Search Results for author: Hongjun Wang

Found 33 papers, 11 papers with code

Parallel Sequence Modeling via Generalized Spatial Propagation Network

no code implementations21 Jan 2025 Hongjun Wang, Wonmin Byeon, Jiarui Xu, Jinwei Gu, Ka Chun Cheung, Xiaolong Wang, Kai Han, Jan Kautz, Sifei Liu

We present the Generalized Spatial Propagation Network (GSPN), a new attention mechanism optimized for vision tasks that inherently captures 2D spatial structures.

16k Computational Efficiency +3

Unveiling the Inflexibility of Adaptive Embedding in Traffic Forecasting

1 code implementation18 Nov 2024 Hongjun Wang, Jiyuan Chen, Lingyu Zhang, Renhe Jiang, Xuan Song

To address this limitation, we reconsider the design of adaptive embeddings and propose a Principal Component Analysis (PCA) embedding approach that enables models to adapt to new scenarios without retraining.

Attribute Traffic Prediction

Learning to Balance: Diverse Normalization for Cloth-Changing Person Re-Identification

no code implementations4 Oct 2024 Hongjun Wang, Jiyuan Chen, Zhengwei Yin, Xuan Song, Yinqiang Zheng

In this paper, we empirically and experimentally demonstrate that completely eliminating or fully retaining clothing features is detrimental to the task.

Cloth-Changing Person Re-Identification

Robust Traffic Forecasting against Spatial Shift over Years

1 code implementation1 Oct 2024 Hongjun Wang, Jiyuan Chen, Tong Pan, Zheng Dong, Lingyu Zhang, Renhe Jiang, Xuan Song

Through meticulous analysis, we attribute this decline to the models' inability to adapt to previously unobserved spatial relationships.

Attribute

STGformer: Efficient Spatiotemporal Graph Transformer for Traffic Forecasting

1 code implementation1 Oct 2024 Hongjun Wang, Jiyuan Chen, Tong Pan, Zheng Dong, Lingyu Zhang, Renhe Jiang, Xuan Song

STGformer effectively balances the strengths of GCNs and Transformers, enabling efficient modeling of both global and local traffic patterns while maintaining a manageable computational footprint.

Dissecting Out-of-Distribution Detection and Open-Set Recognition: A Critical Analysis of Methods and Benchmarks

1 code implementation29 Aug 2024 Hongjun Wang, Sagar Vaze, Kai Han

Detecting test-time distribution shift has emerged as a key capability for safely deployed machine learning models, with the question being tackled under various guises in recent years.

Open Set Learning Out-of-Distribution Detection +1

HiLo: A Learning Framework for Generalized Category Discovery Robust to Domain Shifts

no code implementations8 Aug 2024 Hongjun Wang, Sagar Vaze, Kai Han

Generalized Category Discovery (GCD) is a challenging task in which, given a partially labelled dataset, models must categorize all unlabelled instances, regardless of whether they come from labelled categories or from new ones.

Accurate Cutting-point Estimation for Robotic Lychee Harvesting through Geometry-aware Learning

no code implementations30 Mar 2024 Gengming Zhang, Hao Cao, Kewei Hu, Yaoqiang Pan, Yuqin Deng, Hongjun Wang, Hanwen Kang

Accurately identifying lychee-picking points in unstructured orchard environments and obtaining their coordinate locations is critical to the success of lychee-picking robots.

3D Object Detection object-detection

SPTNet: An Efficient Alternative Framework for Generalized Category Discovery with Spatial Prompt Tuning

no code implementations20 Mar 2024 Hongjun Wang, Sagar Vaze, Kai Han

We thoroughly evaluate our SPTNet on standard benchmarks and demonstrate that our method outperforms existing GCD methods.

Generalist: Decoupling Natural and Robust Generalization

1 code implementation CVPR 2023 Hongjun Wang, Yisen Wang

The parameters of base learners are collected and combined to form a global learner at intervals during the training process.

Multitask Weakly Supervised Learning for Origin Destination Travel Time Estimation

no code implementations13 Jan 2023 Hongjun Wang, Zhiwen Zhang, Zipei Fan, Jiyuan Chen, Lingyu Zhang, Ryosuke Shibasaki, Xuan Song

Subsequently, a Multitask Weakly Supervised Learning Framework for Travel Time Estimation (MWSL TTE) has been proposed to infer transition probability between roads segments, and the travel time on road segments and intersection simultaneously.

Travel Time Estimation Weakly-supervised Learning

Easy Begun is Half Done: Spatial-Temporal Graph Modeling with ST-Curriculum Dropout

2 code implementations28 Nov 2022 Hongjun Wang, Jiyuan Chen, Tong Pan, Zipei Fan, Boyuan Zhang, Renhe Jiang, Lingyu Zhang, Yi Xie, Zhongyi Wang, Xuan Song

Spatial-temporal (ST) graph modeling, such as traffic speed forecasting and taxi demand prediction, is an important task in deep learning area.

GOF-TTE: Generative Online Federated Learning Framework for Travel Time Estimation

no code implementations2 Jul 2022 Zhiwen Zhang, Hongjun Wang, Jiyuan Chen, Zipei Fan, Xuan Song, Ryosuke Shibasaki

However, building a model for such a data-driven task requires a large amount of users' travel information, which directly relates to their privacy and thus is less likely to be shared.

Federated Learning Travel Time Estimation

Route to Time and Time to Route: Travel Time Estimation from Sparse Trajectories

no code implementations21 Jun 2022 Zhiwen Zhang, Hongjun Wang, Zipei Fan, Jiyuan Chen, Xuan Song, Ryosuke Shibasaki

In this case, this paper aims to resolve the problem of travel time estimation (TTE) and route recovery in sparse scenarios, which often leads to the uncertain label of travel time and route between continuously sampled GPS points.

Travel Time Estimation

ST-ExpertNet: A Deep Expert Framework for Traffic Prediction

no code implementations5 May 2022 Hongjun Wang, Jiyuan Chen, Zipei Fan, Zhiwen Zhang, Zekun Cai, Xuan Song

Recently, forecasting the crowd flows has become an important research topic, and plentiful technologies have achieved good performances.

Prediction Traffic Prediction

Self-Ensemble Adversarial Training for Improved Robustness

1 code implementation ICLR 2022 Hongjun Wang, Yisen Wang

In this work, we are dedicated to the weight states of models through the training process and devise a simple but powerful \emph{Self-Ensemble Adversarial Training} (SEAT) method for yielding a robust classifier by averaging weights of history models.

Adversarial Training using Contrastive Divergence

no code implementations1 Jan 2021 Hongjun Wang, Guanbin Li, Liang Lin

To protect the security of machine learning models against adversarial examples, adversarial training becomes the most popular and powerful strategy against various adversarial attacks by injecting adversarial examples into training data.

A Hamiltonian Monte Carlo Method for Probabilistic Adversarial Attack and Learning

no code implementations15 Oct 2020 Hongjun Wang, Guanbin Li, Xiaobai Liu, Liang Lin

Although deep convolutional neural networks (CNNs) have demonstrated remarkable performance on multiple computer vision tasks, researches on adversarial learning have shown that deep models are vulnerable to adversarial examples, which are crafted by adding visually imperceptible perturbations to the input images.

Adversarial Attack

Distributional Discrepancy: A Metric for Unconditional Text Generation

1 code implementation4 May 2020 Ping Cai, Xingyuan Chen, Peng Jin, Hongjun Wang, Tianrui Li

The purpose of unconditional text generation is to train a model with real sentences, then generate novel sentences of the same quality and diversity as the training data.

Diversity Language Modeling +2

Transferable, Controllable, and Inconspicuous Adversarial Attacks on Person Re-identification With Deep Mis-Ranking

1 code implementation CVPR 2020 Hongjun Wang, Guangrun Wang, Ya Li, Dongyu Zhang, Liang Lin

To examine the robustness of ReID systems is rather important because the insecurity of ReID systems may cause severe losses, e. g., the criminals may use the adversarial perturbations to cheat the CCTV systems.

Adversarial Attack Person Re-Identification

Adding A Filter Based on The Discriminator to Improve Unconditional Text Generation

1 code implementation5 Apr 2020 Xingyuan Chen, Ping Cai, Peng Jin, Hongjun Wang, Xin-yu Dai, Jia-Jun Chen

To alleviate the exposure bias, generative adversarial networks (GAN) use the discriminator to update the generator's parameters directly, but they fail by being evaluated precisely.

Language Modelling Text Generation

Micro-supervised Disturbance Learning: A Perspective of Representation Probability Distribution

no code implementations13 Mar 2020 Jielei Chu, Jing Liu, Hongjun Wang, Meng Hua, Zhiguo Gong, Tianrui Li

To explore the representation learning capability under the continuous stimulation of the SPI, we present a deep Micro-supervised Disturbance Learning (Micro-DL) framework based on the Micro-DGRBM and Micro-DRBM models and compare it with a similar deep structure which has not any external stimulation.

Representation Learning

The Detection of Distributional Discrepancy for Text Generation

no code implementations28 Sep 2019 Xingyuan Chen, Ping Cai, Peng Jin, Haokun Du, Hongjun Wang, Xingyu Dai, Jia-Jun Chen

In this paper, we theoretically propose two metric functions to measure the distributional difference between real text and generated text.

Language Modeling Language Modelling +1

Multi-local Collaborative AutoEncoder

no code implementations12 Jun 2019 Jielei Chu, Hongjun Wang, Jing Liu, Zhiguo Gong, Tianrui Li

In mcrRBM and mcrGRBM models, the structure and multi-local collaborative relationships of unlabeled data are integrated into their encoding procedure.

Clustering Representation Learning

Unsupervised Feature Learning Architecture with Multi-clustering Integration RBM

no code implementations5 Dec 2018 Jielei Chu, Hongjun Wang, Jing Liu, Zhiguo Gong, Tianrui Li

In this paper, we present a novel unsupervised feature learning architecture, which consists of a multi-clustering integration module and a variant of RBM termed multi-clustering integration RBM (MIRBM).

Clustering

Crowd Counting using Deep Recurrent Spatial-Aware Network

no code implementations2 Jul 2018 Lingbo Liu, Hongjun Wang, Guanbin Li, Wanli Ouyang, Liang Lin

Crowd counting from unconstrained scene images is a crucial task in many real-world applications like urban surveillance and management, but it is greatly challenged by the camera's perspective that causes huge appearance variations in people's scales and rotations.

Crowd Counting Management

Restricted Boltzmann Machines with Gaussian Visible Units Guided by Pairwise Constraints

no code implementations13 Jan 2017 Jielei Chu, Hongjun Wang, Hua Meng, Peng Jin, Tianrui Li

To enhance the expression ability of traditional RBMs, in this paper, we propose pairwise constraints restricted Boltzmann machine with Gaussian visible units (pcGRBM) model, in which the learning procedure is guided by pairwise constraints and the process of encoding is conducted under these guidances.

Clustering

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