no code implementations • ECCV 2020 • Shuo Wang, Jun Yue, Jianzhuang Liu, Qi Tian, Meng Wang
It is a challenging problem since (1) the identifying process is susceptible to over-fitting with limited samples of an object, and (2) the sample imbalance between a base (known knowledge) category and a novel category is easy to bias the recognition results.
no code implementations • ECCV 2020 • Lin Liu, Jianzhuang Liu, Shanxin Yuan, Gregory Slabaugh, Aleš Leonardis, Wengang Zhou, Qi Tian
When smartphone cameras are used to take photos of digital screens, usually moire patterns result, severely degrading photo quality.
1 code implementation • ECCV 2020 • Xinshuai Dong, Hong Liu, Rongrong Ji, Liujuan Cao, Qixiang Ye, Jianzhuang Liu, Qi Tian
On the contrary, a discriminative classifier only models the conditional distribution of labels given inputs, but benefits from effective optimization owing to its succinct structure.
no code implementations • 19 May 2022 • Zhuoling Li, Zhan Qu, Yang Zhou, Jianzhuang Liu, Haoqian Wang, Lihui Jiang
To tackle this problem, we propose a depth solving system that fully explores the visual clues from the subtasks in M3OD and generates multiple estimations for the depth of each target.
no code implementations • 6 May 2022 • Yuning Lu, Jianzhuang Liu, Yonggang Zhang, Yajing Liu, Xinmei Tian
We present prompt distribution learning for effectively adapting a pre-trained vision-language model to address downstream recognition tasks.
no code implementations • 21 Mar 2022 • Xiaodong Cun, Zhendong Wang, Chi-Man Pun, Jianzhuang Liu, Wengang Zhou, Xu Jia, Houqiang Li
Color constancy aims to restore the constant colors of a scene under different illuminants.
no code implementations • 12 Mar 2022 • Fuhai Chen, Xiaoshuai Sun, Xuri Ge, Jianzhuang Liu, Yongjian Wu, Feiyue Huang, Rongrong Ji
In particular, based on the visual and textual semantic features, RMSL conducts an adaptive learning cycle upon triplet ranking, where (1) the target-negative region-expression pairs with low within-group relevances are used preferentially in model training to distinguish the primary semantics of the target objects, and (2) an across-group relevance regularization is integrated into model training to balance the bias of group priority.
no code implementations • 17 Dec 2021 • Lin Liu, Shanxin Yuan, Jianzhuang Liu, Xin Guo, Youliang Yan, Qi Tian
For zero-shot image restoration, we design a novel model, termed SiamTrans, which is constructed by Siamese transformers, encoders, and decoders.
1 code implementation • 17 Nov 2021 • Yunshan Zhong, Mingbao Lin, Gongrui Nan, Jianzhuang Liu, Baochang Zhang, Yonghong Tian, Rongrong Ji
In this paper, we observe an interesting phenomenon of intra-class heterogeneity in real data and show that existing methods fail to retain this property in their synthetic images, which causes a limited performance increase.
no code implementations • ICCV 2021 • Fang Xu, Lei Yu, Bishan Wang, Wen Yang, Gui-Song Xia, Xu Jia, Zhendong Qiao, Jianzhuang Liu
In this paper, we propose an end-to-end learning framework for event-based motion deblurring in a self-supervised manner, where real-world events are exploited to alleviate the performance degradation caused by data inconsistency.
1 code implementation • 12 Sep 2021 • Bohong Chen, Mingbao Lin, Liujuan Cao, Jianzhuang Liu, Qixiang Ye, Baochang Zhang, Wei Zeng, Yonghong Tian, Rongrong Ji
Then, the sampling will gradually be prone to sampling subnets from the subnet pools.
no code implementations • 3 Aug 2021 • Tianhong Dai, Wei Li, Xilei Cao, Jianzhuang Liu, Xu Jia, Ales Leonardis, Youliang Yan, Shanxin Yuan
The frequency-guided upsampling module reconstructs details from multiple frequency-specific components with rich details.
1 code implementation • 14 Jul 2021 • Mingbao Lin, Rongrong Ji, Bohong Chen, Fei Chao, Jianzhuang Liu, Wei Zeng, Yonghong Tian, Qi Tian
Each filter in our DCFF is firstly given an inter-similarity distribution with a temperature parameter as a filter proxy, on top of which, a fresh Kullback-Leibler divergence based dynamic-coded criterion is proposed to evaluate the filter importance.
no code implementations • CVPR 2021 • Takashi Isobe, Xu Jia, Shuaijun Chen, Jianzhong He, Yongjie Shi, Jianzhuang Liu, Huchuan Lu, Shengjin Wang
To obtain a single model that works across multiple target domains, we propose to simultaneously learn a student model which is trained to not only imitate the output of each expert on the corresponding target domain, but also to pull different expert close to each other with regularization on their weights.
4 code implementations • 6 Jun 2021 • Zhendong Wang, Xiaodong Cun, Jianmin Bao, Wengang Zhou, Jianzhuang Liu, Houqiang Li
Powered by these two designs, Uformer enjoys a high capability for capturing both local and global dependencies for image restoration.
Ranked #1 on
Deblurring
on RealBlur-R (trained on GoPro)
1 code implementation • CVPR 2021 • Yuchao Li, Shaohui Lin, Jianzhuang Liu, Qixiang Ye, Mengdi Wang, Fei Chao, Fan Yang, Jincheng Ma, Qi Tian, Rongrong Ji
Channel pruning and tensor decomposition have received extensive attention in convolutional neural network compression.
1 code implementation • CVPR 2021 • Tianning Yuan, Fang Wan, Mengying Fu, Jianzhuang Liu, Songcen Xu, Xiangyang Ji, Qixiang Ye
Despite the substantial progress of active learning for image recognition, there still lacks an instance-level active learning method specified for object detection.
Ranked #1 on
Active Object Detection
on PASCAL VOC 07+12
1 code implementation • ICCV 2021 • Zihan Xu, Mingbao Lin, Jianzhuang Liu, Jie Chen, Ling Shao, Yue Gao, Yonghong Tian, Rongrong Ji
We prove that reviving the "dead weights" by ReCU can result in a smaller quantization error.
1 code implementation • CVPR 2021 • Shuaijun Chen, Xu Jia, Jianzhong He, Yongjie Shi, Jianzhuang Liu
To address the task of SSDA, a novel framework based on dual-level domain mixing is proposed.
no code implementations • CVPR 2021 • Jianzhong He, Xu Jia, Shuaijun Chen, Jianzhuang Liu
Multi-source unsupervised domain adaptation~(MSDA) aims at adapting models trained on multiple labeled source domains to an unlabeled target domain.
Multi-Source Unsupervised Domain Adaptation
Semantic Segmentation
+1
4 code implementations • CVPR 2021 • Tao Huang, Songjiang Li, Xu Jia, Huchuan Lu, Jianzhuang Liu
In this paper, we present a very simple yet effective method named Neighbor2Neighbor to train an effective image denoising model with only noisy images.
no code implementations • ICCV 2021 • Fengchao Peng, Chao Wang, Jianzhuang Liu, Zhen Yang
The experiments show that our method achieves new state-of-the-art on the lane detection benchmarks.
1 code implementation • ICCV 2021 • Yiyi Zhou, Tianhe Ren, Chaoyang Zhu, Xiaoshuai Sun, Jianzhuang Liu, Xinghao Ding, Mingliang Xu, Rongrong Ji
Due to the superior ability of global dependency modeling, Transformer and its variants have become the primary choice of many vision-and-language tasks.
no code implementations • ICCV 2021 • Peixian Chen, Wenfeng Liu, Pingyang Dai, Jianzhuang Liu, Qixiang Ye, Mingliang Xu, Qi'an Chen, Rongrong Ji
To avoid such problematic models in occluded person ReID, we propose the Occlusion-Aware Mask Network (OAMN).
no code implementations • NeurIPS 2020 • Lin Liu, Shanxin Yuan, Jianzhuang Liu, Liping Bao, Gregory Slabaugh, Qi Tian
In this paper, we propose a self-adaptive learning method for demoiréing a high-frequency image, with the help of an additional defocused moiré-free blur image.
1 code implementation • 3 Nov 2020 • Lin Liu, Shanxin Yuan, Jianzhuang Liu, Liping Bao, Gregory Slabaugh, Qi Tian
In this paper, we propose a self-adaptive learning method for demoireing a high-frequency image, with the help of an additional defocused moire-free blur image.
no code implementations • 8 Sep 2020 • Hanlin Chen, Li'an Zhuo, Baochang Zhang, Xiawu Zheng, Jianzhuang Liu, Rongrong Ji, David Doermann, Guodong Guo
In this paper, binarized neural architecture search (BNAS), with a search space of binarized convolutions, is introduced to produce extremely compressed models to reduce huge computational cost on embedded devices for edge computing.
no code implementations • 7 Sep 2020 • Nan Meng, Kai Li, Jianzhuang Liu, Edmund Y. Lam
This paper presents a learning-based approach to synthesize the view from an arbitrary camera position given a sparse set of images.
1 code implementation • 27 Jul 2020 • Peixian Chen, Pingyang Dai, Jianzhuang Liu, Feng Zheng, Qi Tian, Rongrong Ji
Domain generalization (DG) serves as a promising solution to handle person Re-Identification (Re-ID), which trains the model using labels from the source domain alone, and then directly adopts the trained model to the target domain without model updating.
Domain Generalization
Generalizable Person Re-identification
no code implementations • 14 Jul 2020 • Lin Liu, Jianzhuang Liu, Shanxin Yuan, Gregory Slabaugh, Ales Leonardis, Wengang Zhou, Qi Tian
When smartphone cameras are used to take photos of digital screens, usually moire patterns result, severely degrading photo quality.
1 code implementation • CVPR 2020 • Jie Li, Rongrong Ji, Hong Liu, Jianzhuang Liu, Bineng Zhong, Cheng Deng, Qi Tian
For reducing the solution space, we first model the adversarial perturbation optimization problem as a process of recovering frequency-sparse perturbations with compressed sensing, under the setting that random noise in the low-frequency space is more likely to be adversarial.
1 code implementation • 29 Mar 2020 • Nan Meng, Xiaofei Wu, Jianzhuang Liu, Edmund Y. Lam
In this paper, we propose a novel high-order residual network to learn the geometric features hierarchically from the LF for reconstruction.
1 code implementation • 16 Mar 2020 • Ze Yang, Yali Wang, Xianyu Chen, Jianzhuang Liu, Yu Qiao
Few-shot object detection is a challenging but realistic scenario, where only a few annotated training images are available for training detectors.
2 code implementations • CVPR 2020 • Chengying Gao, Qi Liu, Qi Xu, Li-Min Wang, Jianzhuang Liu, Changqing Zou
We introduce the first method for automatic image generation from scene-level freehand sketches.
Ranked #2 on
Sketch-to-Image Translation
on SketchyCOCO
1 code implementation • 23 Jan 2020 • Mingbao Lin, Liujuan Cao, Shaojie Li, Qixiang Ye, Yonghong Tian, Jianzhuang Liu, Qi Tian, Rongrong Ji
Our approach, referred to as FilterSketch, encodes the second-order information of pre-trained weights, which enables the representation capacity of pruned networks to be recovered with a simple fine-tuning procedure.
3 code implementations • CVPR 2020 • Wei Ke, Tianliang Zhang, Zeyi Huang, Qixiang Ye, Jianzhuang Liu, Dong Huang
In this paper, we propose a Multiple Instance Learning (MIL) approach that selects anchors and jointly optimizes the two modules of a CNN-based object detector.
Ranked #87 on
Object Detection
on COCO test-dev
1 code implementation • 25 Nov 2019 • Hanlin Chen, Li'an Zhuo, Baochang Zhang, Xiawu Zheng, Jianzhuang Liu, David Doermann, Rongrong Ji
A variant, binarized neural architecture search (BNAS), with a search space of binarized convolutions, can produce extremely compressed models.
no code implementations • 25 Nov 2019 • Chunlei Liu, Wenrui Ding, Yuan Hu, Baochang Zhang, Jianzhuang Liu, Guodong Guo
The BGA method is proposed to modify the binary process of GBCNs to alleviate the local minima problem, which can significantly improve the performance of 1-bit DCNNs.
no code implementations • 25 Oct 2019 • Yiheng Liu, Wengang Zhou, Jianzhuang Liu, Guo-Jun Qi, Qi Tian, Houqiang Li
By presenting a target attention loss, the pedestrian features extracted from the foreground branch become more insensitive to the backgrounds, which greatly reduces the negative impacts of changing backgrounds on matching an identical across different camera views.
no code implementations • CVPR 2019 • Chunlei Liu, Wenrui Ding, Xin Xia, Baochang Zhang, Jiaxin Gu, Jianzhuang Liu, Rongrong Ji, David Doermann
The CiFs can be easily incorporated into existing deep convolutional neural networks (DCNNs), which leads to new Circulant Binary Convolutional Networks (CBCNs).
no code implementations • 7 Oct 2019 • Zhen Han, Enyan Dai, Xu Jia, Xiaoying Ren, Shuaijun Chen, Chunjing Xu, Jianzhuang Liu, Qi Tian
The task of single image super-resolution (SISR) aims at reconstructing a high-resolution (HR) image from a low-resolution (LR) image.
no code implementations • 21 Aug 2019 • Chunlei Liu, Wenrui Ding, Xin Xia, Yuan Hu, Baochang Zhang, Jianzhuang Liu, Bohan Zhuang, Guodong Guo
Binarized convolutional neural networks (BCNNs) are widely used to improve memory and computation efficiency of deep convolutional neural networks (DCNNs) for mobile and AI chips based applications.
no code implementations • ICCV 2019 • Jiaxin Gu, Junhe Zhao, Xiao-Long Jiang, Baochang Zhang, Jianzhuang Liu, Guodong Guo, Rongrong Ji
Deep convolutional neural networks (DCNNs) have dominated the recent developments in computer vision through making various record-breaking models.
1 code implementation • ICCV 2019 • Xiawu Zheng, Rongrong Ji, Lang Tang, Baochang Zhang, Jianzhuang Liu, Qi Tian
Therefore, NAS can be transformed to a multinomial distribution learning problem, i. e., the distribution is optimized to have a high expectation of the performance.
1 code implementation • CVPR 2019 • Yuchao Li, Shaohui Lin, Baochang Zhang, Jianzhuang Liu, David Doermann, Yongjian Wu, Feiyue Huang, Rongrong Ji
The relationship between the input feature maps and 2D kernels is revealed in a theoretical framework, based on which a kernel sparsity and entropy (KSE) indicator is proposed to quantitate the feature map importance in a feature-agnostic manner to guide model compression.
no code implementations • 30 Nov 2018 • Jiaxin Gu, Ce Li, Baochang Zhang, Jungong Han, Xian-Bin Cao, Jianzhuang Liu, David Doermann
The advancement of deep convolutional neural networks (DCNNs) has driven significant improvement in the accuracy of recognition systems for many computer vision tasks.
no code implementations • CVPR 2018 • Xiaodi Wang, Baochang Zhang, Ce Li, Rongrong Ji, Jungong Han, Xian-Bin Cao, Jianzhuang Liu
In this paper, we propose new Modulated Convolutional Networks (MCNs) to improve the portability of CNNs via binarized filters.
1 code implementation • 23 Apr 2018 • Chunyu Xie, Ce Li, Baochang Zhang, Chen Chen, Jungong Han, Changqing Zou, Jianzhuang Liu
Specifically, the TARM is deployed in a residual learning module that employs a novel attention learning network to recalibrate the temporal attention of frames in a skeleton sequence.
Ranked #62 on
Skeleton Based Action Recognition
on NTU RGB+D
no code implementations • 1 Apr 2018 • Baochang Zhang, Jiaxin Gu, Chen Chen, Jungong Han, Xiangbo Su, Xian-Bin Cao, Jianzhuang Liu
Compression artifacts reduction (CAR) is a challenging problem in the field of remote sensing.
no code implementations • 3 May 2017 • Shangzhen Luan, Baochang Zhang, Chen Chen, Xian-Bin Cao, Jungong Han, Jianzhuang Liu
Steerable properties dominate the design of traditional filters, e. g., Gabor filters, and endow features the capability of dealing with spatial transformations.
no code implementations • CVPR 2015 • Dihong Gong, Zhifeng Li, DaCheng Tao, Jianzhuang Liu, Xuelong. Li
In this paper, we propose a new approach to overcome the representation and matching problems in age invariant face recognition.
no code implementations • CVPR 2014 • Zhiding Yu, Chunjing Xu, Deyu Meng, Zhuo Hui, Fanyi Xiao, Wenbo Liu, Jianzhuang Liu
We propose a very intuitive and simple approximation for the conventional spectral clustering methods.
no code implementations • CVPR 2014 • Changqing Zou, Heng Yang, Jianzhuang Liu
Reconstructing 3D objects from single line drawings is often desirable in computer vision and graphics applications.
no code implementations • 15 Oct 2013 • Juan Liu, Baochang Zhang, Linlin Shen, Jianzhuang Liu, Jason Zhao
Keystroke Dynamics is an important biometric solution for person authentication.