz Yazici, Xialei Liu, Joost Van de Weijer, Yongmei Cheng, Arnau Ramisa
In this paper, we propose to use network distillation to efficiently compute image embeddings with small networks.
no code implementations • NIPS Workshop CDNNRIA 2018 • Yuxin Zhang, Huan Wang, Yang Luo, Lu Yu, Haoji Hu, Hangguan Shan, Tony Q. S. Quek
Despite enjoying extensive applications in video analysis, three-dimensional convolutional neural networks (3D CNNs)are restricted by their massive computation and storage consumption.
1 code implementation • 11 May 2018 • Lu Yu, Yongmei Cheng, Joost Van de Weijer
The attention branch is used to modulate the pixel-wise color naming predictions of the network.
no code implementations • 1 Aug 2016 • Johannes Lederer, Lu Yu, Irina Gaynanova
The abundance of high-dimensional data in the modern sciences has generated tremendous interest in penalized estimators such as the lasso, scaled lasso, square-root lasso, elastic net, and many others.