no code implementations • 14 May 2024 • Chenlei Lv, Dan Zhang
As an important subtopic of image enhancement, color transfer aims to enhance the color scheme of a source image according to a reference one while preserving the semantic context.
no code implementations • 7 May 2024 • Jinke Li, Xiao He, Chonghua Zhou, Xiaoqiang Cheng, Yang Wen, Dan Zhang
Leveraging the proposed view attention as well as an additional multi-frame streaming temporal attention, we introduce ViewFormer, a vision-centric transformer-based framework for spatiotemporal feature aggregation.
1 code implementation • 20 Mar 2024 • Yumeng Li, William Beluch, Margret Keuper, Dan Zhang, Anna Khoreva
Despite tremendous progress in the field of text-to-video (T2V) synthesis, open-sourced T2V diffusion models struggle to generate longer videos with dynamically varying and evolving content.
no code implementations • 14 Mar 2024 • Haiwen Huang, Songyou Peng, Dan Zhang, Andreas Geiger
We further demonstrate that using our renovated names enables training of stronger open-vocabulary segmentation models.
no code implementations • 28 Feb 2024 • Hannah Kim, Kushan Mitra, Rafael Li Chen, Sajjadur Rahman, Dan Zhang
Large language models (LLMs) can label data faster and cheaper than humans for various NLP tasks.
no code implementations • 24 Feb 2024 • Fanjin Zhang, Shijie Shi, Yifan Zhu, Bo Chen, Yukuo Cen, Jifan Yu, Yelin Chen, Lulu Wang, Qingfei Zhao, Yuqing Cheng, Tianyi Han, Yuwei An, Dan Zhang, Weng Lam Tam, Kun Cao, Yunhe Pang, Xinyu Guan, Huihui Yuan, Jian Song, Xiaoyan Li, Yuxiao Dong, Jie Tang
We envisage that OAG-Bench can serve as a common ground for the community to evaluate and compare algorithms in academic graph mining, thereby accelerating algorithm development and advancement in this field.
no code implementations • 22 Feb 2024 • Xinke Shen, Lingyi Tao, Xuyang Chen, Sen Song, Quanying Liu, Dan Zhang
Targeting the Electroencephalogram (EEG) technique, known for its rich spatial and temporal information, this study presents a general framework for Contrastive Learning of Shared SpatioTemporal EEG Representations across individuals (CL-SSTER).
1 code implementation • 28 Jan 2024 • Dan Zhang, Yangliao Geng, Wenwen Gong, Zhongang Qi, Zhiyu Chen, Xing Tang, Ying Shan, Yuxiao Dong, Jie Tang
In this work, we investigate how to employ both batch-wise CL (BCL) and feature-wise CL (FCL) for recommendation.
1 code implementation • 16 Jan 2024 • Yumeng Li, Margret Keuper, Dan Zhang, Anna Khoreva
Current L2I models either suffer from poor editability via text or weak alignment between the generated image and the input layout.
1 code implementation • 15 Jan 2024 • Dan Zhang, Ziniu Hu, Sining Zhoubian, Zhengxiao Du, Kaiyu Yang, Zihan Wang, Yisong Yue, Yuxiao Dong, Jie Tang
To bridge these gaps, we introduce SciGLM, a suite of scientific language models able to conduct college-level scientific reasoning.
no code implementations • 13 Dec 2023 • Mona Schirmer, Dan Zhang, Eric Nalisnick
Knowing if a model will generalize to data 'in the wild' is crucial for safe deployment.
1 code implementation • 10 Nov 2023 • Metod Jazbec, Patrick Forré, Stephan Mandt, Dan Zhang, Eric Nalisnick
Early-exit neural networks (EENNs) facilitate adaptive inference by producing predictions at multiple stages of the forward pass.
1 code implementation • 18 Oct 2023 • Xiang Chen, Duanzheng Song, Honghao Gui, Chenxi Wang, Ningyu Zhang, Jiang Yong, Fei Huang, Chengfei Lv, Dan Zhang, Huajun Chen
Despite their impressive generative capabilities, LLMs are hindered by fact-conflicting hallucinations in real-world applications.
no code implementations • 12 Oct 2023 • Qiang Li, Dan Zhang, Shengzhao Lei, Xun Zhao, Porawit Kamnoedboon, Weiwei Li, Junhao Dong, Shuyan Li
Despite the promising performance of existing visual models on public benchmarks, the critical assessment of their robustness for real-world applications remains an ongoing challenge.
no code implementations • 21 Aug 2023 • Sijin Wu, Dan Zhang, Teng Hu, Shikun Feng
In this paper, we propose Docprompt for document question answering tasks with powerful zero-shot and few-shot performance.
no code implementations • 19 Aug 2023 • Dan Zhang, Kaspar Sakmann, William Beluch, Robin Hutmacher, Yumeng Li
Within the context of autonomous driving, encountering unknown objects becomes inevitable during deployment in the open world.
no code implementations • 1 Aug 2023 • Dan Zhang, Fangfang Zhou, Felix Albu, Yuanzhou Wei, Xiao Yang, Yuan Gu, Qiang Li
The advent of deep learning has brought a revolutionary transformation to image denoising techniques.
1 code implementation • 20 Jul 2023 • Yumeng Li, Margret Keuper, Dan Zhang, Anna Khoreva
To address the challenges posed by complex prompts or scenarios involving multiple entities and to achieve improved attribute binding, we propose Divide & Bind.
1 code implementation • 2 Jul 2023 • Yumeng Li, Dan Zhang, Margret Keuper, Anna Khoreva
Using the proposed masked noise encoder to randomize style and content combinations in the training set, i. e., intra-source style augmentation (ISSA) effectively increases the diversity of training data and reduces spurious correlation.
no code implementations • NeurIPS 2023 • Zeju Qiu, Weiyang Liu, Haiwen Feng, Yuxuan Xue, Yao Feng, Zhen Liu, Dan Zhang, Adrian Weller, Bernhard Schölkopf
To tackle this challenge, we introduce a principled finetuning method -- Orthogonal Finetuning (OFT), for adapting text-to-image diffusion models to downstream tasks.
no code implementations • 8 Jun 2023 • Fei Ding, Dan Zhang, Yin Yang, Venkat Krovi, Feng Luo
We conduct a theoretical analysis of the proposed loss and highlight how it assigns different weights to negative samples during the process of disentangling the feature representation.
no code implementations • 10 Apr 2023 • Fangfang Zhou, Dan Zhang, Zhenming Fu
In each Dual Transformer (DT), the global features are extracted by the window-based Transformer, while the local details are extracted using the channel attention mechanism with deformable CNNs.
1 code implementation • 4 Apr 2023 • Dan Zhang, Fangfang Zhou, Yuwen Jiang, Zhengming Fu
Our MM-BSN can be used to address the problem of large-noise denoising, which cannot be efficiently handled by other BSN methods.
no code implementations • 4 Apr 2023 • Dan Zhang, Fangfang Zhou
In this paper, we propose a novel Denoise Transformer for real-world image denoising, which is mainly constructed with Context-aware Denoise Transformer (CADT) units and Secondary Noise Extractor (SNE) block.
no code implementations • ICCV 2023 • Jan Hendrik Metzen, Robin Hutmacher, N. Grace Hua, Valentyn Boreiko, Dan Zhang
Despite excellent average-case performance of many image classifiers, their performance can substantially deteriorate on semantically coherent subgroups of the data that were under-represented in the training data.
no code implementations • 2 Mar 2023 • Jun Xue, Cunhang Fan, Jiangyan Yi, Chenglong Wang, Zhengqi Wen, Dan Zhang, Zhao Lv
To address this problem, we propose using the deepest network instruct shallow network for enhancing shallow networks.
1 code implementation • 19 Feb 2023 • Ming Li, Yusheng Su, Hsiu-Yuan Huang, Jiali Cheng, Xin Hu, Xinmiao Zhang, Huadong Wang, Yujia Qin, Xiaozhi Wang, Kristen A. Lindquist, Zhiyuan Liu, Dan Zhang
Humans no doubt use language to communicate about their emotional experiences, but does language in turn help humans understand emotions, or is language just a vehicle of communication?
no code implementations • 9 Jan 2023 • Sajjadur Rahman, Hannah Kim, Dan Zhang, Estevam Hruschka, Eser Kandogan
Human-centered AI workflows involve stakeholders with multiple roles interacting with each other and automated agents to accomplish diverse tasks.
no code implementations • 8 Jan 2023 • Dan Zhang, Hannah Kim, Rafael Li Chen, Eser Kandogan, Estevam Hruschka
We present MEGAnno, a novel exploratory annotation framework designed for NLP researchers and practitioners.
1 code implementation • 22 Dec 2022 • Haiwen Huang, Andreas Geiger, Dan Zhang
We address the task of open-world class-agnostic object detection, i. e., detecting every object in an image by learning from a limited number of base object classes.
Ranked #1 on Open World Object Detection on COCO VOC to non-VOC
no code implementations • 29 Nov 2022 • Srivatsan Krishnan, Natasha Jaques, Shayegan Omidshafiei, Dan Zhang, Izzeddin Gur, Vijay Janapa Reddi, Aleksandra Faust
It is unclear how scalable single-agent formulations are as we increase the complexity of the design space (e. g., full stack System-on-Chip design).
no code implementations • 2 Nov 2022 • Mingqi Li, Fei Ding, Dan Zhang, Long Cheng, Hongxin Hu, Feng Luo
In this paper, we propose Multi-level Multilingual Knowledge Distillation (MMKD), a novel method for improving multilingual language models.
1 code implementation • 18 Oct 2022 • Yumeng Li, Dan Zhang, Margret Keuper, Anna Khoreva
Using the proposed masked noise encoder to randomize style and content combinations in the training set, ISSA effectively increases the diversity of training data and reduces spurious correlation.
1 code implementation • 11 Oct 2022 • Dan Zhang, Rui Zheng, Luosang Gadeng, Pei Yang
The proposed method underscores the significance of multi-task learning and explicit cross-task consistency enhancement for advancing semantic segmentation and highlights the potential of multitasking in real-time semantic segmentation.
1 code implementation • 15 Sep 2022 • Vadim Sushko, Dan Zhang, Juergen Gall, Anna Khoreva
To this end, inspired by the recent architectural developments of single-image GANs, we introduce our OSMIS model which enables the synthesis of segmentation masks that are precisely aligned to the generated images in the one-shot regime.
1 code implementation • 23 Aug 2022 • Jinkui Hao, Ting Shen, Xueli Zhu, Yonghuai Liu, Ardhendu Behera, Dan Zhang, Bang Chen, Jiang Liu, Jiong Zhang, Yitian Zhao
Automated detection of retinal structures, such as retinal vessels (RV), the foveal avascular zone (FAZ), and retinal vascular junctions (RVJ), are of great importance for understanding diseases of the eye and clinical decision-making.
no code implementations • 26 Jul 2022 • Dan Zhang, Xi Zhou, Zi-Hao Wang, Yan Peng, Shao-Rong Xie
This paper presents a novel data-driven methodology to provide a multi-step prediction of ship roll motions in high sea states.
no code implementations • 25 Jul 2022 • Huaying Hao, Cong Xu, Dan Zhang, Qifeng Yan, Jiong Zhang, Yue Liu, Yitian Zhao
To be more specific, we first perform a simple degradation of the 3x3 mm2/high-resolution (HR) image to obtain the synthetic LR image.
no code implementations • CVPR 2022 • Jinke Li, Xiao He, Yang Wen, Yuan Gao, Xiaoqiang Cheng, Dan Zhang
As a rising task, panoptic segmentation is faced with challenges in both semantic segmentation and instance segmentation.
no code implementations • 20 Sep 2021 • Xinke Shen, Xianggen Liu, Xin Hu, Dan Zhang, Sen Song
Contrastive learning was employed to minimize the inter-subject differences by maximizing the similarity in EEG signal representations across subjects when they received the same emotional stimuli in contrast to different ones.
no code implementations • 27 Jul 2021 • Qi Tang, Runmin Cong, Ronghui Sheng, Lingzhi He, Dan Zhang, Yao Zhao, Sam Kwong
The other is the content guidance bridge (CGBdg) designed for the depth map reconstruction process, which provides the content guidance learned from DSR task for MDE task.
no code implementations • 26 May 2021 • Dan Zhang, Safeen Huda, Ebrahim Songhori, Kartik Prabhu, Quoc Le, Anna Goldie, Azalia Mirhoseini
The rapidly-changing deep learning landscape presents a unique opportunity for building inference accelerators optimized for specific datacenter-scale workloads.
1 code implementation • 5 Apr 2021 • Yoshihiko Suhara, Jinfeng Li, Yuliang Li, Dan Zhang, Çağatay Demiralp, Chen Chen, Wang-Chiew Tan
Inferring meta information about tables, such as column headers or relationships between columns, is an active research topic in data management as we find many tables are missing some of this information.
Ranked #1 on Column Type Annotation on VizNet-Sato-MultiColumn
1 code implementation • 24 Mar 2021 • Vadim Sushko, Dan Zhang, Juergen Gall, Anna Khoreva
In this work, we introduce SIV-GAN, an unconditional generative model that can generate new scene compositions from a single training image or a single video clip.
no code implementations • 16 Feb 2021 • Zuohui Chen, Qing Yuan, Xujie Song, Cheng Chen, Dan Zhang, Yun Xiang, Ruigang Liu, Qi Xuan
Magnetic induction tomography (MIT) is an efficient solution for long-term brain disease monitoring, which focuses on reconstructing bio-impedance distribution inside the human brain using non-intrusive electromagnetic fields.
no code implementations • 4 Feb 2021 • Dan Zhang, Jingkai Xia, YiFan Li, Jingtao You, Yao Li, Changbo Fu, Jianglai Liu, Ning Zhou, Jie Bao, Huan Jia, Chenzhang Yuan, Yuan He, Weixing Xiong, Mengyun Guan
$\rm ^{83m}Kr$, with a short lifetime, is an ideal calibration source for liquid xenon or liquid argon detectors.
Nuclear Experiment Instrumentation and Detectors
1 code implementation • ICLR 2021 • Vadim Sushko, Edgar Schönfeld, Dan Zhang, Juergen Gall, Bernt Schiele, Anna Khoreva
By providing stronger supervision to the discriminator as well as to the generator through spatially- and semantically-aware discriminator feedback, we are able to synthesize images of higher fidelity with better alignment to their input label maps, making the use of the perceptual loss superfluous.
1 code implementation • ICLR 2021 • Kanil Patel, William Beluch, Bin Yang, Michael Pfeiffer, Dan Zhang
The goal of this paper is to resolve the identified issues of HB in order to provide calibrated confidence estimates using only a small holdout calibration dataset for bin optimization while preserving multi-class ranking accuracy.
1 code implementation • NeurIPS 2020 • Robin Tibor Schirrmeister, Yuxuan Zhou, Tonio Ball, Dan Zhang
We refine previous investigations of this failure at anomaly detection for invertible generative networks and provide a clear explanation of it as a combination of model bias and domain prior: Convolutional networks learn similar low-level feature distributions when trained on any natural image dataset and these low-level features dominate the likelihood.
no code implementations • 26 Feb 2020 • Jinyin Chen, Yixian Chen, Haibin Zheng, Shijing Shen, Shanqing Yu, Dan Zhang, Qi Xuan
The adversarial attack methods based on gradient information can adequately find the perturbations, that is, the combinations of rewired links, thereby reducing the effectiveness of the deep learning model based graph embedding algorithms, but it is also easy to fall into a local optimum.
Social and Information Networks
no code implementations • 16 Dec 2019 • Kanil Patel, William Beluch, Dan Zhang, Michael Pfeiffer, Bin Yang
Uncertainty estimates help to identify ambiguous, novel, or anomalous inputs, but the reliable quantification of uncertainty has proven to be challenging for modern deep networks.
1 code implementation • 14 Nov 2019 • Dan Zhang, Yoshihiko Suhara, Jinfeng Li, Madelon Hulsebos, Çağatay Demiralp, Wang-Chiew Tan
Detecting the semantic types of data columns in relational tables is important for various data preparation and information retrieval tasks such as data cleaning, schema matching, data discovery, and semantic search.
Ranked #2 on Column Type Annotation on VizNet-Sato-MultiColumn
no code implementations • 9 Aug 2019 • Chaithanya Kumar Mummadi, Tim Genewein, Dan Zhang, Thomas Brox, Volker Fischer
We achieve state-of-the-art pruning results for ResNet-50 with higher accuracy on ImageNet.
no code implementations • 17 Jun 2019 • Xu Liu, Licheng Jiao, Dan Zhang, Fang Liu
In this paper, a novel POLSAR image classification method is proposed based on polarimetric scattering coding and sparse support matrix machine.
no code implementations • 27 May 2019 • Qi Xuan, Jun Zheng, Lihong Chen, Shanqing Yu, Jinyin Chen, Dan Zhang, Qingpeng Zhang Member
Since a large number of downstream network algorithms, such as community detection and node classification, rely on the Euclidean distance between nodes to evaluate the similarity between them in the embedding space, EDA can be considered as a universal attack on a variety of network algorithms.
Social and Information Networks Physics and Society
1 code implementation • 22 Feb 2019 • Jinyin Chen, Jian Zhang, Xuanheng Xu, Chengbo Fu, Dan Zhang, Qingpeng Zhang, Qi Xuan
Predicting the potential relations between nodes in networks, known as link prediction, has long been a challenge in network science.
1 code implementation • NeurIPS 2019 • Dan Zhang, Anna Khoreva
Training of Generative Adversarial Networks (GANs) is notoriously fragile, requiring to maintain a careful balance between the generator and the discriminator in order to perform well.
Ranked #3 on Image Generation on CelebA-HQ 128x128
no code implementations • 27 Sep 2018 • Dan Zhang, Anna Khoreva
Despite recent progress, Generative Adversarial Networks (GANs) still suffer from training instability, requiring careful consideration of architecture design choices and hyper-parameter tuning.
1 code implementation • 9 Jul 2018 • Xu Liu, Licheng Jiao, Xu Tang, Qigong Sun, Dan Zhang
Based on sparse scattering coding and convolution neural network, the polarimetric convolutional network is proposed to classify PolSAR images by making full use of polarimetric information.
no code implementations • 20 Dec 2017 • Yang Nan, Gianmarc Coppola, Qiaokang Liang, Kunglin Zou, Wei Sun, Dan Zhang, Yaonan Wang, Guanzhen Yu
Gastric cancer is the second leading cause of cancer-related deaths worldwide, and the major hurdle in biomedical image analysis is the determination of the cancer extent.
1 code implementation • 15 Dec 2015 • Michael Hay, Ashwin Machanavajjhala, Gerome Miklau, Yan Chen, Dan Zhang
Differential privacy has become the dominant standard in the research community for strong privacy protection.
Databases Cryptography and Security
no code implementations • NeurIPS 2011 • Dan Zhang, Yan Liu, Luo Si, Jian Zhang, Richard D. Lawrence
Ignoring this structure information limits the performance of existing MIL algorithms.