no code implementations • 21 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.
1 code implementation • 18 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.
1 code implementation • 7 Oct 2024 • Hongjun Wang, Jiyuan Chen, Tong Pan, Zheng Dong, Lingyu Zhang, Renhe Jiang, Xuan Song
The generalization ability of these models remains largely unexplored.
no code implementations • 7 Oct 2024 • Hongjun Wang, Jiyuan Chen, Renhe Jiang, Xuan Song, Yinqiang Zheng
Cloth-changing person re-identification (CC-ReID) poses a significant challenge in computer vision.
Cloth-Changing Person Re-Identification
Density Ratio Estimation
+1
no code implementations • 4 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.
1 code implementation • 1 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.
1 code implementation • 1 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.
1 code implementation • 29 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.
no code implementations • 8 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.
no code implementations • 30 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.
no code implementations • 20 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.
no code implementations • 7 Mar 2024 • Zezheng Feng, Yifan Jiang, Hongjun Wang, Zipei Fan, Yuxin Ma, Shuang-Hua Yang, Huamin Qu, Xuan Song
Recent achievements in deep learning (DL) have shown its potential for predicting traffic flows.
no code implementations • CVPR 2024 • Hongjun Wang, Jiyuan Chen, Yinqiang Zheng, Tieyong Zeng
Deep learning has led to a dramatic leap on Single Image Super-Resolution (SISR) performances in recent years.
no code implementations • 22 May 2023 • Hongjun Wang, Jiyuan Chen, Lun Du, Qiang Fu, Shi Han, Xuan Song
Recent years have witnessed the great potential of attention mechanism in graph representation learning.
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.
no code implementations • 13 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.
2 code implementations • 28 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.
no code implementations • 2 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.
no code implementations • 21 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.
no code implementations • 5 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.
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.
no code implementations • 11 Mar 2022 • Yifan Jiang, Zezheng Feng, Hongjun Wang, Zipei Fan, Xuan Song
TrafPS consists of three layers, from data process to results computation and visualization.
no code implementations • 1 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.
no code implementations • 15 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.
1 code implementation • 4 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.
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.
1 code implementation • 5 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.
no code implementations • 13 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.
no code implementations • 28 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.
no code implementations • 12 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.
no code implementations • 5 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).
no code implementations • 2 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.
no code implementations • 13 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.