Tianwei Yue

Tianwei Yue

Auto-generated profile, based on publicly available information

Tianwei Yue

Carnegie Mellon University Carnegie Mellon University Columbia University Carnegie Mellon University Carnegie Mellon University Carnegie Mellon University

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 November 2017 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
YWYao Wang
Yao Wang
LLLin Lin
Lin Lin
QZQian Zhao
Qian Zhao
TYTianwei Yue
Tianwei Yue
DMDeyu Meng
Deyu Meng
YLYee Leung
Yee Leung
In this letter, we consider the problem of compressive sensing of hyperspectral images (HSIs). We propose a novel tensor-based approach by modeling the global spatial–spectral correlation and local smoothness properties hidden in HSIs. Specifically, we use the tensor Tucker decomposition to describe the global spatial–spectral correlation among all HSI bands, and a weighted 3-D total variation to characterize the local smooth structure in both spatial and spectral modes. We then design an efficient algorithm to solve the resulting optimization problem by using the alternating direction method of multipliers. Experimental results on several HSI data sets demonstrate improved reconstruction performance of the proposed approach, as compared with other competing approaches.

Verified
Journal Article
Open access
PDF file
TYTianwei Yue
Tianwei Yue
YWYuanxin Wang
Yuanxin Wang
LZLongxiang Zhang
Longxiang Zhang
CGChunming Gu
Chunming Gu
HXHaoru Xue
Haoru Xue
YDYujie Dun
Yujie Dun
The data explosion driven by advancements in genomic research, such as high-throughput sequencing techniques, is constantly challenging conventional methods used in genomics. In parallel with the urgent demand for robust algorithms, deep learning has succeeded in various fields such as vision, speech, and text processing. Yet genomics entails unique challenges to deep learning, since we expect a superhuman intelligence that explores beyond our knowledge to interpret the genome from deep learning. A powerful deep learning model should rely on the insightful utilization of task-specific knowledge. In this paper, we briefly discuss the strengths of different deep learning models from a genomic perspective so as to fit each particular task with proper deep learning-based architecture, and we remark on practical considerations of developing deep learning architectures for genomics. We also provide a concise review of deep learning applications in various aspects of genomic research and point out current challenges and potential research directions for future genomics applications. We believe the collaborative use of ever-growing diverse data and the fast iteration of deep learning models will continue to contribute to the future of genomics.

30 June 2023 in Applied Sciences
Verified
Journal Article
Open access
PDF file
TCTong Chen
Tong Chen
XWXuewei Wang
Xuewei Wang
TYTianwei Yue
Tianwei Yue
XBXiaoyu Bai
Xiaoyu Bai
CLCindy X. Le
Cindy X. Le
WWWenping Wang
Wenping Wang
As the popularity of large language models (LLMs) has risen over the course of the last year, led by GPT-3/4 and especially its productization as ChatGPT, we have witnessed the extensive application of LLMs to text summarization. However, LLMs do not intrinsically have the power to verify the correctness of the information they supply and generate. This research introduces a novel approach to abstractive summarization, aiming to address the limitations of LLMs in that they struggle to understand the truth. The proposed method leverages extracted knowledge graph information and structured semantics as a guide for summarization. Building upon BART, one of the state-of-the-art sequence-to-sequence pre-trained LLMs, multi-source transformer modules are developed as an encoder, which are capable of processing textual and graphical inputs. Decoding is performed based on this enriched encoding to enhance the summary quality. The Wiki-Sum dataset, derived from Wikipedia text dumps, is introduced for evaluation purposes. Comparative experiments with baseline models demonstrate the strengths of the proposed approach in generating informative and relevant summaries. We conclude by presenting our insights into utilizing LLMs with graph external information, which will become a powerful aid towards the goal of factually correct and verified LLMs.

21 August 2023 in Applied Sciences
Verified
Journal Article
Open access
PDF file
ZZZhihao Zhou
Zhihao Zhou
TYTianwei Yue
Tianwei Yue
CLChen Liang
Chen Liang
XBXiaoyu Bai
Xiaoyu Bai
DCDachi Chen
Dachi Chen
WWWenping Wang
Wenping Wang
Harnessing commonsense knowledge poses a significant challenge for machine comprehension systems. This paper primarily focuses on incorporating a specific subset of commonsense knowledge, namely, script knowledge. Script knowledge is about sequences of actions that are typically performed by individuals in everyday life. Our experiments were centered around the MCScript dataset, which was the basis of the SemEval-2018 Task 11: Machine Comprehension using Commonsense Knowledge. As a baseline, we utilized our Three-Way Attentive Networks (TriANs) framework to model the interactions among passages, questions, and answers. Building upon the TriAN, we proposed to: (1) integrate a pre-trained language model to capture script knowledge; (2) introduce multi-layer attention to facilitate multi-hop reasoning; and (3) incorporate positional embeddings to enhance the model’s capacity for event-ordering reasoning. In this paper, we present our proposed methods and prove their efficacy in improving script knowledge integration and reasoning.

13 April 2024 in arXiv
Verified
Preprint
Open access
PDF file
CHCongrui Hetang
Congrui Hetang
HXHaoru Xue
Haoru Xue
CLCindy Le
Cindy Le
TYTianwei Yue
Tianwei Yue
WWWenping Wang
Wenping Wang
YHYihui He
Yihui He
We propose SAM-Road, an adaptation of the Segment Anything Model (SAM) for extracting large-scale, vectorized road network graphs from satellite imagery. To predict graph geometry, we formulate it as a dense semantic segmentation task, leveraging the inherent strengths of SAM. The image encoder of SAM is fine-tuned to produce probability masks for roads and intersections, from which the graph vertices are extracted via simple non-maximum suppression. To predict graph topology, we designed a lightweight transformer-based graph neural network, which leverages the SAM image embeddings to estimate the edge existence probabilities between vertices. Our approach directly predicts the graph vertices and edges for large regions without expensive and complex post-processing heuristics, and is capable of building complete road network graphs spanning multiple square kilometers in a matter of seconds. With its simple, straightforward, and minimalist design, SAM-Road achieves comparable accuracy with the state-of-the-art method RNGDet++, while being 40 times faster on the City-scale dataset. We thus demonstrate the power of a foundational vision model when applied to a graph learning task. The code is available at https://github.com/htcr/sam_road.

23 September 2023 in arXiv
Verified
Preprint
Open access
PDF file
YHYihui He
Yihui He
JQJianing Qian
Jianing Qian
JWJianren Wang
Jianren Wang
CLCindy X. Le
Cindy X. Le
CHCongrui Hetang
Congrui Hetang
TYTianwei Yue
Tianwei Yue
Very deep convolutional neural networks (CNNs) have been firmly established as the primary methods for many computer vision tasks. However, most state-of-the-art CNNs are large, which results in high inference latency. Recently, depth-wise separable convolution has been proposed for image recognition tasks on computationally limited platforms such as robotics and self-driving cars. Though it is much faster than its counterpart, regular convolution, accuracy is sacrificed. In this paper, we propose a novel decomposition approach based on SVD, namely depth-wise decomposition, for expanding regular convolutions into depthwise separable convolutions while maintaining high accuracy. We show our approach can be further generalized to the multi-channel and multi-layer cases, based on Generalized Singular Value Decomposition (GSVD) [59]. We conduct thorough experiments with the latest ShuffleNet V2 model [47] on both random synthesized dataset and a large-scale image recognition dataset: ImageNet [10]. Our approach outperforms channel decomposition [73] on all datasets. More importantly, our approach improves the Top-1 accuracy of ShuffleNet V2 by ~2%.