Search Results for author: Tao Chen

Found 198 papers, 91 papers with code

Relating CNN-Transformer Fusion Network for Change Detection

1 code implementation3 Jul 2024 Yuhao Gao, Gensheng Pei, Mengmeng Sheng, Zeren Sun, Tao Chen, Yazhou Yao

While deep learning, particularly convolutional neural networks (CNNs), has revolutionized remote sensing (RS) change detection (CD), existing approaches often miss crucial features due to neglecting global context and incomplete change learning.

Change Detection Decoder

Knowledge Transfer with Simulated Inter-Image Erasing for Weakly Supervised Semantic Segmentation

1 code implementation3 Jul 2024 Tao Chen, Xiruo Jiang, Gensheng Pei, Zeren Sun, Yucheng Wang, Yazhou Yao

Considering the adopted bidirectional alignment will also weaken the anchor image activation if appropriate constraints are missing, we propose a self-supervised regularization module to maintain the reliable activation in discriminative regions and improve the inter-class object boundary recognition for complex images with multiple categories of objects.

Object Object Discovery +3

Foster Adaptivity and Balance in Learning with Noisy Labels

no code implementations3 Jul 2024 Mengmeng Sheng, Zeren Sun, Tao Chen, Shuchao Pang, Yucheng Wang, Yazhou Yao

Moreover, existing methods tend to neglect the class balance in selecting samples, leading to biased model performance.

Learning with noisy labels

HiDiff: Hybrid Diffusion Framework for Medical Image Segmentation

1 code implementation3 Jul 2024 Tao Chen, Chenhui Wang, Zhihao Chen, Yiming Lei, Hongming Shan

In this work, we propose to complement discriminative segmentation methods with the knowledge of underlying data distribution from generative models.

Image Segmentation Medical Image Segmentation +2

Lightweight Model Pre-training via Language Guided Knowledge Distillation

1 code implementation17 Jun 2024 Mingsheng Li, Lin Zhang, Mingzhen Zhu, Zilong Huang, Gang Yu, Jiayuan Fan, Tao Chen

In this paper, for the first time, we introduce language guidance to the distillation process and propose a new method named Language-Guided Distillation (LGD) system, which uses category names of the target downstream task to help refine the knowledge transferred between the teacher and student.

Knowledge Distillation

Adapter-X: A Novel General Parameter-Efficient Fine-Tuning Framework for Vision

no code implementations5 Jun 2024 Minglei Li, Peng Ye, Yongqi Huang, Lin Zhang, Tao Chen, Tong He, Jiayuan Fan, Wanli Ouyang

Parameter-efficient fine-tuning (PEFT) has become increasingly important as foundation models continue to grow in both popularity and size.

3D Classification

FNP: Fourier Neural Processes for Arbitrary-Resolution Data Assimilation

no code implementations3 Jun 2024 Kun Chen, Tao Chen, Peng Ye, Hao Chen, Kang Chen, Tao Han, Wanli Ouyang, Lei Bai

Data assimilation is a vital component in modern global medium-range weather forecasting systems to obtain the best estimation of the atmospheric state by combining the short-term forecast and observations.

Weather Forecasting

$Δ$-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers

no code implementations3 Jun 2024 Pengtao Chen, Mingzhu Shen, Peng Ye, JianJian Cao, Chongjun Tu, Christos-Savvas Bouganis, Yiren Zhao, Tao Chen

Based on this insight, we propose an overall training-free inference acceleration framework $\Delta$-DiT: using a designed cache mechanism to accelerate the rear DiT blocks in the early sampling stages and the front DiT blocks in the later stages.

Image Generation

MeshXL: Neural Coordinate Field for Generative 3D Foundation Models

1 code implementation31 May 2024 Sijin Chen, Xin Chen, Anqi Pang, Xianfang Zeng, Wei Cheng, Yijun Fu, Fukun Yin, Yanru Wang, Zhibin Wang, Chi Zhang, Jingyi Yu, Gang Yu, Bin Fu, Tao Chen

The polygon mesh representation of 3D data exhibits great flexibility, fast rendering speed, and storage efficiency, which is widely preferred in various applications.

Language Modelling Large Language Model

FLDM-VTON: Faithful Latent Diffusion Model for Virtual Try-on

no code implementations22 Apr 2024 Chenhui Wang, Tao Chen, Zhihao Chen, Zhizhong Huang, Taoran Jiang, Qi Wang, Hongming Shan

Despite their impressive generative performance, latent diffusion model-based virtual try-on (VTON) methods lack faithfulness to crucial details of the clothes, such as style, pattern, and text.

Virtual Try-on

Multimodal Emotion Recognition by Fusing Video Semantic in MOOC Learning Scenarios

no code implementations11 Apr 2024 Yuan Zhang, Xiaomei Tao, Hanxu Ai, Tao Chen, Yanling Gan

The method proposed in this paper not only contributes to a deeper understanding of the impact of instructional videos on learners' emotional states but also provides a beneficial reference for future research on emotion recognition in MOOC learning scenarios.

Language Modelling Large Language Model +2

Adapting Multi-objectivized Software Configuration Tuning

1 code implementation6 Apr 2024 Tao Chen, Miqing Li

Experiments on several real-world systems, objectives, and budgets show that, for 71% of the cases, AdMMO is considerably superior to MMO and a wide range of state-of-the-art optimizers while achieving generally better efficiency with the best speedup between 2. 2x and 20x.

Once for Both: Single Stage of Importance and Sparsity Search for Vision Transformer Compression

1 code implementation CVPR 2024 Hancheng Ye, Chong Yu, Peng Ye, Renqiu Xia, Yansong Tang, Jiwen Lu, Tao Chen, Bo Zhang

Recent Vision Transformer Compression (VTC) works mainly follow a two-stage scheme, where the importance score of each model unit is first evaluated or preset in each submodule, followed by the sparsity score evaluation according to the target sparsity constraint.

Dimensionality Reduction

Learning Physical Dynamics for Object-centric Visual Prediction

no code implementations15 Mar 2024 Huilin Xu, Tao Chen, Feng Xu

The ability to model the underlying dynamics of visual scenes and reason about the future is central to human intelligence.

Object

Chaotic Masking Protocol for Secure Communication and Attack Detection in Remote Estimation of Cyber-Physical Systems

no code implementations14 Mar 2024 Tao Chen, Andreu Cecilia, Daniele Astolfi, Lei Wang, Zhitao Liu, Hongye Su

In remote estimation of cyber-physical systems (CPSs), sensor measurements transmitted through network may be attacked by adversaries, leading to leakage risk of privacy (e. g., the system state), and/or failure of the remote estimator.

Enhanced Sparsification via Stimulative Training

no code implementations11 Mar 2024 Shengji Tang, Weihao Lin, Hancheng Ye, Peng Ye, Chong Yu, Baopu Li, Tao Chen

To alleviate this issue, we first study and reveal the relative sparsity effect in emerging stimulative training and then propose a structured pruning framework, named STP, based on an enhanced sparsification paradigm which maintains the magnitude of dropped weights and enhances the expressivity of kept weights by self-distillation.

Knowledge Distillation Model Compression

Low-dose CT Denoising with Language-engaged Dual-space Alignment

1 code implementation10 Mar 2024 Zhihao Chen, Tao Chen, Chenhui Wang, Chuang Niu, Ge Wang, Hongming Shan

While various deep learning methods were proposed for low-dose computed tomography (CT) denoising, they often suffer from over-smoothing, blurring, and lack of explainability.

Computed Tomography (CT) Denoising

Reconciling Reality through Simulation: A Real-to-Sim-to-Real Approach for Robust Manipulation

no code implementations6 Mar 2024 Marcel Torne, Anthony Simeonov, Zechu Li, April Chan, Tao Chen, Abhishek Gupta, Pulkit Agrawal

To learn performant, robust policies without the burden of unsafe real-world data collection or extensive human supervision, we propose RialTo, a system for robustifying real-world imitation learning policies via reinforcement learning in "digital twin" simulation environments constructed on the fly from small amounts of real-world data.

Imitation Learning reinforcement-learning

Cascaded Self-supervised Learning for Subject-independent EEG-based Emotion Recognition

no code implementations6 Mar 2024 Hanqi Wang, Tao Chen, Liang Song

Inspired by recent efforts in combining low-level and high-level tasks in deep learning, we propose a cascaded self-supervised architecture for EEG emotion recognition.

Contrastive Learning EEG +2

MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer

1 code implementation CVPR 2024 JianJian Cao, Peng Ye, Shengze Li, Chong Yu, Yansong Tang, Jiwen Lu, Tao Chen

To this end, we propose a novel framework named Multimodal Alignment-Guided Dynamic Token Pruning (MADTP) for accelerating various VLTs.

Deep Configuration Performance Learning: A Systematic Survey and Taxonomy

1 code implementation5 Mar 2024 Jingzhi Gong, Tao Chen

Performance is arguably the most crucial attribute that reflects the quality of a configurable software system.

Attribute

VideoMAC: Video Masked Autoencoders Meet ConvNets

1 code implementation CVPR 2024 Gensheng Pei, Tao Chen, Xiruo Jiang, Huafeng Liu, Zeren Sun, Yazhou Yao

In this paper, we propose a new approach termed as \textbf{VideoMAC}, which combines video masked autoencoders with resource-friendly ConvNets.

Pose Tracking Representation Learning +4

Unlocking the `Why' of Buying: Introducing a New Dataset and Benchmark for Purchase Reason and Post-Purchase Experience

no code implementations20 Feb 2024 Tao Chen, Siqi Zuo, Cheng Li, Mingyang Zhang, Qiaozhu Mei, Michael Bendersky

To this end, we introduce an LLM-based approach to generate a dataset that consists of textual explanations of why real users make certain purchase decisions.

Explanation Generation Recommendation Systems

Predicting Configuration Performance in Multiple Environments with Sequential Meta-learning

1 code implementation5 Feb 2024 Jingzhi Gong, Tao Chen

Through comparing with 15 state-of-the-art models under nine systems, our extensive experimental results demonstrate that SeMPL performs considerably better on 89% of the systems with up to 99% accuracy improvement, while being data-efficient, leading to a maximum of 3. 86x speedup.

Meta-Learning

ClipSAM: CLIP and SAM Collaboration for Zero-Shot Anomaly Segmentation

1 code implementation23 Jan 2024 Shengze Li, JianJian Cao, Peng Ye, Yuhan Ding, Chongjun Tu, Tao Chen

Recently, foundational models such as CLIP and SAM have shown promising performance for the task of Zero-Shot Anomaly Segmentation (ZSAS).

Segmentation

Spatial Structure Constraints for Weakly Supervised Semantic Segmentation

1 code implementation20 Jan 2024 Tao Chen, Yazhou Yao, Xingguo Huang, Zechao Li, Liqiang Nie, Jinhui Tang

In this paper, we propose spatial structure constraints (SSC) for weakly supervised semantic segmentation to alleviate the unwanted object over-activation of attention expansion.

Object Object Localization +2

HOPE: Hybrid-granularity Ordinal Prototype Learning for Progression Prediction of Mild Cognitive Impairment

1 code implementation19 Jan 2024 Chenhui Wang, Yiming Lei, Tao Chen, Junping Zhang, Yuxin Li, Hongming Shan

Inspired by that various longitudinal biomarkers and cognitive measurements present an ordinal pathway on AD progression, we propose a novel Hybrid-granularity Ordinal PrototypE learning (HOPE) method to characterize AD ordinal progression for MCI progression prediction.

IQAGPT: Image Quality Assessment with Vision-language and ChatGPT Models

no code implementations25 Dec 2023 Zhihao Chen, Bin Hu, Chuang Niu, Tao Chen, Yuxin Li, Hongming Shan, Ge Wang

Second, we fine-tune the image quality captioning VLM on the CT-IQA dataset to generate quality descriptions.

Image Quality Assessment

Partial Fine-Tuning: A Successor to Full Fine-Tuning for Vision Transformers

no code implementations25 Dec 2023 Peng Ye, Yongqi Huang, Chongjun Tu, Minglei Li, Tao Chen, Tong He, Wanli Ouyang

We first validate eight manually-defined partial fine-tuning strategies across kinds of datasets and vision transformer architectures, and find that some partial fine-tuning strategies (e. g., ffn only or attention only) can achieve better performance with fewer tuned parameters than full fine-tuning, and selecting appropriate layers is critical to partial fine-tuning.

Merging Vision Transformers from Different Tasks and Domains

no code implementations25 Dec 2023 Peng Ye, Chenyu Huang, Mingzhu Shen, Tao Chen, Yongqi Huang, Yuning Zhang, Wanli Ouyang

This work targets to merge various Vision Transformers (ViTs) trained on different tasks (i. e., datasets with different object categories) or domains (i. e., datasets with the same categories but different environments) into one unified model, yielding still good performance on each task or domain.

Make-A-Character: High Quality Text-to-3D Character Generation within Minutes

no code implementations24 Dec 2023 Jianqiang Ren, Chao He, Lin Liu, Jiahao Chen, Yutong Wang, Yafei Song, Jianfang Li, Tangli Xue, Siqi Hu, Tao Chen, Kunkun Zheng, Jianjing Xiang, Liefeng Bo

There is a growing demand for customized and expressive 3D characters with the emergence of AI agents and Metaverse, but creating 3D characters using traditional computer graphics tools is a complex and time-consuming task.

3D Generation Text to 3D

Efficient Architecture Search via Bi-level Data Pruning

no code implementations21 Dec 2023 Chongjun Tu, Peng Ye, Weihao Lin, Hancheng Ye, Chong Yu, Tao Chen, Baopu Li, Wanli Ouyang

Improving the efficiency of Neural Architecture Search (NAS) is a challenging but significant task that has received much attention.

Neural Architecture Search

Rethinking of Feature Interaction for Multi-task Learning on Dense Prediction

no code implementations21 Dec 2023 Jingdong Zhang, Jiayuan Fan, Peng Ye, Bo Zhang, Hancheng Ye, Baopu Li, Yancheng Cai, Tao Chen

In this work, we propose to learn a comprehensive intermediate feature globally from both task-generic and task-specific features, we reveal an important fact that this intermediate feature, namely the bridge feature, is a good solution to the above issues.

Decoder Multi-Task Learning

Towards an end-to-end artificial intelligence driven global weather forecasting system

no code implementations18 Dec 2023 Kun Chen, Lei Bai, Fenghua Ling, Peng Ye, Tao Chen, Jing-Jia Luo, Hao Chen, Yi Xiao, Kang Chen, Tao Han, Wanli Ouyang

Initial states are typically generated by traditional data assimilation components, which are computational expensive and time-consuming.

Weather Forecasting

M3DBench: Let's Instruct Large Models with Multi-modal 3D Prompts

1 code implementation17 Dec 2023 Mingsheng Li, Xin Chen, Chi Zhang, Sijin Chen, Hongyuan Zhu, Fukun Yin, Gang Yu, Tao Chen

Furthermore, we establish a new benchmark for assessing the performance of large models in understanding multi-modal 3D prompts.

Instruction Following

Hierarchical Graph Pattern Understanding for Zero-Shot VOS

1 code implementation15 Dec 2023 Gensheng Pei, Fumin Shen, Yazhou Yao, Tao Chen, Xian-Sheng Hua, Heng-Tao Shen

However, existing optical flow-based methods have a significant dependency on optical flow, which results in poor performance when the optical flow estimation fails for a particular scene.

Decoder Graph Neural Network +6

Adaptive Integration of Partial Label Learning and Negative Learning for Enhanced Noisy Label Learning

no code implementations15 Dec 2023 Mengmeng Sheng, Zeren Sun, Zhenhuang Cai, Tao Chen, Yichao Zhou, Yazhou Yao

There has been significant attention devoted to the effectiveness of various domains, such as semi-supervised learning, contrastive learning, and meta-learning, in enhancing the performance of methods for noisy label learning (NLL) tasks.

Contrastive Learning Meta-Learning +1

MMICT: Boosting Multi-Modal Fine-Tuning with In-Context Examples

no code implementations11 Dec 2023 Tao Chen, Enwei Zhang, Yuting Gao, Ke Li, Xing Sun, Yan Zhang, Hui Li

Although In-Context Learning (ICL) brings remarkable performance gains to Large Language Models (LLMs), the improvements remain lower than fine-tuning on downstream tasks.

In-Context Learning

LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning

1 code implementation30 Nov 2023 Sijin Chen, Xin Chen, Chi Zhang, Mingsheng Li, Gang Yu, Hao Fei, Hongyuan Zhu, Jiayuan Fan, Tao Chen

However, developing LMMs that can comprehend, reason, and plan in complex and diverse 3D environments remains a challenging topic, especially considering the demand for understanding permutation-invariant point cloud 3D representations of the 3D scene.

3D dense captioning Dense Captioning +1

ShapeGPT: 3D Shape Generation with A Unified Multi-modal Language Model

no code implementations29 Nov 2023 Fukun Yin, Xin Chen, Chi Zhang, Biao Jiang, Zibo Zhao, Jiayuan Fan, Gang Yu, Taihao Li, Tao Chen

The advent of large language models, enabling flexibility through instruction-driven approaches, has revolutionized many traditional generative tasks, but large models for 3D data, particularly in comprehensively handling 3D shapes with other modalities, are still under-explored.

3D Shape Generation Language Modelling +1

Creator Context for Tweet Recommendation

no code implementations29 Nov 2023 Spurthi Amba Hombaiah, Tao Chen, Mingyang Zhang, Michael Bendersky, Marc Najork, Matt Colen, Sergey Levi, Vladimir Ofitserov, Tanvir Amin

In other words, grounding the interpretation of the tweet in the context of its creator plays an important role in deciphering the true intent and the importance of the tweet.

DECap: Towards Generalized Explicit Caption Editing via Diffusion Mechanism

no code implementations25 Nov 2023 Zhen Wang, Xinyun Jiang, Jun Xiao, Tao Chen, Long Chen

The denoising process involves the explicit predictions of edit operations and corresponding content words, refining reference captions through iterative step-wise editing.

Caption Generation Denoising +1

Deep Calibration of Market Simulations using Neural Density Estimators and Embedding Networks

no code implementations20 Nov 2023 Namid R. Stillman, Rory Baggott, Justin Lyon, Jianfei Zhang, Dingqiu Zhu, Tao Chen, Perukrishnen Vytelingum

The ability to construct a realistic simulator of financial exchanges, including reproducing the dynamics of the limit order book, can give insight into many counterfactual scenarios, such as a flash crash, a margin call, or changes in macroeconomic outlook.

counterfactual

Deep Learning-Based Frequency Offset Estimation

no code implementations8 Nov 2023 Tao Chen, Shilian Zheng, Jiawei Zhu, Qi Xuan, Xiaoniu Yang

In wireless communication systems, the asynchronization of the oscillators in the transmitter and the receiver along with the Doppler shift due to relative movement may lead to the presence of carrier frequency offset (CFO) in the received signals.

SpVOS: Efficient Video Object Segmentation with Triple Sparse Convolution

no code implementations23 Oct 2023 Weihao Lin, Tao Chen, Chong Yu

Therefore, we propose a sparse baseline of VOS named SpVOS in this work, which develops a novel triple sparse convolution to reduce the computation costs of the overall VOS framework.

Object Semantic Segmentation +2

VQ-NeRF: Vector Quantization Enhances Implicit Neural Representations

no code implementations23 Oct 2023 Yiying Yang, Wen Liu, Fukun Yin, Xin Chen, Gang Yu, Jiayuan Fan, Tao Chen

Recent advancements in implicit neural representations have contributed to high-fidelity surface reconstruction and photorealistic novel view synthesis.

Decoder Novel View Synthesis +2

Lifelong Robot Learning with Human Assisted Language Planners

no code implementations25 Sep 2023 Meenal Parakh, Alisha Fong, Anthony Simeonov, Tao Chen, Abhishek Gupta, Pulkit Agrawal

Large Language Models (LLMs) have been shown to act like planners that can decompose high-level instructions into a sequence of executable instructions.

Robust Geometry-Preserving Depth Estimation Using Differentiable Rendering

no code implementations ICCV 2023 Chi Zhang, Wei Yin, Gang Yu, Zhibin Wang, Tao Chen, Bin Fu, Joey Tianyi Zhou, Chunhua Shen

In this paper, we propose a learning framework that trains models to predict geometry-preserving depth without requiring extra data or annotations.

Monocular Depth Estimation

Rethinking Cross-Domain Pedestrian Detection: A Background-Focused Distribution Alignment Framework for Instance-Free One-Stage Detectors

1 code implementation15 Sep 2023 Yancheng Cai, Bo Zhang, Baopu Li, Tao Chen, Hongliang Yan, Jingdong Zhang, Jiahao Xu

Therefore, we focus on cross-domain background feature alignment while minimizing the influence of foreground features on the cross-domain alignment stage.

Pedestrian Detection

ReSimAD: Zero-Shot 3D Domain Transfer for Autonomous Driving with Source Reconstruction and Target Simulation

2 code implementations11 Sep 2023 Bo Zhang, Xinyu Cai, Jiakang Yuan, Donglin Yang, Jianfei Guo, Xiangchao Yan, Renqiu Xia, Botian Shi, Min Dou, Tao Chen, Si Liu, Junchi Yan, Yu Qiao

Domain shifts such as sensor type changes and geographical situation variations are prevalent in Autonomous Driving (AD), which poses a challenge since AD model relying on the previous domain knowledge can be hardly directly deployed to a new domain without additional costs.

Autonomous Driving Domain Generalization

MLN-net: A multi-source medical image segmentation method for clustered microcalcifications using multiple layer normalization

1 code implementation6 Sep 2023 Ke Wang, Zanting Ye, Xiang Xie, Haidong Cui, Tao Chen, Banteng Liu

Extensive experiments validate the effectiveness of MLN-net in segmenting clustered microcalcifications from different domains and the its segmentation accuracy surpasses state-of-the-art methods.

Image Augmentation Image Segmentation +3

Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioning

1 code implementation6 Sep 2023 Sijin Chen, Hongyuan Zhu, Mingsheng Li, Xin Chen, Peng Guo, Yinjie Lei, Gang Yu, Taihao Li, Tao Chen

Moreover, we argue that object localization and description generation require different levels of scene understanding, which could be challenging for a shared set of queries to capture.

3D dense captioning Caption Generation +4

Boosting Residual Networks with Group Knowledge

1 code implementation26 Aug 2023 Shengji Tang, Peng Ye, Baopu Li, Weihao Lin, Tao Chen, Tong He, Chong Yu, Wanli Ouyang

Specifically, we implicitly divide all subnets into hierarchical groups by subnet-in-subnet sampling, aggregate the knowledge of different subnets in each group during training, and exploit upper-level group knowledge to supervise lower-level subnet groups.

Knowledge Distillation

MMAPS: End-to-End Multi-Grained Multi-Modal Attribute-Aware Product Summarization

1 code implementation22 Aug 2023 Tao Chen, Ze Lin, Hui Li, Jiayi Ji, Yiyi Zhou, Guanbin Li, Rongrong Ji

Furthermore, we model product attributes based on both text and image modalities so that multi-modal product characteristics can be manifested in the generated summaries.

Attribute

Experts Weights Averaging: A New General Training Scheme for Vision Transformers

no code implementations11 Aug 2023 Yongqi Huang, Peng Ye, Xiaoshui Huang, Sheng Li, Tao Chen, Tong He, Wanli Ouyang

As Vision Transformers (ViTs) are gradually surpassing CNNs in various visual tasks, one may question: if a training scheme specifically for ViTs exists that can also achieve performance improvement without increasing inference cost?

Parallel $Q$-Learning: Scaling Off-policy Reinforcement Learning under Massively Parallel Simulation

no code implementations24 Jul 2023 Zechu Li, Tao Chen, Zhang-Wei Hong, Anurag Ajay, Pulkit Agrawal

This paper presents a Parallel $Q$-Learning (PQL) scheme that outperforms PPO in wall-clock time while maintaining superior sample efficiency of off-policy learning.

Q-Learning reinforcement-learning

Attention Consistency Refined Masked Frequency Forgery Representation for Generalizing Face Forgery Detection

1 code implementation21 Jul 2023 Decheng Liu, Tao Chen, Chunlei Peng, Nannan Wang, Ruimin Hu, Xinbo Gao

Due to the successful development of deep image generation technology, visual data forgery detection would play a more important role in social and economic security.

Image Generation

Breadcrumbs to the Goal: Goal-Conditioned Exploration from Human-in-the-Loop Feedback

1 code implementation20 Jul 2023 Marcel Torne, Max Balsells, Zihan Wang, Samedh Desai, Tao Chen, Pulkit Agrawal, Abhishek Gupta

This procedure can leverage noisy, asynchronous human feedback to learn policies with no hand-crafted reward design or exploration bonuses.

Decision Making reinforcement-learning +1

Holistic Prototype Attention Network for Few-Shot VOS

1 code implementation16 Jul 2023 Yin Tang, Tao Chen, Xiruo Jiang, Yazhou Yao, Guo-Sen Xie, Heng-Tao Shen

Existing methods have demonstrated that the domain agent-based attention mechanism is effective in FSVOS by learning the correlation between support images and query frames.

Graph Attention Semantic Segmentation +2

Coordinating O&M and Logistical Resources to Enhance Post-Disaster Resilience of Interdependent Power and Natural Gas Distribution Systems

no code implementations28 Jun 2023 Wei Wang, Kaigui Xie, Hongbin Wang, Tao Chen, Hongzhou Chen, Yufei He

Electric power and natural gas systems are becoming increasingly interdependent, driven by the growth of natural gas-fired generation and the electrification of the gas industry.

Scheduling

MotionGPT: Human Motion as a Foreign Language

2 code implementations NeurIPS 2023 Biao Jiang, Xin Chen, Wen Liu, Jingyi Yu, Gang Yu, Tao Chen

Building upon this "motion vocabulary", we perform language modeling on both motion and text in a unified manner, treating human motion as a specific language.

Language Modelling Motion Captioning +2

Exploring Multi-Timestep Multi-Stage Diffusion Features for Hyperspectral Image Classification

1 code implementation15 Jun 2023 Jingyi Zhou, Jiamu Sheng, Jiayuan Fan, Peng Ye, Tong He, Bin Wang, Tao Chen

To address this issue, we propose a novel diffusion-based feature learning framework that explores Multi-Timestep Multi-Stage Diffusion features for HSI classification for the first time, called MTMSD.

Classification Hyperspectral Image Classification

QuadSwarm: A Modular Multi-Quadrotor Simulator for Deep Reinforcement Learning with Direct Thrust Control

1 code implementation15 Jun 2023 Zhehui Huang, Sumeet Batra, Tao Chen, Rahul Krupani, Tushar Kumar, Artem Molchanov, Aleksei Petrenko, James A. Preiss, Zhaojing Yang, Gaurav S. Sukhatme

In addition to speed, such simulators need to model the physics of the robots and their interaction with the environment to a level acceptable for transferring policies learned in simulation to reality.

Reinforcement Learning (RL)

Predicting Software Performance with Divide-and-Learn

1 code implementation11 Jun 2023 Jingzhi Gong, Tao Chen

Predicting the performance of highly configurable software systems is the foundation for performance testing and quality assurance.

AD-PT: Autonomous Driving Pre-Training with Large-scale Point Cloud Dataset

1 code implementation NeurIPS 2023 Jiakang Yuan, Bo Zhang, Xiangchao Yan, Tao Chen, Botian Shi, Yikang Li, Yu Qiao

It is a long-term vision for Autonomous Driving (AD) community that the perception models can learn from a large-scale point cloud dataset, to obtain unified representations that can achieve promising results on different tasks or benchmarks.

Autonomous Driving Point Cloud Pre-training

Boost Vision Transformer with GPU-Friendly Sparsity and Quantization

no code implementations CVPR 2023 Chong Yu, Tao Chen, Zhongxue Gan, Jiayuan Fan

Moreover, GPUSQ-ViT can boost actual deployment performance by 1. 39-1. 79 times and 3. 22-3. 43 times of latency and throughput on A100 GPU, and 1. 57-1. 69 times and 2. 11-2. 51 times improvement of latency and throughput on AGX Orin.

Benchmarking Knowledge Distillation +1

Multi-Granularity Denoising and Bidirectional Alignment for Weakly Supervised Semantic Segmentation

1 code implementation9 May 2023 Tao Chen, Yazhou Yao, Jinhui Tang

Weakly supervised semantic segmentation (WSSS) models relying on class activation maps (CAMs) have achieved desirable performance comparing to the non-CAMs-based counterparts.

Denoising Image Generation +2

Stimulative Training++: Go Beyond The Performance Limits of Residual Networks

no code implementations4 May 2023 Peng Ye, Tong He, Shengji Tang, Baopu Li, Tao Chen, Lei Bai, Wanli Ouyang

In this work, we aim to re-investigate the training process of residual networks from a novel social psychology perspective of loafing, and further propose a new training scheme as well as three improved strategies for boosting residual networks beyond their performance limits.

Revolutionizing Agrifood Systems with Artificial Intelligence: A Survey

no code implementations3 May 2023 Tao Chen, Liang Lv, Di Wang, Jing Zhang, Yue Yang, Zeyang Zhao, Chen Wang, Xiaowei Guo, Hao Chen, Qingye Wang, Yufei Xu, Qiming Zhang, Bo Du, Liangpei Zhang, DaCheng Tao

With the world population rapidly increasing, transforming our agrifood systems to be more productive, efficient, safe, and sustainable is crucial to mitigate potential food shortages.

PGPointNovo: an efficient neural network-based tool for parallel de novo peptide sequencing

1 code implementation Bioinformatics Advances 2023 Xiaofang Xu, Chunde Yang, Qiang He, Kunxian Shu, Yuan Xinpu, Zhiguang Chen, Yunping Zhu, Tao Chen

De novo peptide sequencing for tandem mass spectrometry data is not only a key technology for novel peptide identification, but also a precedent task for many downstream tasks, such as vaccine and antibody studies.

de novo peptide sequencing Efficient Neural Network

Semi-Supervised Semantic Segmentation With Region Relevance

1 code implementation23 Apr 2023 Rui Chen, Tao Chen, Qiong Wang, Yazhou Yao

The most common approach is to generate pseudo-labels for unlabeled images to augment the training data.

Diversity Pseudo Label +3

Multi-view Vision-Prompt Fusion Network: Can 2D Pre-trained Model Boost 3D Point Cloud Data-scarce Learning?

no code implementations20 Apr 2023 Haoyang Peng, Baopu Li, Bo Zhang, Xin Chen, Tao Chen, Hongyuan Zhu

Then, a novel multi-view prompt fusion module is developed to effectively fuse information from different views to bridge the gap between 3D point cloud data and 2D pre-trained models.

Autonomous Driving Classification +3

BerDiff: Conditional Bernoulli Diffusion Model for Medical Image Segmentation

no code implementations10 Apr 2023 Tao Chen, Chenhui Wang, Hongming Shan

Second, by leveraging the stochastic nature of the diffusion model, our BerDiff randomly samples the initial Bernoulli noise and intermediate latent variables multiple times to produce a range of diverse segmentation masks, which can highlight salient regions of interest that can serve as valuable references for radiologists.

Image Segmentation Medical Image Segmentation +2

A Closer Look at Few-Shot 3D Point Cloud Classification

1 code implementation31 Mar 2023 Chuangguan Ye, Hongyuan Zhu, Bo Zhang, Tao Chen

In recent years, research on few-shot learning (FSL) has been fast-growing in the 2D image domain due to the less requirement for labeled training data and greater generalization for novel classes.

Few-Shot 3D Point Cloud Classification Few-Shot Learning +1

What Makes for Effective Few-shot Point Cloud Classification?

1 code implementation31 Mar 2023 Chuangguan Ye, Hongyuan Zhu, Yongbin Liao, Yanggang Zhang, Tao Chen, Jiayuan Fan

Due to the emergence of powerful computing resources and large-scale annotated datasets, deep learning has seen wide applications in our daily life.

Benchmarking Classification +2

DexDeform: Dexterous Deformable Object Manipulation with Human Demonstrations and Differentiable Physics

no code implementations27 Mar 2023 Sizhe Li, Zhiao Huang, Tao Chen, Tao Du, Hao Su, Joshua B. Tenenbaum, Chuang Gan

Reinforcement learning approaches for dexterous rigid object manipulation would struggle in this setting due to the complexity of physics interaction with deformable objects.

Deformable Object Manipulation Object

TactoFind: A Tactile Only System for Object Retrieval

no code implementations23 Mar 2023 Sameer Pai, Tao Chen, Megha Tippur, Edward Adelson, Abhishek Gupta, Pulkit Agrawal

We study the problem of object retrieval in scenarios where visual sensing is absent, object shapes are unknown beforehand and objects can move freely, like grabbing objects out of a drawer.

Object Retrieval

Performance-aware Approximation of Global Channel Pruning for Multitask CNNs

1 code implementation21 Mar 2023 Hancheng Ye, Bo Zhang, Tao Chen, Jiayuan Fan, Bin Wang

Global channel pruning (GCP) aims to remove a subset of channels (filters) across different layers from a deep model without hurting the performance.

Model Compression

Tucker Bilinear Attention Network for Multi-scale Remote Sensing Object Detection

no code implementations9 Mar 2023 Tao Chen, Ruirui Li, Jiafeng Fu, Daguang Jiang

However, for small targets, there still be seriously missed detections due to the loss of key detail features.

Management Object +2

ConceptFusion: Open-set Multimodal 3D Mapping

1 code implementation14 Feb 2023 Krishna Murthy Jatavallabhula, Alihusein Kuwajerwala, Qiao Gu, Mohd Omama, Tao Chen, Alaa Maalouf, Shuang Li, Ganesh Iyer, Soroush Saryazdi, Nikhil Keetha, Ayush Tewari, Joshua B. Tenenbaum, Celso Miguel de Melo, Madhava Krishna, Liam Paull, Florian Shkurti, Antonio Torralba

ConceptFusion leverages the open-set capabilities of today's foundation models pre-trained on internet-scale data to reason about concepts across modalities such as natural language, images, and audio.

Autonomous Driving Robot Navigation

FECANet: Boosting Few-Shot Semantic Segmentation with Feature-Enhanced Context-Aware Network

1 code implementation19 Jan 2023 Huafeng Liu, Pai Peng, Tao Chen, Qiong Wang, Yazhou Yao, Xian-Sheng Hua

Few-shot semantic segmentation is the task of learning to locate each pixel of the novel class in the query image with only a few annotated support images.

Few-Shot Semantic Segmentation

$β$-DARTS++: Bi-level Regularization for Proxy-robust Differentiable Architecture Search

1 code implementation16 Jan 2023 Peng Ye, Tong He, Baopu Li, Tao Chen, Lei Bai, Wanli Ouyang

To address the robustness problem, we first benchmark different NAS methods under a wide range of proxy data, proxy channels, proxy layers and proxy epochs, since the robustness of NAS under different kinds of proxies has not been explored before.

Neural Architecture Search

Do Performance Aspirations Matter for Guiding Software Configuration Tuning?

1 code implementation9 Jan 2023 Tao Chen, Miqing Li

Before we design better optimizers, a crucial engineering decision to make therein is how to handle the performance requirements with clear aspirations in the tuning process.

Decision Making

End-to-End 3D Dense Captioning with Vote2Cap-DETR

1 code implementation CVPR 2023 Sijin Chen, Hongyuan Zhu, Xin Chen, Yinjie Lei, Tao Chen, Gang Yu

Compared with prior arts, our framework has several appealing advantages: 1) Without resorting to numerous hand-crafted components, our method is based on a full transformer encoder-decoder architecture with a learnable vote query driven object decoder, and a caption decoder that produces the dense captions in a set-prediction manner.

3D dense captioning Decoder +2

UnICLAM:Contrastive Representation Learning with Adversarial Masking for Unified and Interpretable Medical Vision Question Answering

no code implementations21 Dec 2022 Chenlu Zhan, Peng Peng, Hongsen Wang, Tao Chen, Hongwei Wang

Moreover, for grasping the unified semantic representation, we extend the adversarial masking data augmentation to the contrastive representation learning of vision and text in a unified manner.

Data Augmentation Decision Making +4

Executing your Commands via Motion Diffusion in Latent Space

1 code implementation CVPR 2023 Xin Chen, Biao Jiang, Wen Liu, Zilong Huang, Bin Fu, Tao Chen, Jingyi Yu, Gang Yu

We study a challenging task, conditional human motion generation, which produces plausible human motion sequences according to various conditional inputs, such as action classes or textual descriptors.

Motion Synthesis

Towards Accurate Ground Plane Normal Estimation from Ego-Motion

1 code implementation8 Dec 2022 Jiaxin Zhang, Wei Sui, Qian Zhang, Tao Chen, Cong Yang

In this paper, we introduce a novel approach for ground plane normal estimation of wheeled vehicles.

3D Object Detection Autonomous Driving +3

Visual Dexterity: In-Hand Reorientation of Novel and Complex Object Shapes

1 code implementation21 Nov 2022 Tao Chen, Megha Tippur, Siyang Wu, Vikash Kumar, Edward Adelson, Pulkit Agrawal

The controller is trained using reinforcement learning in simulation and evaluated in the real world on new object shapes not used for training, including the most challenging scenario of reorienting objects held in the air by a downward-facing hand that must counteract gravity during reorientation.

Object

Instance-aware Model Ensemble With Distillation For Unsupervised Domain Adaptation

no code implementations15 Nov 2022 Weimin Wu, Jiayuan Fan, Tao Chen, Hancheng Ye, Bo Zhang, Baopu Li

To enhance the model, adaptability between domains and reduce the computational cost when deploying the ensemble model, we propose a novel framework, namely Instance aware Model Ensemble With Distillation, IMED, which fuses multiple UDA component models adaptively according to different instances and distills these components into a small model.

Knowledge Distillation Unsupervised Domain Adaptation

Coordinates Are NOT Lonely -- Codebook Prior Helps Implicit Neural 3D Representations

1 code implementation20 Oct 2022 Fukun Yin, Wen Liu, Zilong Huang, Pei Cheng, Tao Chen, Gang Yu

Implicit neural 3D representation has achieved impressive results in surface or scene reconstruction and novel view synthesis, which typically uses the coordinate-based multi-layer perceptrons (MLPs) to learn a continuous scene representation.

Novel View Synthesis

Stimulative Training of Residual Networks: A Social Psychology Perspective of Loafing

1 code implementation9 Oct 2022 Peng Ye, Shengji Tang, Baopu Li, Tao Chen, Wanli Ouyang

In this work, we aim to re-investigate the training process of residual networks from a novel social psychology perspective of loafing, and further propose a new training strategy to strengthen the performance of residual networks.

Distilling Task-specific Logical Rules from Large Pre-trained Models

no code implementations6 Oct 2022 Tao Chen, Luxin Liu, Xuepeng Jia, Baoliang Cui, Haihong Tang, Siliang Tang

Specifically, we borrow recent prompt-based language models as the knowledge expert to yield initial seed rules, and based on the formed high-quality instance pool that acts as an intermediary role, we keep teaching the expert to fit our task and learning task-specific logical rules.

Multifaceted Hierarchical Report Identification for Non-Functional Bugs in Deep Learning Frameworks

1 code implementation4 Oct 2022 Guoming Long, Tao Chen, Georgina Cosma

Yet, given the growing number of new GitHub reports for DL frameworks, it is intrinsically difficult for developers to distinguish those that reveal non-functional bugs among the others, and assign them to the right contributor for investigation in a timely manner.

Watermark Vaccine: Adversarial Attacks to Prevent Watermark Removal

1 code implementation17 Jul 2022 Xinwei Liu, Jian Liu, Yang Bai, Jindong Gu, Tao Chen, Xiaojun Jia, Xiaochun Cao

Inspired by the vulnerability of DNNs on adversarial perturbations, we propose a novel defence mechanism by adversarial machine learning for good.

Saliency Guided Inter- and Intra-Class Relation Constraints for Weakly Supervised Semantic Segmentation

1 code implementation20 Jun 2022 Tao Chen, Yazhou Yao, Lei Zhang, Qiong Wang, Guo-Sen Xie, Fumin Shen

Specifically, we propose a saliency guided class-agnostic distance module to pull the intra-category features closer by aligning features to their class prototypes.

Object Pseudo Label +4

Rapid Locomotion via Reinforcement Learning

no code implementations5 May 2022 Gabriel B Margolis, Ge Yang, Kartik Paigwar, Tao Chen, Pulkit Agrawal

Agile maneuvers such as sprinting and high-speed turning in the wild are challenging for legged robots.

reinforcement-learning Reinforcement Learning (RL)

On Parametric Optimal Execution and Machine Learning Surrogates

1 code implementation18 Apr 2022 Tao Chen, Mike Ludkovski, Moritz Voß

Precise calibration of price impact, resilience, etc., is known to be extremely challenging and hence it is critical to understand sensitivity of the execution policy to these parameters.

BIG-bench Machine Learning

TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation

3 code implementations CVPR 2022 Wenqiang Zhang, Zilong Huang, Guozhong Luo, Tao Chen, Xinggang Wang, Wenyu Liu, Gang Yu, Chunhua Shen

Although vision transformers (ViTs) have achieved great success in computer vision, the heavy computational cost hampers their applications to dense prediction tasks such as semantic segmentation on mobile devices.

Segmentation Semantic Segmentation

Does Configuration Encoding Matter in Learning Software Performance? An Empirical Study on Encoding Schemes

1 code implementation30 Mar 2022 Jingzhi Gong, Tao Chen

Learning and predicting the performance of a configurable software system helps to provide better quality assurance.

Topological Experience Replay

1 code implementation ICLR 2022 Zhang-Wei Hong, Tao Chen, Yen-Chen Lin, Joni Pajarinen, Pulkit Agrawal

State-of-the-art deep Q-learning methods update Q-values using state transition tuples sampled from the experience replay buffer.

Q-Learning

Planning Landscape Analysis for Self-Adaptive Systems

no code implementations23 Mar 2022 Tao Chen

To assure performance on the fly, planning is arguably one of the most important steps for self-adaptive systems (SASs), especially when they are highly configurable with a daunting number of adaptation options.

$β$-DARTS: Beta-Decay Regularization for Differentiable Architecture Search

1 code implementation3 Mar 2022 Peng Ye, Baopu Li, Yikang Li, Tao Chen, Jiayuan Fan, Wanli Ouyang

Neural Architecture Search~(NAS) has attracted increasingly more attention in recent years because of its capability to design deep neural networks automatically.

Neural Architecture Search

Curriculum-style Local-to-global Adaptation for Cross-domain Remote Sensing Image Segmentation

1 code implementation3 Mar 2022 Bo Zhang, Tao Chen, Bin Wang

Although domain adaptation has been extensively studied in natural image-based segmentation task, the research on cross-domain segmentation for very high resolution (VHR) remote sensing images (RSIs) still remains underexplored.

Domain Adaptation Image Segmentation +2

The Weights can be Harmful: Pareto Search versus Weighted Search in Multi-Objective Search-Based Software Engineering

1 code implementation8 Feb 2022 Tao Chen, Miqing Li

However, when clear preferences of the stakeholders (e. g., a set of weights which reflect relative importance between objectives) are available prior to the search, weighted search is believed to be the first choice since it simplifies the search via converting the original multi-objective problem into a single-objective one and enable the search to focus on what only the stakeholders are interested in.

Pre-Trained Language Models for Interactive Decision-Making

1 code implementation3 Feb 2022 Shuang Li, Xavier Puig, Chris Paxton, Yilun Du, Clinton Wang, Linxi Fan, Tao Chen, De-An Huang, Ekin Akyürek, Anima Anandkumar, Jacob Andreas, Igor Mordatch, Antonio Torralba, Yuke Zhu

Together, these results suggest that language modeling induces representations that are useful for modeling not just language, but also goals and plans; these representations can aid learning and generalization even outside of language processing.

Imitation Learning Language Modelling

Out-of-Domain Semantics to the Rescue! Zero-Shot Hybrid Retrieval Models

no code implementations25 Jan 2022 Tao Chen, Mingyang Zhang, Jing Lu, Michael Bendersky, Marc Najork

In this work, we carefully select five datasets, including two in-domain datasets and three out-of-domain datasets with different levels of domain shift, and study the generalization of a deep model in a zero-shot setting.

Language Modelling Passage Retrieval +1

Lifelong Dynamic Optimization for Self-Adaptive Systems: Fact or Fiction?

no code implementations18 Jan 2022 Tao Chen

When faced with changing environment, highly configurable software systems need to dynamically search for promising adaptation plan that keeps the best possible performance, e. g., higher throughput or smaller latency -- a typical planning problem for self-adaptive systems (SASs).

Swin Transformer coupling CNNs Makes Strong Contextual Encoders for VHR Image Road Extraction

no code implementations10 Jan 2022 Tao Chen, Yiran Liu, Haoyu Jiang, Ruirui Li

While CNN excels at extracting local detail features, the Transformer naturally perceives global contextual information.

Decoder

b-DARTS: Beta-Decay Regularization for Differentiable Architecture Search

1 code implementation CVPR 2022 Peng Ye, Baopu Li, Yikang Li, Tao Chen, Jiayuan Fan, Wanli Ouyang

Neural Architecture Search (NAS) has attracted increasingly more attention in recent years because of its capability to design deep neural network automatically.

Neural Architecture Search

Neural Hierarchical Factorization Machines for User's Event Sequence Analysis

no code implementations31 Dec 2021 Dongbo Xi, Fuzhen Zhuang, Bowen Song, Yongchun Zhu, Shuai Chen, Dan Hong, Tao Chen, Xi Gu, Qing He

Many prediction tasks of real-world applications need to model multi-order feature interactions in user's event sequence for better detection performance.

Feature-context driven Federated Meta-Learning for Rare Disease Prediction

no code implementations29 Dec 2021 Bingyang Chen, Tao Chen, Xingjie Zeng, Weishan Zhang, Qinghua Lu, Zhaoxiang Hou, Jiehan Zhou, Sumi Helal

Additionally, a dynamic-weight based fusion strategy is proposed to further improve the accuracy of federated learning, which dynamically selects clients based on the accuracy of each local model.

Disease Prediction Federated Learning +1

MMO: Meta Multi-Objectivization for Software Configuration Tuning

1 code implementation14 Dec 2021 Pengzhou Chen, Tao Chen, Miqing Li

We also demonstrate that the MMO model with the new normalization can consolidate recent model-based tuning tools on 68% of the cases with up to 1. 22x speedup in general.

CO2Sum:Contrastive Learning for Factual-Consistent Abstractive Summarization

no code implementations2 Dec 2021 Wei Liu, Huanqin Wu, Wenjing Mu, Zhen Li, Tao Chen, Dan Nie

We propose CO2Sum (Contrastive for Consistency), a contrastive learning scheme that can be easily applied on sequence-to-sequence models for factual-consistent abstractive summarization, proving that the model can be fact-aware without modifying the architecture.

Abstractive Text Summarization Contrastive Learning +1

Point Cloud Instance Segmentation with Semi-supervised Bounding-Box Mining

1 code implementation30 Nov 2021 Yongbin Liao, Hongyuan Zhu, Yanggang Zhang, Chuangguan Ye, Tao Chen, Jiayuan Fan

For stage two, the bounding box proposals with SPCR are grouped into some subsets, and the instance masks are mined inside each subset with a novel semantic propagation module and a property consistency graph module.

Instance Segmentation Semantic Segmentation

A System for General In-Hand Object Re-Orientation

1 code implementation4 Nov 2021 Tao Chen, Jie Xu, Pulkit Agrawal

The videos of the learned policies are available at: https://taochenshh. github. io/projects/in-hand-reorientation.

Object

Fine-grained Identity Preserving Landmark Synthesis for Face Reenactment

no code implementations10 Oct 2021 Haichao Zhang, Youcheng Ben, Weixi Zhang, Tao Chen, Gang Yu, Bin Fu

Recent face reenactment works are limited by the coarse reference landmarks, leading to unsatisfactory identity preserving performance due to the distribution gap between the manipulated landmarks and those sampled from a real person.

Face Reenactment

Sketch Me A Video

no code implementations10 Oct 2021 Haichao Zhang, Gang Yu, Tao Chen, Guozhong Luo

Video creation has been an attractive yet challenging task for artists to explore.

Joint Distribution Alignment via Adversarial Learning for Domain Adaptive Object Detection

1 code implementation19 Sep 2021 Bo Zhang, Tao Chen, Bin Wang, Ruoyao Li

Unsupervised domain adaptive object detection aims to adapt a well-trained detector from its original source domain with rich labeled data to a new target domain with unlabeled data.

Object object-detection +2

Densely Semantic Enhancement for Domain Adaptive Region-free Detectors

no code implementations30 Aug 2021 Bo Zhang, Tao Chen, Bin Wang, Xiaofeng Wu, Liming Zhang, Jiayuan Fan

Unsupervised domain adaptive object detection aims to adapt a well-trained detector from its original source domain with rich labeled data to a new target domain with unlabeled data.

object-detection Object Detection +1

Object-aware Long-short-range Spatial Alignment for Few-Shot Fine-Grained Image Classification

no code implementations30 Aug 2021 Yike Wu, Bo Zhang, Gang Yu, Weixi Zhang, Bin Wang, Tao Chen, Jiayuan Fan

The goal of few-shot fine-grained image classification is to recognize rarely seen fine-grained objects in the query set, given only a few samples of this class in the support set.

Fine-Grained Image Classification Object +3

Concept-Based Label Embedding via Dynamic Routing for Hierarchical Text Classification

1 code implementation ACL 2021 Xuepeng Wang, Li Zhao, Bing Liu, Tao Chen, Feng Zhang, Di Wang

In this paper, we propose a novel concept-based label embedding method that can explicitly represent the concept and model the sharing mechanism among classes for the hierarchical text classification.

text-classification Text Classification

An End-to-End Differentiable Framework for Contact-Aware Robot Design

1 code implementation15 Jul 2021 Jie Xu, Tao Chen, Lara Zlokapa, Michael Foshey, Wojciech Matusik, Shinjiro Sueda, Pulkit Agrawal

Existing methods for co-optimization are limited and fail to explore a rich space of designs.

Empower Distantly Supervised Relation Extraction with Collaborative Adversarial Training

1 code implementation21 Jun 2021 Tao Chen, Haochen Shi, Liyuan Liu, Siliang Tang, Jian Shao, Zhigang Chen, Yueting Zhuang

In this paper, we propose collaborative adversarial training to improve the data utilization, which coordinates virtual adversarial training (VAT) and adversarial training (AT) at different levels.

Relation Relation Extraction

CIL: Contrastive Instance Learning Framework for Distantly Supervised Relation Extraction

1 code implementation ACL 2021 Tao Chen, Haizhou Shi, Siliang Tang, Zhigang Chen, Fei Wu, Yueting Zhuang

The journey of reducing noise from distant supervision (DS) generated training data has been started since the DS was first introduced into the relation extraction (RE) task.

Relation Relation Extraction +1

Dynamic Language Models for Continuously Evolving Content

no code implementations11 Jun 2021 Spurthi Amba Hombaiah, Tao Chen, Mingyang Zhang, Michael Bendersky, Marc Najork

To this end, we both explore two different vocabulary composition methods, as well as propose three sampling methods which help in efficient incremental training for BERT-like models.

UniKeyphrase: A Unified Extraction and Generation Framework for Keyphrase Prediction

1 code implementation Findings (ACL) 2021 Huanqin Wu, Wei Liu, Lei LI, Dan Nie, Tao Chen, Feng Zhang, Di Wang

Keyphrase Prediction (KP) task aims at predicting several keyphrases that can summarize the main idea of the given document.

Diversity Relation

Multi-Objectivizing Software Configuration Tuning (for a single performance concern)

no code implementations31 May 2021 Tao Chen, Miqing Li

Automatically tuning software configuration for optimizing a single performance attribute (e. g., minimizing latency) is not trivial, due to the nature of the configuration systems (e. g., complex landscape and expensive measurement).

Attribute

Gradient Descent in Materio

no code implementations15 May 2021 Marcus N. Boon, Hans-Christian Ruiz Euler, Tao Chen, Bram van de Ven, Unai Alegre Ibarra, Peter A. Bobbert, Wilfred G. van der Wiel

Here, we demonstrate an efficient and accurate homodyne gradient extraction method for performing gradient descent on the loss function directly in the material system.

LAMPRET: Layout-Aware Multimodal PreTraining for Document Understanding

no code implementations16 Apr 2021 Te-Lin Wu, Cheng Li, Mingyang Zhang, Tao Chen, Spurthi Amba Hombaiah, Michael Bendersky

text, table, image) and propose a novel layout-aware multimodal hierarchical framework, LAMPreT, to model the blocks and the whole document.

document understanding

Residual Model Learning for Microrobot Control

no code implementations1 Apr 2021 Joshua Gruenstein, Tao Chen, Neel Doshi, Pulkit Agrawal

RML provides a general framework for learning from extremely small amounts of interaction data, and our experiments with HAMR clearly demonstrate that RML substantially outperforms existing techniques.

EADNet: Efficient Asymmetric Dilated Network for Semantic Segmentation

no code implementations16 Mar 2021 Qihang Yang, Tao Chen, Jiayuan Fan, Ye Lu, Chongyan Zuo, Qinghua Chi

Due to real-time image semantic segmentation needs on power constrained edge devices, there has been an increasing desire to design lightweight semantic segmentation neural network, to simultaneously reduce computational cost and increase inference speed.

Segmentation Semantic Segmentation

Noncyclic Geometric Quantum Gates with Smooth Paths via Invariant-based Shortcuts

no code implementations1 Feb 2021 Li-Na Ji, Cheng-Yun Ding, Tao Chen, Zheng-Yuan Xue

Here, we propose a scheme to realize geometric quantum gates with noncyclic and nonadiabatic evolution via invariant-based shortcuts, where universal quantum gates can be induced in one step without path mutation and the gate time is also effectively shortened.