Search Results for author: Haoran Wang

Found 27 papers, 10 papers with code

Supervised Edge Attention Network for Accurate Image Instance Segmentation

1 code implementation ECCV 2020 Xier Chen, Yanchao Lian, Licheng Jiao, Haoran Wang, YanJie Gao, Shi Lingling

In this task, many works segment instance based on a bounding box from the box head, which means the quality of the detection also affects the completeness of the mask.

Instance Segmentation Semantic Segmentation

Can multi-label classification networks know what they don't know?

1 code implementation NeurIPS 2021 Haoran Wang, Weitang Liu, Alex Bocchieri, Yixuan Li

Our results show consistent improvement over previous methods that are based on the maximum-valued scores, which fail to capture joint information from multiple labels.

Classification Multi-class Classification +2

Efficient and Systematic Partitioning of Large and Deep Neural Networks for Parallelization

1 code implementation Part of the Lecture Notes in Computer Science book series 2021 Haoran Wang, Chong Li, Thibaut Tachon, Hongxing Wang, Sheng Yang, Sébastien Limet, Sophie Robert

We propose the Flex-Edge Recursive Graph and the Double Recursive Algorithm, successfully limiting our parallelization strategy generation to a linear complexity with a good quality of parallelization strategy.

Freeing Hybrid Distributed AI Training Configuration

1 code implementation Proceedings of the 29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering 2021 Haoran Wang

Hybrid Parallelism (HP), which applies different parallel strategies on different parts of DNNs, is more efficient but requires advanced configurations.

CONet: Channel Optimization for Convolutional Neural Networks

1 code implementation15 Aug 2021 Mahdi S. Hosseini, Jia Shu Zhang, Zhe Liu, Andre Fu, Jingxuan Su, Mathieu Tuli, Sepehr Hosseini, Arsh Kadakia, Haoran Wang, Konstantinos N. Plataniotis

To solve this, we introduce an efficient dynamic scaling algorithm -- CONet -- that automatically optimizes channel sizes across network layers for a given CNN.

Neural Architecture Search

Step-Wise Hierarchical Alignment Network for Image-Text Matching

no code implementations11 Jun 2021 Zhong Ji, Kexin Chen, Haoran Wang

Image-text matching plays a central role in bridging the semantic gap between vision and language.

Text Matching

Can multi-label classification networks know what they don’t know?

1 code implementation NeurIPS 2021 Haoran Wang, Weitang Liu, Alex Bocchieri, Yixuan Li

Our results show consistent improvement over previous methods that are based on the maximum-valued scores, which fail to capture joint information from multiple labels.

Classification Multi-class Classification +2

Robo-Advising: Enhancing Investment with Inverse Optimization and Deep Reinforcement Learning

no code implementations19 May 2021 Haoran Wang, Shi Yu

Machine Learning (ML) has been embraced as a powerful tool by the financial industry, with notable applications spreading in various domains including investment management.

Portfolio Optimization reinforcement-learning

Hierarchical Cost Analysis for Distributed DL

1 code implementation IEEE International Parallel and Distributed Processing Symposium Workshops 2021 Haoran Wang

In order to formalize the behaviors of the HP in distributed DL and quantitatively evaluate the cost caused by HP, we are studying Bridging DL composed by a double-level execution model associated with a symbolic cost model.

Code Generation

Strictly Decentralized Adaptive Estimation of External Fields using Reproducing Kernels

no code implementations23 Mar 2021 Jia Guo, Michael E. Kepler, Sai Tej Paruchuri, Haoran Wang, Andrew J. Kurdila, Daniel J. Stilwell

Approximations of the evolution of the ideal local estimate $\hat{g}^i_t$ of agent $i$ is constructed solely using observations made by agent $i$ on a fine time scale.

Unity

Energy-based Out-of-distribution Detection for Multi-label Classification

no code implementations1 Jan 2021 Haoran Wang, Weitang Liu, Alex Bocchieri, Yixuan Li

Our results show consistent improvement over previous methods that are based on the maximum-valued scores, which fail to capture joint information from multiple labels.

Classification General Classification +4

Exploring Fluent Query Reformulations with Text-to-Text Transformers and Reinforcement Learning

no code implementations18 Dec 2020 Jerry Zikun Chen, Shi Yu, Haoran Wang

Query reformulation aims to alter noisy or ambiguous text sequences into coherent ones closer to natural language questions.

Intent Classification Question Answering +2

Context-Aware Graph Convolution Network for Target Re-identification

no code implementations8 Dec 2020 Deyi Ji, Haoran Wang, Hanzhe Hu, Weihao Gan, Wei Wu, Junjie Yan

Most existing re-identification methods focus on learning robust and discriminative features with deep convolution networks.

Vehicle Re-Identification

Frame Aggregation and Multi-Modal Fusion Framework for Video-Based Person Recognition

no code implementations19 Oct 2020 Fangtao Li, Wenzhe Wang, Zihe Liu, Haoran Wang, Chenghao Yan, Bin Wu

To tackle the challenges above, we propose a novel Frame Aggregation and Multi-Modal Fusion (FAMF) framework for video-based person recognition, which aggregates face features and incorporates them with multi-modal information to identify persons in videos.

Frame Person Recognition

Learning Risk Preferences from Investment Portfolios Using Inverse Optimization

no code implementations4 Oct 2020 Shi Yu, Haoran Wang, Chaosheng Dong

Our approach allows the learner to continuously estimate real-time risk preferences using concurrent observed portfolios and market price data.

Decision Making

Consensus-Aware Visual-Semantic Embedding for Image-Text Matching

1 code implementation ECCV 2020 Haoran Wang, Ying Zhang, Zhong Ji, Yanwei Pang, Lin Ma

In this paper, we propose a Consensus-aware Visual-Semantic Embedding (CVSE) model to incorporate the consensus information, namely the commonsense knowledge shared between both modalities, into image-text matching.

Image Captioning Text Matching

Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentation

1 code implementation ECCV 2020 Haoran Wang, Tong Shen, Wei zhang, Ling-Yu Duan, Tao Mei

To fully exploit the supervision in the source domain, we propose a fine-grained adversarial learning strategy for class-level feature alignment while preserving the internal structure of semantics across domains.

Domain Adaptation Semantic Segmentation +1

Large scale continuous-time mean-variance portfolio allocation via reinforcement learning

no code implementations26 Jul 2019 Haoran Wang

We propose to solve large scale Markowitz mean-variance (MV) portfolio allocation problem using reinforcement learning (RL).

reinforcement-learning

Saliency-Guided Attention Network for Image-Sentence Matching

no code implementations ICCV 2019 Zhong Ji, Haoran Wang, Jungong Han, Yanwei Pang

Concretely, the saliency detector provides the visual saliency information as the guidance for the two attention modules.

Enhancing Topic Modeling for Short Texts with Auxiliary Word Embeddings

no code implementations22 Dec 2018 Chenliang Li, Yu Duan, Haoran Wang, Zhiqian Zhang, Aixin Sun, Zongyang Ma

Recent studies show that the Dirichlet Multinomial Mixture (DMM) model is effective for topic inference over short texts by assuming that each piece of short text is generated by a single topic.

Topic Models Word Embeddings

Exploration versus exploitation in reinforcement learning: a stochastic control approach

no code implementations4 Dec 2018 Haoran Wang, Thaleia Zariphopoulou, Xunyu Zhou

We carry out a complete analysis of the problem in the linear--quadratic (LQ) setting and deduce that the optimal feedback control distribution for balancing exploitation and exploration is Gaussian.

reinforcement-learning

Parameter-Free Spatial Attention Network for Person Re-Identification

3 code implementations29 Nov 2018 Haoran Wang, Yue Fan, Zexin Wang, Licheng Jiao, Bernt Schiele

We propose a novel architecture for Person Re-Identification, based on a novel parameter-free spatial attention layer introducing spatial relations among the feature map activations back to the model.

Person Re-Identification

Multi-task Sparse Learning with Beta Process Prior for Action Recognition

no code implementations CVPR 2013 Chunfeng Yuan, Weiming Hu, Guodong Tian, Shuang Yang, Haoran Wang

In this paper, we formulate human action recognition as a novel Multi-Task Sparse Learning(MTSL) framework which aims to construct a test sample with multiple features from as few bases as possible.

Action Recognition Sparse Learning

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