Search Results for author: Ziyi Liu

Found 29 papers, 12 papers with code

ER-TEST Evaluating Explanation Regularization Methods for NLP Models

no code implementations NAACL (TrustNLP) 2022 Brihi Joshi, Aaron Chan, Ziyi Liu, Xiang Ren

For the latter, explanation regularization (ER) aims to improve NLM generalization by pushing the machine rationales to align with human rationales.


Self-Contradictory Reasoning Evaluation and Detection

no code implementations16 Nov 2023 Ziyi Liu, Isabelle Lee, Yongkang Du, Soumya Sanyal, Jieyu Zhao

In a plethora of recent work, large language models (LLMs) demonstrated impressive reasoning ability, but many proposed downstream reasoning tasks focus on performance-wise evaluation.

Dual Defense: Adversarial, Traceable, and Invisible Robust Watermarking against Face Swapping

no code implementations25 Oct 2023 Yunming Zhang, Dengpan Ye, Caiyun Xie, Long Tang, Chuanxi Chen, Ziyi Liu, Jiacheng Deng

Dual Defense invisibly embeds a single robust watermark within the target face to actively respond to sudden cases of malicious face swapping.

Face Swapping Misinformation

Bootstrap Your Own Skills: Learning to Solve New Tasks with Large Language Model Guidance

no code implementations16 Oct 2023 Jesse Zhang, Jiahui Zhang, Karl Pertsch, Ziyi Liu, Xiang Ren, Minsuk Chang, Shao-Hua Sun, Joseph J. Lim

Instead, our approach BOSS (BOotStrapping your own Skills) learns to accomplish new tasks by performing "skill bootstrapping," where an agent with a set of primitive skills interacts with the environment to practice new skills without receiving reward feedback for tasks outside of the initial skill set.

Language Modelling Large Language Model

Are Machine Rationales (Not) Useful to Humans? Measuring and Improving Human Utility of Free-Text Rationales

1 code implementation11 May 2023 Brihi Joshi, Ziyi Liu, Sahana Ramnath, Aaron Chan, Zhewei Tong, Shaoliang Nie, Qifan Wang, Yejin Choi, Xiang Ren

Existing metrics like task performance of the LM generating the rationales, or similarity between generated and gold rationales are not good indicators of their human utility.

Handling Concept Drift in Global Time Series Forecasting

1 code implementation4 Apr 2023 Ziyi Liu, Rakshitha Godahewa, Kasun Bandara, Christoph Bergmeir

Handling concept drift in forecasting is essential for many ML methods in use nowadays, however, the prior work only proposes methods to handle concept drift in the classification domain.

Time Series Time Series Forecasting

SOAR: Scene-debiasing Open-set Action Recognition

no code implementations ICCV 2023 Yuanhao Zhai, Ziyi Liu, Zhenyu Wu, Yi Wu, Chunluan Zhou, David Doermann, Junsong Yuan, Gang Hua

Deep models have the risk of utilizing spurious clues to make predictions, e. g., recognizing actions via classifying the background scene.

Open Set Action Recognition Scene Classification

Clustered Federated Learning based on Nonconvex Pairwise Fusion

1 code implementation8 Nov 2022 Xue Yu, Ziyi Liu, Wu Wang, Yifan Sun

We propose a clustered FL framework that incorporates a nonconvex penalty to pairwise differences of parameters.

Federated Learning

XMD: An End-to-End Framework for Interactive Explanation-Based Debugging of NLP Models

no code implementations30 Oct 2022 Dong-Ho Lee, Akshen Kadakia, Brihi Joshi, Aaron Chan, Ziyi Liu, Kiran Narahari, Takashi Shibuya, Ryosuke Mitani, Toshiyuki Sekiya, Jay Pujara, Xiang Ren

Explanation-based model debugging aims to resolve spurious biases by showing human users explanations of model behavior, asking users to give feedback on the behavior, then using the feedback to update the model.

text-classification Text Classification

Correlation Information Bottleneck: Towards Adapting Pretrained Multimodal Models for Robust Visual Question Answering

1 code implementation14 Sep 2022 Jingjing Jiang, Ziyi Liu, Nanning Zheng

In this paper, we aim to improve input robustness from an information bottleneck perspective when adapting pretrained VLMs to the downstream VQA task.

Adversarial Robustness Question Answering +1

AiM: Taking Answers in Mind to Correct Chinese Cloze Tests in Educational Applications

1 code implementation COLING 2022 Yusen Zhang, Zhongli Li, Qingyu Zhou, Ziyi Liu, Chao Li, Mina Ma, Yunbo Cao, Hongzhi Liu

To automatically correct handwritten assignments, the traditional approach is to use an OCR model to recognize characters and compare them to answers.

Optical Character Recognition (OCR)

Multi-Marginal Contrastive Learning for Multi-Label Subcellular Protein Localization

1 code implementation CVPR 2022 Ziyi Liu, Zengmao Wang, Bo Du

In this paper, we propose a deep protein subcellular localization method with multi-marginal contrastive learning to perceive the same PSLs in different tissue images and different PSLs within the same tissue image.

Contrastive Learning

LiVLR: A Lightweight Visual-Linguistic Reasoning Framework for Video Question Answering

1 code implementation29 Nov 2021 Jingjing Jiang, Ziyi Liu, Nanning Zheng

Video Question Answering (VideoQA), aiming to correctly answer the given question based on understanding multi-modal video content, is challenging due to the rich video content.

Question Answering Video Question Answering +2

Machine Learning for Multimodal Electronic Health Records-based Research: Challenges and Perspectives

no code implementations9 Nov 2021 Ziyi Liu, JiaQi Zhang, Yongshuai Hou, Xinran Zhang, Ge Li, Yang Xiang

Background: Electronic Health Records (EHRs) contain rich information of patients' health history, which usually include both structured and unstructured data.

BIG-bench Machine Learning

SGEN: Single-cell Sequencing Graph Self-supervised Embedding Network

no code implementations15 Oct 2021 Ziyi Liu, Minghui Liao, Fulin Luo, Bo Du

This method constructs the graph by the similarity relationship between cells and adopts GCN to analyze the neighbor embedding information of samples, which makes the similar cell closer to each other on the 2D scatter plot.

Dimensionality Reduction Graph Embedding

X-GGM: Graph Generative Modeling for Out-of-Distribution Generalization in Visual Question Answering

1 code implementation24 Jul 2021 Jingjing Jiang, Ziyi Liu, Yifan Liu, Zhixiong Nan, Nanning Zheng

In this paper, we formulate OOD generalization in VQA as a compositional generalization problem and propose a graph generative modeling-based training scheme (X-GGM) to implicitly model the problem.

Attribute Out-of-Distribution Generalization +2

LightFuse: Lightweight CNN based Dual-exposure Fusion

1 code implementation5 Jul 2021 Ziyi Liu, Jie Yang, Svetlana Yanushkevich, Orly Yadid-Pecht

Embedded systems have a huge market, and utilizing DCNNs' powerful functionality into them will further reduce human intervention.

Mobile-end Tone Mapping based on Integral Image and Integral Histogram

no code implementations2 Feb 2021 Jie Yang, Mengchen Lin, Ziyi Liu, Ulian Shahnovich, Orly Yadid-Pecht

It is especially crucial for mobile devices because most of the images taken today are from mobile phones, hence such technology is highly demanded in the consumer market of mobile devices and is essential for a good customer experience.

Tone Mapping

Deep Reformulated Laplacian Tone Mapping

1 code implementation31 Jan 2021 Jie Yang, Ziyi Liu, Mengchen Lin, Svetlana Yanushkevich, Orly Yadid-Pecht

The reformulated Laplacian pyramid always decompose a WDR image into two frequency bands where the low-frequency band is global feature-oriented, and the high-frequency band is local feature-oriented.

Tone Mapping

Tone Mapping Based on Multi-scale Histogram Synthesis

1 code implementation31 Jan 2021 Jie Yang, Ziyi Liu, Ulian Shahnovich, Orly Yadid-Pecht

HVS perceives luminance differently when under different adaptation levels, and therefore our algorithm uses functions built upon different scales to tone map pixels to different values.

Tone Mapping

A review for Tone-mapping Operators on Wide Dynamic Range Image

no code implementations8 Jan 2021 Ziyi Liu

The dynamic range of our normal life can exceeds 120 dB, however, the smart-phone cameras and the conventional digital cameras can only capture a dynamic range of 90 dB, which sometimes leads to loss of details for the recorded image.

Tone Mapping

Detecting Foodborne Illness Complaints in Multiple Languages Using English Annotations Only

no code implementations EMNLP (Louhi) 2020 Ziyi Liu, Giannis Karamanolakis, Daniel Hsu, Luis Gravano

To improve performance without extra annotations, we create artificial training documents in the target language through machine translation and train mBERT jointly for the source (English) and target language.

Machine Translation text-classification +1

Weakly Supervised Temporal Action Localization Through Contrast Based Evaluation Networks

no code implementations ICCV 2019 Ziyi Liu, Le Wang, Qilin Zhang, Zhanning Gao, Zhenxing Niu, Nanning Zheng, Gang Hua

To address this challenge, we propose the Contrast-based Localization EvaluAtioN Network (CleanNet) with our new action proposal evaluator, which provides pseudo-supervision by leveraging the temporal contrast in snippet-level action classification predictions.

Action Classification Weakly Supervised Action Localization +2

Attention-based Temporal Weighted Convolutional Neural Network for Action Recognition

no code implementations19 Mar 2018 Jinliang Zang, Le Wang, Ziyi Liu, Qilin Zhang, Zhenxing Niu, Gang Hua, Nanning Zheng

Research in human action recognition has accelerated significantly since the introduction of powerful machine learning tools such as Convolutional Neural Networks (CNNs).

Action Recognition Temporal Action Localization

Detecting Drivable Area for Self-driving Cars: An Unsupervised Approach

no code implementations1 May 2017 Ziyi Liu, Siyu Yu, Xiao Wang, Nanning Zheng

Experiments show that our unsupervised approach is efficient and robust for detecting drivable area for self-driving cars.

Self-Driving Cars

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