Search Results for author: Ying Jin

Found 31 papers, 12 papers with code

Computational and Statistical Tradeoffs in Inferring Combinatorial Structures of Ising Model

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.

valid

Adaptively Learning to Select-Rank in Online Platforms

no code implementations7 Jun 2024 Jingyuan Wang, Perry Dong, Ying Jin, Ruohan Zhan, Zhengyuan Zhou

We develop a user response model that considers diverse user preferences and the varying effects of item positions, aiming to optimize overall user satisfaction with the ranked list.

Multi-Armed Bandits Thompson Sampling

ReasonPix2Pix: Instruction Reasoning Dataset for Advanced Image Editing

no code implementations18 May 2024 Ying Jin, Pengyang Ling, Xiaoyi Dong, Pan Zhang, Jiaqi Wang, Dahua Lin

Instruction-based image editing focuses on equipping a generative model with the capacity to adhere to human-written instructions for editing images.

Conformal Alignment: Knowing When to Trust Foundation Models with Guarantees

no code implementations16 May 2024 Yu Gui, Ying Jin, Zhimei Ren

Given any pre-trained model and new units with model-generated outputs, Conformal Alignment leverages a set of reference data with ground-truth alignment status to train an alignment predictor.

Decision Making Informativeness +2

Confidence on the Focal: Conformal Prediction with Selection-Conditional Coverage

1 code implementation6 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.

Conformal Prediction Drug Discovery +4

SepRep-Net: Multi-source Free Domain Adaptation via Model Separation And Reparameterization

no code implementations13 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.

Source-Free Domain Adaptation

Uncertainty Quantification over Graph with Conformalized Graph Neural Networks

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.

Conformal Prediction Uncertainty Quantification +1

Topological properties and organizing principles of semantic networks

no code implementations24 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.

UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers

1 code implementation31 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.

Image Captioning Image Classification +8

Semi-Supervised Semantic Segmentation via Gentle Teaching Assistant

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.

Segmentation Semi-Supervised Semantic Segmentation

Multi-Level Logit Distillation

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.

Knowledge Distillation

Policy learning "without'' overlap: Pessimism and generalized empirical Bernstein's inequality

no code implementations19 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.

Image-Text Retrieval with Binary and Continuous Label Supervision

no code implementations20 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.

Image Captioning Image-text Retrieval +2

Selection by Prediction with Conformal p-values

2 code implementations4 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.

Decision Making Drug Discovery

Upper bounds on the Natarajan dimensions of some function classes

no code implementations15 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.

Multi-class Classification

The Overlooked Classifier in Human-Object Interaction Recognition

no code implementations10 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.

Classification Human-Object Interaction Detection +4

Improving Vision Transformers for Incremental Learning

no code implementations12 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.

Class Incremental Learning Incremental Learning

Few-Shot Object Detection via Association and DIscrimination

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.

Few-Shot Object Detection Object +3

Single-DARTS: Towards Stable Architecture Search

no code implementations18 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.

Neural Architecture Search

Is Pessimism Provably Efficient for Offline RL?

no code implementations30 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.

Offline RL Reinforcement Learning (RL)

Single-level Optimization For Differential Architecture Search

no code implementations15 Dec 2020 Pengfei Hou, Ying Jin

The bias causes the architecture parameters of non-learnable operations to surpass that of learnable operations.

Incorporating planning intelligence into deep learning: A planning support tool for street network design

no code implementations9 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.

DeepStreet: A deep learning powered urban street network generation module

no code implementations9 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.

Learning Nonparametric Human Mesh Reconstruction from a Single Image without Ground Truth Meshes

no code implementations28 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.

Segmentation

Minimum Class Confusion for Versatile Domain Adaptation

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).

Inductive Bias Multi-target Domain Adaptation +1

3D RoI-aware U-Net for Accurate and Efficient Colorectal Tumor Segmentation

2 code implementations27 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.

Image Segmentation Multi-Task Learning +2

Cannot find the paper you are looking for? You can Submit a new open access paper.