no code implementations • ICML 2020 • Ying Jin, Zhaoran Wang, Junwei Lu
We study the computational and statistical tradeoffs in inferring combinatorial structures of high dimensional simple zero-field ferromagnetic Ising model.
1 code implementation • 6 Mar 2024 • Ying Jin, Zhimei Ren
In such cases, marginally valid conformal prediction intervals may not provide valid coverage for the focal unit(s) due to selection bias.
no code implementations • 13 Feb 2024 • Ying Jin, Jiaqi Wang, Dahua Lin
We consider multi-source free domain adaptation, the problem of adapting multiple existing models to a new domain without accessing the source data.
1 code implementation • 7 Oct 2023 • Pengfei Zhou, Weiqing Min, Yang Zhang, Jiajun Song, Ying Jin, Shuqiang Jiang
To tackle this, we propose the Semantic Separable Diffusion Synthesizer (SeeDS) framework for Zero-Shot Food Detection (ZSFD).
Ranked #1 on Generalized Zero-Shot Object Detection on MS-COCO
1 code implementation • NeurIPS 2023 • Kexin Huang, Ying Jin, Emmanuel Candès, Jure Leskovec
We establish a permutation invariance condition that enables the validity of CP on graph data and provide an exact characterization of the test-time coverage.
no code implementations • 24 Apr 2023 • Gabriel Budel, Ying Jin, Piet Van Mieghem, Maksim Kitsak
We find that depending on the semantic relation type and the language, the link formation in semantic networks is guided by different principles.
1 code implementation • 31 Jan 2023 • Dachuan Shi, Chaofan Tao, Ying Jin, Zhendong Yang, Chun Yuan, Jiaqi Wang
Real-world data contains a vast amount of multimodal information, among which vision and language are the two most representative modalities.
1 code implementation • NIPS 2022 • Ying Jin, Jiaqi Wang, Dahua Lin
Semi-Supervised Semantic Segmentation aims at training the segmentation model with limited labeled data and a large amount of unlabeled data.
1 code implementation • CVPR 2023 • Ying Jin, Jiaqi Wang, Dahua Lin
Through this framework, the prediction alignment is not only conducted at the instance level, but also at the batch and class level, through which the student model learns instance prediction, input correlation, and category correlation simultaneously.
no code implementations • 19 Dec 2022 • Ying Jin, Zhimei Ren, Zhuoran Yang, Zhaoran Wang
Existing policy learning methods rely on a uniform overlap assumption, i. e., the propensities of exploring all actions for all individual characteristics are lower bounded in the offline dataset.
no code implementations • 20 Oct 2022 • Zheng Li, Caili Guo, Zerun Feng, Jenq-Neng Hwang, Ying Jin, Yufeng Zhang
Such a binary indicator covers only a limited subset of image-text semantic relations, which is insufficient to represent relevance degrees between images and texts described by continuous labels such as image captions.
2 code implementations • 4 Oct 2022 • Ying Jin, Emmanuel J. Candès
Decision making or scientific discovery pipelines such as job hiring and drug discovery often involve multiple stages: before any resource-intensive step, there is often an initial screening that uses predictions from a machine learning model to shortlist a few candidates from a large pool.
no code implementations • 15 Sep 2022 • Ying Jin
The Natarajan dimension is a fundamental tool for characterizing multi-class PAC learnability, generalizing the Vapnik-Chervonenkis (VC) dimension from binary to multi-class classification problems.
no code implementations • 10 Mar 2022 • Ying Jin, Yinpeng Chen, Lijuan Wang, JianFeng Wang, Pei Yu, Lin Liang, Jenq-Neng Hwang, Zicheng Liu
Human-Object Interaction (HOI) recognition is challenging due to two factors: (1) significant imbalance across classes and (2) requiring multiple labels per image.
no code implementations • arXiv 2021 • Ying Jin, Yinpeng Chen, Lijuan Wang, JianFeng Wang, Pei Yu, Lin Liang, Jenq-Neng Hwang, Zicheng Liu
Human-Object Interaction (HOI) recognition is challenging due to two factors: (1) significant imbalance across classes and (2) requiring multiple labels per image.
Ranked #1 on Human-Object Interaction Detection on HICO
no code implementations • 12 Dec 2021 • Pei Yu, Yinpeng Chen, Ying Jin, Zicheng Liu
This paper proposes a working recipe of using Vision Transformer (ViT) in class incremental learning.
1 code implementation • NeurIPS 2021 • Yuhang Cao, Jiaqi Wang, Ying Jin, Tong Wu, Kai Chen, Ziwei Liu, Dahua Lin
1) In the association step, in contrast to implicitly leveraging multiple base classes, we construct a compact novel class feature space via explicitly imitating a specific base class feature space.
no code implementations • 18 Aug 2021 • Pengfei Hou, Ying Jin, Yukang Chen
Differentiable architecture search (DARTS) marks a milestone in Neural Architecture Search (NAS), boasting simplicity and small search costs.
4 code implementations • 29 Jul 2021 • William La Cava, Patryk Orzechowski, Bogdan Burlacu, Fabrício Olivetti de França, Marco Virgolin, Ying Jin, Michael Kommenda, Jason H. Moore
We assess 14 symbolic regression methods and 7 machine learning methods on a set of 252 diverse regression problems.
no code implementations • arXiv 2021 • Ying Jin, Yinpeng Chen, Lijuan Wang, JianFeng Wang, Pei Yu, Zicheng Liu, Jenq-Neng Hwang
This paper revisits human-object interaction (HOI) recognition at image level without using supervisions of object location and human pose.
no code implementations • 30 Dec 2020 • Ying Jin, Zhuoran Yang, Zhaoran Wang
We study offline reinforcement learning (RL), which aims to learn an optimal policy based on a dataset collected a priori.
no code implementations • 15 Dec 2020 • Pengfei Hou, Ying Jin
The bias causes the architecture parameters of non-learnable operations to surpass that of learnable operations.
no code implementations • 9 Oct 2020 • Zhou Fang, Tianren Yang, Ying Jin
Specifically, the CNN is firstly trained to detect, recognize and capture the local features as well as the patterns of the existing street network sourced from the OpenStreetMap.
no code implementations • 9 Oct 2020 • Zhou Fang, Ying Jin, Tianren Yang
Deep learning applications in shaping ad hoc planning proposals are limited by the difficulty in integrating professional knowledge about cities with artificial intelligence.
no code implementations • 28 Feb 2020 • Kevin Lin, Lijuan Wang, Ying Jin, Zicheng Liu, Ming-Ting Sun
Experimental results on multiple public datasets show that without using 3D ground truth meshes, the proposed approach outperforms the previous state-of-the-art approaches that require ground truth meshes for training.
3 code implementations • ECCV 2020 • Ying Jin, Ximei Wang, Mingsheng Long, Jian-Min Wang
It can be characterized as (1) a non-adversarial DA method without explicitly deploying domain alignment, enjoying faster convergence speed; (2) a versatile approach that can handle four existing scenarios: Closed-Set, Partial-Set, Multi-Source, and Multi-Target DA, outperforming the state-of-the-art methods in these scenarios, especially on one of the largest and hardest datasets to date (7. 3% on DomainNet).
Ranked #3 on Multi-target Domain Adaptation on DomainNet
1 code implementation • NeurIPS 2019 • Ximei Wang, Ying Jin, Mingsheng Long, Jian-Min Wang, Michael. I. Jordan
Deep neural networks (DNNs) excel at learning representations when trained on large-scale datasets.
2 code implementations • 27 Jun 2018 • Yi-Jie Huang, Qi Dou, Zi-Xian Wang, Li-Zhi Liu, Ying Jin, Chao-Feng Li, Lisheng Wang, Hao Chen, Rui-Hua Xu
With the region proposals from the encoder, we crop multi-level RoI in-region features from the encoder to form a GPU memory-efficient decoder for detailpreserving segmentation and therefore enlarged applicable volume size and effective receptive field.