no code implementations • 28 Apr 2024 • Kaiyu Song, Hanjiang Lai
Recently, the diffusion model with the training-free methods has succeeded in conditional image generation tasks.
no code implementations • 8 Dec 2023 • Kaiyu Song, Hanjiang Lai
Diffusion-based adversarial purification focuses on using the diffusion model to generate a clean image against such adversarial attacks.
no code implementations • 8 Dec 2023 • Kaiyu Song, Hanjiang Lai
However, 1) the semantic information loss from test data to the source domain and 2) the model shift between the source classifier and diffusion model would prevent the diffusion model from mapping the test data back to the source domain correctly.
no code implementations • 13 Nov 2023 • Junyang Chen, Hanjiang Lai
Then, we propose a masked tuning, which uses the text and the masked image to learn the modifications of the original image.
no code implementations • 31 Oct 2023 • Guoliang Lin, Hanjiang Lai, Yan Pan, Jian Yin
This new perspective allows us to explore how entropy minimization influences test-time adaptation.
no code implementations • 16 Aug 2023 • Junyang Chen, Hanjiang Lai
Specifically, our approach mainly comprises three components: (1) In-sample uncertainty, which aims to capture semantic diversity using a Gaussian distribution derived from both combined and target features; (2) Cross-sample uncertainty, which further mines the ranking information from other samples' distributions; and (3) Distribution regularization, which aligns the distributional representations of source inputs and targeted image.
Ranked #3 on Image Retrieval on Fashion IQ
no code implementations • 5 May 2023 • Wangzhen Guo, Linyin Luo, Hanjiang Lai, Jian Yin
The parser uses the KoPL to generate the transparent logical forms.
no code implementations • CVPR 2023 • Liangdao Wang, Yan Pan, Cong Liu, Hanjiang Lai, Jian Yin, Ye Liu
This paper presents an optimization method that finds hash centers with a constraint on the minimal distance between any pair of hash centers, which is non-trivial due to the non-convex nature of the problem.
no code implementations • 13 Oct 2022 • Wangzhen Guo, Qinkang Gong, Hanjiang Lai
With the causal graph, a counterfactual inference is proposed to disentangle the disconnected reasoning from the total causal effect, which provides us a new perspective and technology to learn a QA model that exploits the true multi-hop reasoning instead of shortcuts.
1 code implementation • 28 Sep 2022 • Guoliang Lin, Yongheng Xu, Hanjiang Lai, Jian Yin
In this paper, we try to interpret these metric-based few-shot learning methods via causal mechanism.
no code implementations • 14 Jan 2022 • Qinkang Gong, Liangdao Wang, Hanjiang Lai, Yan Pan, Jian Yin
Specifically, from pixels to continuous features, we first propose a feature-preserving module, using the corrupted image as input to reconstruct the original feature from the pre-trained ViT model and the complete image, so that the feature extractor can focus on preserving the meaningful information of original data.
no code implementations • CVPR 2022 • Guoliang Lin, Hanlu Chu, Hanjiang Lai
Our method also achieves 6. 33% higher accuracy on TinyImageNet.
no code implementations • ICLR 2020 • Zhenyu Shi*, Runsheng Yu*, Xinrun Wang*, Rundong Wang, Youzhi Zhang, Hanjiang Lai, Bo An
The main difficulties of expensive coordination are that i) the leader has to consider the long-term effect and predict the followers' behaviors when assigning bonuses and ii) the complex interactions between followers make the training process hard to converge, especially when the leader's policy changes with time.
no code implementations • 20 Dec 2019 • Haien Zeng, Hanjiang Lai, Jian Yin
Second, since the image may contain other unwanted attributes, an attribute disentanglement network is used to separate the individual embedding and learn the common embedding that contains information about the face attribute (e. g., race).
no code implementations • 19 Nov 2019 • Haien Zeng, Hanjiang Lai, Hanlu Chu, Yong Tang, Jian Yin
The modal-aware operation consists of a kernel network and an attention network.
no code implementations • 19 Nov 2019 • Haien Zeng, Hanjiang Lai, Jian Yin
Fine-grained image hashing is a challenging problem due to the difficulties of discriminative region localization and hash code generation.
no code implementations • 18 Nov 2019 • Runsheng Yu, Zhenyu Shi, Xinrun Wang, Rundong Wang, Buhong Liu, Xinwen Hou, Hanjiang Lai, Bo An
Existing value-factorized based Multi-Agent deep Reinforce-ment Learning (MARL) approaches are well-performing invarious multi-agent cooperative environment under thecen-tralized training and decentralized execution(CTDE) scheme, where all agents are trained together by the centralized valuenetwork and each agent execute its policy independently.
no code implementations • 4 Apr 2019 • Yifan Yang, Libing Geng, Hanjiang Lai, Yan Pan, Jian Yin
In recent years, deep-networks-based hashing has become a leading approach for large-scale image retrieval.
no code implementations • ICCV 2019 • Haoye Dong, Xiaodan Liang, Bochao Wang, Hanjiang Lai, Jia Zhu, Jian Yin
Given an input person image, a desired clothes image, and a desired pose, the proposed Multi-pose Guided Virtual Try-on Network (MG-VTON) can generate a new person image after fitting the desired clothes into the input image and manipulating human poses.
Ranked #1 on Virtual Try-on on Deep-Fashion
no code implementations • NeurIPS 2018 • Haoye Dong, Xiaodan Liang, Ke Gong, Hanjiang Lai, Jia Zhu, Jian Yin
Despite remarkable advances in image synthesis research, existing works often fail in manipulating images under the context of large geometric transformations.
no code implementations • 17 Apr 2018 • Jikai Chen, Hanjiang Lai, Libing Geng, Yan Pan
In this paper, we focus on triplet-based deep binary embedding networks for image retrieval task.
no code implementations • 26 Mar 2018 • Libing Geng, Yan Pan, Jikai Chen, Hanjiang Lai
To address this issue, in this paper, we propose a simple two-stage pipeline to learn deep hashing models, by regularizing the deep hashing networks using fake images.
no code implementations • 26 Nov 2017 • Siyu Zhou, Weiqiang Zhao, Jiashi Feng, Hanjiang Lai, Yan Pan, Jian Yin, Shuicheng Yan
Second, we propose a new occupational-aware adversarial face aging network, which learns human aging process under different occupations.
no code implementations • 26 Nov 2017 • Xi Zhang, Siyu Zhou, Jiashi Feng, Hanjiang Lai, Bo Li, Yan Pan, Jian Yin, Shuicheng Yan
The proposed new adversarial network, HashGAN, consists of three building blocks: 1) the feature learning module to obtain feature representations, 2) the generative attention module to generate an attention mask, which is used to obtain the attended (foreground) and the unattended (background) feature representations, 3) the discriminative hash coding module to learn hash functions that preserve the similarities between different modalities.
no code implementations • 8 Nov 2017 • Hanjiang Lai, Yan Pan
It mainly consists of two building blocks in the proposed deep architecture: 1) a shared two-streams network, which the first stream operates on the source data and the second stream operates on the unlabeled data, to learn the effective common image representations, and 2) a coarse-to-fine module, which begins with finding the most representative images from target classes and then further detect similarities among these images, to transfer the similarities of the source data to the target data in a greedy fashion.
no code implementations • 19 Oct 2017 • Hanjiang Lai, Yan Pan
Similarity-preserving hashing is a widely-used method for nearest neighbour search in large-scale image retrieval tasks.
no code implementations • CVPR 2017 • Zhen Wei, Yao Sun, Jinqiao Wang, Hanjiang Lai, Si Liu
In this paper, we introduce a novel approach to regulate receptive field in deep image parsing network automatically.
no code implementations • 4 Jun 2017 • Xiangbo Shu, Jinhui Tang, Zechao Li, Hanjiang Lai, Liyan Zhang, Shuicheng Yan
Basically, for each age group, we learn an aging dictionary to reveal its aging characteristics (e. g., wrinkles), where the dictionary bases corresponding to the same index yet from two neighboring aging dictionaries form a particular aging pattern cross these two age groups, and a linear combination of all these patterns expresses a particular personalized aging process.
no code implementations • 10 Mar 2016 • Hanjiang Lai, Pan Yan, Xiangbo Shu, Yunchao Wei, Shuicheng Yan
The instance-aware representations not only bring advantages to semantic hashing, but also can be used in category-aware hashing, in which an image is represented by multiple pieces of hash codes and each piece of code corresponds to a category.
no code implementations • 30 Oct 2015 • Hanjiang Lai, Shengtao Xiao, Yan Pan, Zhen Cui, Jiashi Feng, Chunyan Xu, Jian Yin, Shuicheng Yan
We propose a novel end-to-end deep architecture for face landmark detection, based on a deep convolutional and deconvolutional network followed by carefully designed recurrent network structures.
no code implementations • ICCV 2015 • Xiangbo Shu, Jinhui Tang, Hanjiang Lai, Luoqi Liu, Shuicheng Yan
Second, it is challenging or even impossible to collect faces of all age groups for a particular subject, yet much easier and more practical to get face pairs from neighboring age groups.
no code implementations • CVPR 2015 • Hanjiang Lai, Yan Pan, Ye Liu, Shuicheng Yan
Similarity-preserving hashing is a widely-used method for nearest neighbour search in large-scale image retrieval tasks.
no code implementations • CVPR 2013 • Yan Pan, Hanjiang Lai, Cong Liu, Shuicheng Yan
To address this issue, we provide a scalable solution for large-scale low-rank latent matrix pursuit by a divide-andconquer method.