1 code implementation • 25 Mar 2023 • ShangHua Gao, Pan Zhou, Ming-Ming Cheng, Shuicheng Yan
Despite its success in image synthesis, we observe that diffusion probabilistic models (DPMs) often lack contextual reasoning ability to learn the relations among object parts in an image, leading to a slow learning process.
Ranked #1 on Image Generation on ImageNet 256x256
1 code implementation • 17 Mar 2023 • Yupeng Zhou, Zhen Li, Chun-Le Guo, Song Bai, Ming-Ming Cheng, Qibin Hou
Previous works have shown that increasing the window size for Transformer-based image super-resolution models (e. g., SwinIR) can significantly improve the model performance but the computation overhead is also considerable.
1 code implementation • 16 Mar 2023 • YuXuan Li, Qibin Hou, Zhaohui Zheng, Ming-Ming Cheng, Jian Yang, Xiang Li
To the best of our knowledge, this is the first time that large and selective kernel mechanisms have been explored in the field of remote sensing object detection.
Ranked #1 on Object Detection In Aerial Images on DOTA
1 code implementation • 14 Mar 2023 • Ziyue Zhu, Zhao Zhang, Zheng Lin, Xing Sun, Ming-Ming Cheng
Such irrelevant information in the co-representation interferes with its locating of co-salient objects.
no code implementations • 6 Mar 2023 • Peng-Tao Jiang, YuQi Yang, Yang Cao, Qibin Hou, Ming-Ming Cheng, Chunhua Shen
Traffic scene parsing is one of the most important tasks to achieve intelligent cities.
no code implementations • 15 Jan 2023 • Cheng-Ze Lu, Xiaojie Jin, Zhicheng Huang, Qibin Hou, Ming-Ming Cheng, Jiashi Feng
Contrastive Masked Autoencoder (CMAE), as a new self-supervised framework, has shown its potential of learning expressive feature representations in visual image recognition.
1 code implementation • 14 Jan 2023 • Zhaohui Zheng, Yuming Chen, Qibin Hou, Xiang Li, Ming-Ming Cheng
In this paper, we study the spatial disequilibrium problem of modern object detectors and propose to quantify this ``spatial bias'' by measuring the detection performance over zones.
no code implementations • 16 Dec 2022 • Xialei Liu, Jiang-Tian Zhai, Andrew D. Bagdanov, Ke Li, Ming-Ming Cheng
Data-Free Class Incremental Learning (DFCIL) aims to sequentially learn tasks with access only to data from the current one.
no code implementations • 28 Nov 2022 • Jiang-Tian Zhai, Qi Zhang, Tong Wu, Xing-Yu Chen, Jiang-Jiang Liu, Bo Ren, Ming-Ming Cheng
By aggregating cross-modal information, the region filter selects key regions and the region adaptor updates their coordinates with text guidance.
1 code implementation • 22 Nov 2022 • Qibin Hou, Cheng-Ze Lu, Ming-Ming Cheng, Jiashi Feng
This paper does not attempt to design a state-of-the-art method for visual recognition but investigates a more efficient way to make use of convolutions to encode spatial features.
1 code implementation • 20 Oct 2022 • ShangHua Gao, Pan Zhou, Ming-Ming Cheng, Shuicheng Yan
In this work, we explore a sustainable SSL framework with two major challenges: i) learning a stronger new SSL model based on the existing pretrained SSL model, also called as "base" model, in a cost-friendly manner, ii) allowing the training of the new model to be compatible with various base models.
Ranked #1 on Semantic Segmentation on ImageNet-S
1 code implementation • 8 Oct 2022 • Shijie Li, Ming-Ming Cheng, Juergen Gall
The goal of semantic image synthesis is to generate photo-realistic images from semantic label maps.
1 code implementation • 1 Oct 2022 • Xialei Liu, Yu-Song Hu, Xu-Sheng Cao, Andrew D. Bagdanov, Ke Li, Ming-Ming Cheng
However, conventional CIL methods consider a balanced distribution for each new task, which ignores the prevalence of long-tailed distributions in the real world.
3 code implementations • 18 Sep 2022 • Meng-Hao Guo, Cheng-Ze Lu, Qibin Hou, ZhengNing Liu, Ming-Ming Cheng, Shi-Min Hu
Notably, SegNeXt outperforms EfficientNet-L2 w/ NAS-FPN and achieves 90. 6% mIoU on the Pascal VOC 2012 test leaderboard using only 1/10 parameters of it.
no code implementations • 18 Aug 2022 • Yu-Huan Wu, Da Zhang, Le Zhang, Xin Zhan, Dengxin Dai, Yun Liu, Ming-Ming Cheng
Current efficient LiDAR-based detection frameworks are lacking in exploiting object relations, which naturally present in both spatial and temporal manners.
1 code implementation • 27 Jul 2022 • Zhicheng Huang, Xiaojie Jin, Chengze Lu, Qibin Hou, Ming-Ming Cheng, Dongmei Fu, Xiaohui Shen, Jiashi Feng
The target encoder, fed with the full images, enhances the feature discriminability via contrastive learning with its online counterpart.
1 code implementation • 21 Jul 2022 • Zuo-Liang Zhu, Zhen Li, Rui-Xun Zhang, Chun-Le Guo, Ming-Ming Cheng
Lighting is a determining factor in photography that affects the style, expression of emotion, and even quality of images.
no code implementations • 7 Jul 2022 • Gang Xu, Yuchen Yang, Jun Xu, Liang Wang, Xian-Tong Zhen, Ming-Ming Cheng
To this end, we propose a lightweight Feature Decomposition Aggregation Network (FDAN).
no code implementations • 5 Jul 2022 • Hongzhi Huang, Yu Wang, QinGhua Hu, Ming-Ming Cheng
In this study, we propose a novel method, called Class-Specific Semantic Reconstruction (CSSR), that integrates the power of AE and prototype learning.
2 code implementations • 14 Jun 2022 • ShangHua Gao, Zhong-Yu Li, Qi Han, Ming-Ming Cheng, Liang Wang
Our search scheme exploits both global search to find the coarse combinations and local search to get the refined receptive field combinations further.
Ranked #2 on Instance Segmentation on COCO 2017 val (AP metric)
no code implementations • 10 Jun 2022 • Zhong-Yu Li, ShangHua Gao, Ming-Ming Cheng
Learning representations with self-supervision for convolutional networks (CNN) has proven effective for vision tasks.
Ranked #5 on Semantic Segmentation on ImageNet-S
1 code implementation • 13 May 2022 • YuChao Gu, Xintao Wang, Liangbin Xie, Chao Dong, Gen Li, Ying Shan, Ming-Ming Cheng
Equipped with the VQ codebook as a facial detail dictionary and the parallel decoder design, the proposed VQFR can largely enhance the restored quality of facial details while keeping the fidelity to previous methods.
1 code implementation • 12 Apr 2022 • Zhaohui Zheng, Rongguang Ye, Qibin Hou, Dongwei Ren, Ping Wang, WangMeng Zuo, Ming-Ming Cheng
Combining these two new components, for the first time, we show that logit mimicking can outperform feature imitation and the absence of localization distillation is a critical reason for why logit mimicking underperforms for years.
1 code implementation • CVPR 2022 • Zhen Li, Cheng-Ze Lu, Jianhua Qin, Chun-Le Guo, Ming-Ming Cheng
Optical flow, which captures motion information across frames, is exploited in recent video inpainting methods through propagating pixels along its trajectories.
Ranked #1 on Video Inpainting on YouTube-VOS 2018
no code implementations • 25 Mar 2022 • Zheng Lin, Zhao Zhang, Kang-Rui Zhang, Bo Ren, Ming-Ming Cheng
Our IST method can serve as a brush, dip style from anywhere, and then paint to any region of the target content image.
1 code implementation • CVPR 2022 • Chang-Bin Zhang, Jia-Wen Xiao, Xialei Liu, Ying-Cong Chen, Ming-Ming Cheng
In this work, we study the continual semantic segmentation problem, where the deep neural networks are required to incorporate new classes continually without catastrophic forgetting.
Ranked #1 on Domain 1-1 on Cityscapes
Class Incremental Learning Continual Semantic Segmentation +15
17 code implementations • 20 Feb 2022 • Meng-Hao Guo, Cheng-Ze Lu, Zheng-Ning Liu, Ming-Ming Cheng, Shi-Min Hu
In this paper, we propose a novel linear attention named large kernel attention (LKA) to enable self-adaptive and long-range correlations in self-attention while avoiding its shortcomings.
Ranked #1 on Panoptic Segmentation on COCO panoptic
no code implementations • 23 Jan 2022 • Ming-Ming Cheng, Peng-Tao Jiang, Ling-Hao Han, Liang Wang, Philip Torr
The proposed framework can generate a deep hierarchy of strongly associated supporting evidence for the network decision, which provides insight into the decision-making process.
1 code implementation • CVPR 2022 • Zheng Lin, Zheng-Peng Duan, Zhao Zhang, Chun-Le Guo, Ming-Ming Cheng
However, the global view makes the model lose focus from later clicks, and is not in line with user intentions.
Ranked #5 on Interactive Segmentation on SBD
no code implementations • 17 Dec 2021 • Dingwen Zhang, Wenyuan Zeng, Guangyu Guo, Chaowei Fang, Lechao Cheng, Ming-Ming Cheng, Junwei Han
Current weakly supervised semantic segmentation (WSSS) frameworks usually contain the separated mask-refinement model and the main semantic region mining model.
Knowledge Distillation Weakly supervised Semantic Segmentation +1
2 code implementations • 15 Nov 2021 • Meng-Hao Guo, Tian-Xing Xu, Jiang-Jiang Liu, Zheng-Ning Liu, Peng-Tao Jiang, Tai-Jiang Mu, Song-Hai Zhang, Ralph R. Martin, Ming-Ming Cheng, Shi-Min Hu
Humans can naturally and effectively find salient regions in complex scenes.
1 code implementation • ICCV 2021 • Yu Zhang, Chang-Bin Zhang, Peng-Tao Jiang, Ming-Ming Cheng, Feng Mao
In this paper, we address the problem of personalized image segmentation.
2 code implementations • 23 Jun 2021 • Qibin Hou, Zihang Jiang, Li Yuan, Ming-Ming Cheng, Shuicheng Yan, Jiashi Feng
By realizing the importance of the positional information carried by 2D feature representations, unlike recent MLP-like models that encode the spatial information along the flattened spatial dimensions, Vision Permutator separately encodes the feature representations along the height and width dimensions with linear projections.
4 code implementations • 22 Jun 2021 • Yu-Huan Wu, Yun Liu, Xin Zhan, Ming-Ming Cheng
A popular solution to this problem is to use a single pooling operation to reduce the sequence length.
Ranked #3 on RGB Salient Object Detection on DUTS-TE
3 code implementations • IEEE 2021 • Peng-Tao Jiang, Chang-Bin Zhang, Qibin Hou, Ming-Ming Cheng, Yunchao Wei
To evaluate the quality of the class activation maps produced by LayerCAM, we apply them to weakly-supervised object localization and semantic segmentation.
Semantic Segmentation Weakly Supervised Object Localization +1
no code implementations • CVPR 2021 • Shang-Hua Gao, Qi Han, Duo Li, Ming-Ming Cheng, Pai Peng
We propose to add a simple yet effective feature calibration scheme into the centering and scaling operations of BatchNorm, enhancing the instance-specific representations with the negligible computational cost.
1 code implementation • ICLR 2022 • Qi Han, Zejia Fan, Qi Dai, Lei Sun, Ming-Ming Cheng, Jiaying Liu, Jingdong Wang
Sparse connectivity: there is no connection across channels, and each position is connected to the positions within a small local window.
3 code implementations • 6 Jun 2021 • ShangHua Gao, Zhong-Yu Li, Ming-Hsuan Yang, Ming-Ming Cheng, Junwei Han, Philip Torr
In this work, we propose a new problem of large-scale unsupervised semantic segmentation (LUSS) with a newly created benchmark dataset to help the research progress.
Ranked #1 on Unsupervised Semantic Segmentation on ImageNet-S-50
2 code implementations • 25 May 2021 • Jia-Wang Bian, Huangying Zhan, Naiyan Wang, Zhichao Li, Le Zhang, Chunhua Shen, Ming-Ming Cheng, Ian Reid
We propose a monocular depth estimator SC-Depth, which requires only unlabelled videos for training and enables the scale-consistent prediction at inference time.
Ranked #37 on Monocular Depth Estimation on KITTI Eigen split
2 code implementations • 7 May 2021 • Deng-Ping Fan, Jing Zhang, Gang Xu, Ming-Ming Cheng, Ling Shao
This design bias has led to a saturation in performance for state-of-the-art SOD models when evaluated on existing datasets.
3 code implementations • 21 Apr 2021 • Chongyi Li, Chunle Guo, Linghao Han, Jun Jiang, Ming-Ming Cheng, Jinwei Gu, Chen Change Loy
Low-light image enhancement (LLIE) aims at improving the perception or interpretability of an image captured in an environment with poor illumination.
1 code implementation • CVPR 2021 • Gang Xu, Jun Xu, Zhen Li, Liang Wang, Xing Sun, Ming-Ming Cheng
To well exploit the temporal information, we propose a Locally-temporal Feature Comparison (LFC) module, along with the Bi-directional Deformable ConvLSTM, to extract short-term and long-term motion cues in videos.
2 code implementations • CVPR 2022 • Zhaohui Zheng, Rongguang Ye, Ping Wang, Dongwei Ren, WangMeng Zuo, Qibin Hou, Ming-Ming Cheng
Previous KD methods for object detection mostly focus on imitating deep features within the imitation regions instead of mimicking classification logit due to its inefficiency in distilling localization information and trivial improvement.
1 code implementation • 20 Feb 2021 • Deng-Ping Fan, Ge-Peng Ji, Ming-Ming Cheng, Ling Shao
We present the first systematic study on concealed object detection (COD), which aims to identify objects that are "perfectly" embedded in their background.
Ranked #1 on Camouflaged Object Segmentation on CAMO (using extra training data)
Camouflaged Object Segmentation Dichotomous Image Segmentation +1
2 code implementations • CVPR 2021 • Shang-Hua Gao, Qi Han, Zhong-Yu Li, Pai Peng, Liang Wang, Ming-Ming Cheng
Our search scheme exploits both global search to find the coarse combinations and local search to get the refined receptive field combination patterns further.
Ranked #14 on Action Segmentation on Breakfast
no code implementations • ICCV 2021 • Yu-Chao Gu, Shang-Hua Gao, Xu-Sheng Cao, Peng Du, Shao-Ping Lu, Ming-Ming Cheng
Existing salient object detection (SOD) models usually focus on either backbone feature extractors or saliency heads, ignoring their relations.
1 code implementation • 24 Dec 2020 • Yu-Huan Wu, Yun Liu, Le Zhang, Ming-Ming Cheng, Bo Ren
In this paper, we tap into this gap and show that enhancing high- level features is essential for SOD as well.
1 code implementation • 24 Dec 2020 • Yu-Huan Wu, Yun Liu, Jun Xu, Jia-Wang Bian, Yu-Chao Gu, Ming-Ming Cheng
Therefore, we propose an implicit depth restoration (IDR) technique to strengthen the mobile networks' feature representation capability for RGB-D SOD.
no code implementations • 21 Dec 2020 • Jiang-Jiang Liu, Zhi-Ang Liu, Ming-Ming Cheng
Our approach can cooperate with various existing U-shape-based salient object detection methods by substituting the connections between the bottom-up and top-down pathways.
1 code implementation • NeurIPS 2020 • Wen-Da Jin, Jun Xu, Ming-Ming Cheng, Yi Zhang, Wei Guo
Intra-saliency and inter-saliency cues have been extensively studied for co-saliency detection (Co-SOD).
3 code implementations • 26 Nov 2020 • Qijian Zhang, Runmin Cong, Chongyi Li, Ming-Ming Cheng, Yuming Fang, Xiaochun Cao, Yao Zhao, Sam Kwong
Despite the remarkable advances in visual saliency analysis for natural scene images (NSIs), salient object detection (SOD) for optical remote sensing images (RSIs) still remains an open and challenging problem.
2 code implementations • 25 Nov 2020 • Chang-Bin Zhang, Peng-Tao Jiang, Qibin Hou, Yunchao Wei, Qi Han, Zhen Li, Ming-Ming Cheng
Experiments demonstrate that based on the same classification models, the proposed approach can effectively improve the classification performance on CIFAR-100, ImageNet, and fine-grained datasets.
no code implementations • 17 Oct 2020 • Yunchao Wei, Shuai Zheng, Ming-Ming Cheng, Hang Zhao, LiWei Wang, Errui Ding, Yi Yang, Antonio Torralba, Ting Liu, Guolei Sun, Wenguan Wang, Luc van Gool, Wonho Bae, Junhyug Noh, Jinhwan Seo, Gunhee Kim, Hao Zhao, Ming Lu, Anbang Yao, Yiwen Guo, Yurong Chen, Li Zhang, Chuangchuang Tan, Tao Ruan, Guanghua Gu, Shikui Wei, Yao Zhao, Mariia Dobko, Ostap Viniavskyi, Oles Dobosevych, Zhendong Wang, Zhenyuan Chen, Chen Gong, Huanqing Yan, Jun He
The purpose of the Learning from Imperfect Data (LID) workshop is to inspire and facilitate the research in developing novel approaches that would harness the imperfect data and improve the data-efficiency during training.
no code implementations • CVPR 2021 • Yu-Chao Gu, Li-Juan Wang, Yun Liu, Yi Yang, Yu-Huan Wu, Shao-Ping Lu, Ming-Ming Cheng
DARTS mainly focuses on the operation search and derives the cell topology from the operation weights.
1 code implementation • 10 Sep 2020 • Yun Liu, Yu-Huan Wu, Pei-Song Wen, Yu-Jun Shi, Yu Qiu, Ming-Ming Cheng
For each proposal, this MIL framework can simultaneously compute probability distributions and category-aware semantic features, with which we can formulate a large undirected graph.
Ranked #1 on Image-level Supervised Instance Segmentation on COCO test-dev (using extra training data)
Image-level Supervised Instance Segmentation Multiple Instance Learning +2
1 code implementation • 1 Sep 2020 • Yu-Chao Gu, Le Zhang, Yun Liu, Shao-Ping Lu, Ming-Ming Cheng
Recent generative methods formulate GZSL as a missing data problem, which mainly adopts GANs or VAEs to generate visual features for unseen classes.
1 code implementation • 28 Aug 2020 • Yu-Huan Wu, Yun Liu, Le Zhang, Wang Gao, Ming-Ming Cheng
Much of the recent efforts on salient object detection (SOD) have been devoted to producing accurate saliency maps without being aware of their instance labels.
9 code implementations • 1 Aug 2020 • Tao Zhou, Deng-Ping Fan, Ming-Ming Cheng, Jianbing Shen, Ling Shao
Further, considering that the light field can also provide depth maps, we review SOD models and popular benchmark datasets from this domain as well.
no code implementations • 10 Jul 2020 • Xiao-Chang Liu, Xuan-Yi Li, Ming-Ming Cheng, Peter Hall
Our contribution is to introduce a neural architecture that supports transfer of geometric style.
1 code implementation • 8 Jul 2020 • Xin-Yu Zhang, Taihong Xiao, HaoLin Jia, Ming-Ming Cheng, Ming-Hsuan Yang
In this work, we propose a simple yet effective meta-learning algorithm in semi-supervised learning.
2 code implementations • 7 Jul 2020 • Deng-Ping Fan, Tengpeng Li, Zheng Lin, Ge-Peng Ji, Dingwen Zhang, Ming-Ming Cheng, Huazhu Fu, Jianbing Shen
CoSOD is an emerging and rapidly growing extension of salient object detection (SOD), which aims to detect the co-occurring salient objects in a group of images.
Ranked #6 on Co-Salient Object Detection on CoCA
no code implementations • 3 Jul 2020 • Shipeng Fu, Zhen Li, Jun Xu, Ming-Ming Cheng, Zitao Liu, Xiaomin Yang
Knowledge distillation is a standard teacher-student learning framework to train a light-weight student network under the guidance of a well-trained large teacher network.
1 code implementation • 16 Jun 2020 • Shijie Li, Yazan Abu Farha, Yun Liu, Ming-Ming Cheng, Juergen Gall
Despite the capabilities of these approaches in capturing temporal dependencies, their predictions suffer from over-segmentation errors.
Ranked #2 on Action Segmentation on Assembly101
no code implementations • 6 May 2020 • Kai Zhao, Xin-Yu Zhang, Qi Han, Ming-Ming Cheng
Convolutional neural networks (CNNs) are typically over-parameterized, bringing considerable computational overhead and memory footprint in inference.
1 code implementation • ECCV 2020 • Zhao Zhang, Wenda Jin, Jun Xu, Ming-Ming Cheng
Co-saliency detection (Co-SOD) aims to segment the common salient foreground in a group of relevant images.
Ranked #6 on Co-Salient Object Detection on CoSOD3k
1 code implementation • 23 Apr 2020 • Ying-Jun Du, Jun Xu, Xian-Tong Zhen, Ming-Ming Cheng, Ling Shao
In this paper, we propose a Conditional Variational Image Deraining (CVID) network for better deraining performance, leveraging the exclusive generative ability of Conditional Variational Auto-Encoder (CVAE) on providing diverse predictions for the rainy image.
no code implementations • 18 Apr 2020 • Jiang-Jiang Liu, Qibin Hou, Ming-Ming Cheng
To evaluate the performance of our proposed network on these tasks, we conduct exhaustive experiments on multiple representative datasets.
1 code implementation • 15 Apr 2020 • Yu-Huan Wu, Shang-Hua Gao, Jie Mei, Jun Xu, Deng-Ping Fan, Rong-Guo Zhang, Ming-Ming Cheng
The chest CT scan test provides a valuable complementary tool to the RT-PCR test, and it can identify the patients in the early-stage with high sensitivity.
1 code implementation • 9 Apr 2020 • Lin-Zhuo Chen, Zheng Lin, Ziqin Wang, Yong-Liang Yang, Ming-Ming Cheng
S-Conv is competent to infer the sampling offset of the convolution kernel guided by the 3D spatial information, helping the convolutional layer adjust the receptive field and adapt to geometric transformations.
Ranked #2 on Semantic Segmentation on RSMSS
2 code implementations • CVPR 2020 • Qibin Hou, Li Zhang, Ming-Ming Cheng, Jiashi Feng
Spatial pooling has been proven highly effective in capturing long-range contextual information for pixel-wise prediction tasks, such as scene parsing.
Ranked #26 on Semantic Segmentation on Cityscapes test
1 code implementation • ECCV 2020 • Shang-Hua Gao, Yong-Qiang Tan, Ming-Ming Cheng, Chengze Lu, Yunpeng Chen, Shuicheng Yan
Salient object detection models often demand a considerable amount of computation cost to make precise prediction for each pixel, making them hardly applicable on low-power devices.
1 code implementation • ECCV 2020 • Kai Zhao, Qi Han, Chang-Bin Zhang, Jun Xu, Ming-Ming Cheng
In addition to the proposed method, we design an evaluation metric to assess the quality of line detection and construct a large scale dataset for the line detection task.
Ranked #2 on Line Detection on NKL
1 code implementation • 19 Feb 2020 • Xin-Yu Zhang, Kai Zhao, Taihong Xiao, Ming-Ming Cheng, Ming-Hsuan Yang
Recent advances in convolutional neural networks(CNNs) usually come with the expense of excessive computational overhead and memory footprint.
no code implementations • 24 Dec 2019 • Le Zhang, Zenglin Shi, Joey Tianyi Zhou, Ming-Ming Cheng, Yun Liu, Jia-Wang Bian, Zeng Zeng, Chunhua Shen
Specifically, with a diagnostic analysis, we show that the recurrent structure may not be effective to learn temporal dependencies than what we expected and implicitly yields an orderless representation.
no code implementations • 27 Nov 2019 • Xin-Yu Zhang, Le Zhang, Zao-Yi Zheng, Yun Liu, Jia-Wang Bian, Ming-Ming Cheng
The effectiveness of the triplet loss heavily relies on the triplet selection, in which a common practice is to first sample intra-class patches (positives) from the dataset for batch construction and then mine in-batch negatives to form triplets.
no code implementations • 25 Sep 2019 • Yujun Shi, Benben Liao, Guangyong Chen, Yun Liu, Ming-Ming Cheng, Jiashi Feng
Then, we show by experiments that DNNs under standard training rely heavily on optimizing the non-robust component in achieving decent performance.
1 code implementation • ICCV 2019 • Chaohao Xie, Shaohui Liu, Chao Li, Ming-Ming Cheng, WangMeng Zuo, Xiao Liu, Shilei Wen, Errui Ding
Most convolutional network (CNN)-based inpainting methods adopt standard convolution to indistinguishably treat valid pixels and holes, making them limited in handling irregular holes and more likely to generate inpainting results with color discrepancy and blurriness.
Ranked #2 on Image Inpainting on Paris StreetView
2 code implementations • NeurIPS 2019 • Jia-Wang Bian, Zhichao Li, Naiyan Wang, Huangying Zhan, Chunhua Shen, Ming-Ming Cheng, Ian Reid
To the best of our knowledge, this is the first work to show that deep networks trained using unlabelled monocular videos can predict globally scale-consistent camera trajectories over a long video sequence.
Ranked #42 on Monocular Depth Estimation on KITTI Eigen split
no code implementations • 26 Aug 2019 • Jia-Wang Bian, Yu-Huan Wu, Ji Zhao, Yun Liu, Le Zhang, Ming-Ming Cheng, Ian Reid
According to this, we propose three high-quality matching systems and a Coarse-to-Fine RANSAC estimator.
no code implementations • 24 Aug 2019 • Le Zhang, Zenglin Shi, Ming-Ming Cheng, Yun Liu, Jia-Wang Bian, Joey Tianyi Zhou, Guoyan Zheng, Zeng Zeng
Nonlinear regression has been extensively employed in many computer vision problems (e. g., crowd counting, age estimation, affective computing).
no code implementations • 22 Aug 2019 • Jia-Xing Zhao, Jiang-Jiang Liu, Den-Ping Fan, Yang Cao, Jufeng Yang, Ming-Ming Cheng
In the second step, we integrate the local edge information and global location information to obtain the salient edge features.
1 code implementation • ICCV 2019 • Deng-Ping Fan, Shengchuan Zhang, Yu-Huan Wu, Yun Liu, Ming-Ming Cheng, Bo Ren, Paul L. Rosin, Rongrong Ji
In this paper, we design a perceptual metric, called Structure Co-Occurrence Texture (Scoot), which simultaneously considers the block-level spatial structure and co-occurrence texture statistics.
1 code implementation • 18 Aug 2019 • Jinshan Pan, Yang Liu, Deqing Sun, Jimmy Ren, Ming-Ming Cheng, Jian Yang, Jinhui Tang
We present a simple and effective image super-resolution algorithm that imposes an image formation constraint on the deep neural networks via pixel substitution.
2 code implementations • 15 Jul 2019 • Deng-Ping Fan, Zheng Lin, Jia-Xing Zhao, Yun Liu, Zhao Zhang, Qibin Hou, Menglong Zhu, Ming-Ming Cheng
The use of RGB-D information for salient object detection has been extensively explored in recent years.
Ranked #4 on RGB-D Salient Object Detection on RGBD135
1 code implementation • 17 Jun 2019 • Jun Xu, Yuan Huang, Ming-Ming Cheng, Li Liu, Fan Zhu, Zhou Xu, Ling Shao
A simple but useful observation on our NAC is: as long as the noise is weak, it is feasible to learn a self-supervised network only with the corrupted image, approximating the optimal parameters of a supervised network learned with pairs of noisy and clean images.
no code implementations • 6 Jun 2019 • Yujun Shi, Benben Liao, Guangyong Chen, Yun Liu, Ming-Ming Cheng, Jiashi Feng
Despite many previous works studying the reason behind such adversarial behavior, the relationship between the generalization performance and adversarial behavior of DNNs is still little understood.
1 code implementation • 14 May 2019 • Lin-Zhuo Chen, Xuan-Yi Li, Deng-Ping Fan, Kai Wang, Shao-Ping Lu, Ming-Ming Cheng
We design a novel Local Spatial Aware (LSA) layer, which can learn to generate Spatial Distribution Weights (SDWs) hierarchically based on the spatial relationship in local region for spatial independent operations, to establish the relationship between these operations and spatial distribution, thus capturing the local geometric structure sensitively. We further propose the LSANet, which is based on LSA layer, aggregating the spatial information with associated features in each layer of the network better in network design. The experiments show that our LSANet can achieve on par or better performance than the state-of-the-art methods when evaluating on the challenging benchmark datasets.
5 code implementations • CVPR 2019 • Jiang-Jiang Liu, Qibin Hou, Ming-Ming Cheng, Jiashi Feng, Jianmin Jiang
We further design a feature aggregation module (FAM) to make the coarse-level semantic information well fused with the fine-level features from the top-down pathway.
Ranked #1 on RGB Salient Object Detection on SOD
20 code implementations • 2 Apr 2019 • Shang-Hua Gao, Ming-Ming Cheng, Kai Zhao, Xin-Yu Zhang, Ming-Hsuan Yang, Philip Torr
We evaluate the Res2Net block on all these models and demonstrate consistent performance gains over baseline models on widely-used datasets, e. g., CIFAR-100 and ImageNet.
Ranked #2 on Image Classification on GasHisSDB
1 code implementation • 28 Mar 2019 • Yun Liu, Ming-Ming Cheng, Xin-Yu Zhang, Guang-Yu Nie, Meng Wang
Recent progress on salient object detection mainly aims at exploiting how to effectively integrate multi-scale convolutional features in convolutional neural networks (CNNs).
no code implementations • 23 Jan 2019 • Jie Liang, Jufeng Yang, Ming-Ming Cheng, Paul L. Rosin, Liang Wang
In this paper we propose a unified framework to simultaneously discover the number of clusters and group the data points into them using subspace clustering.
no code implementations • 28 Dec 2018 • Yun Liu, Yu Qiu, Le Zhang, Jia-Wang Bian, Guang-Yu Nie, Ming-Ming Cheng
In this paper, we observe that the contexts of a natural image can be well expressed by a high-to-low self-learning of side-output convolutional features.
no code implementations • NeurIPS 2018 • Qibin Hou, Peng-Tao Jiang, Yunchao Wei, Ming-Ming Cheng
To test the quality of the generated attention maps, we employ the mined object regions as heuristic cues for learning semantic segmentation models.
no code implementations • ECCV 2018 • Ruochen Fan, Qibin Hou, Ming-Ming Cheng, Gang Yu, Ralph R. Martin, Shi-Min Hu
We also combine our method with Mask R-CNN for instance segmentation, and demonstrated for the first time the ability of weakly supervised instance segmentation using only keyword annotations.
Ranked #3 on Image-level Supervised Instance Segmentation on COCO test-dev (using extra training data)
graph partitioning Image-level Supervised Instance Segmentation +4
no code implementations • 7 Aug 2018 • Jia-Wang Bian, Ruihan Yang, Yun Liu, Le Zhang, Ming-Ming Cheng, Ian Reid, WenHai Wu
This leads to a critical absence in this field that there is no standard datasets and evaluation metrics to evaluate different feature matchers fairly.
no code implementations • 1 Jul 2018 • Kai Zhao, Wei Shen, ShangHua Gao, Dandan Li, Ming-Ming Cheng
In natural images, the scales (thickness) of object skeletons may dramatically vary among objects and object parts.
1 code implementation • CVPR 2018 • Zenglin Shi, Le Zhang, Yun Liu, Xiaofeng Cao, Yangdong Ye, Ming-Ming Cheng, Guoyan Zheng
Deep convolutional networks (ConvNets) have achieved unprecedented performances on many computer vision tasks.
Ranked #9 on Crowd Counting on WorldExpo’10
2 code implementations • 26 May 2018 • Deng-Ping Fan, Cheng Gong, Yang Cao, Bo Ren, Ming-Ming Cheng, Ali Borji
The existing binary foreground map (FM) measures to address various types of errors in either pixel-wise or structural ways.
no code implementations • ICCV 2019 • Kai Zhao, Shang-Hua Gao, Wenguan Wang, Ming-Ming Cheng
By reformulating the standard F-measure we propose the relaxed F-measure which is differentiable w. r. t the posterior and can be easily appended to the back of CNNs as the loss function.
no code implementations • 19 May 2018 • Yun Liu, Yujun Shi, Jia-Wang Bian, Le Zhang, Ming-Ming Cheng, Jiashi Feng
Collecting sufficient annotated data is very expensive in many applications, especially for pixel-level prediction tasks such as semantic segmentation.
1 code implementation • 9 Apr 2018 • Deng-Ping Fan, Shengchuan Zhang, Yu-Huan Wu, Ming-Ming Cheng, Bo Ren, Rongrong Ji, Paul L. Rosin
However, human perception of the similarity of two sketches will consider both structure and texture as essential factors and is not sensitive to slight ("pixel-level") mismatches.
1 code implementation • 9 Apr 2018 • Yun Liu, Ming-Ming Cheng, Deng-Ping Fan, Le Zhang, Jiawang Bian, DaCheng Tao
Semantic edge detection (SED), which aims at jointly extracting edges as well as their category information, has far-reaching applications in domains such as semantic segmentation, object proposal generation, and object recognition.
no code implementations • 27 Mar 2018 • Qibin Hou, Jiang-Jiang Liu, Ming-Ming Cheng, Ali Borji, Philip H. S. Torr
Although these tasks are inherently very different, we show that our unified approach performs very well on all of them and works far better than current single-purpose state-of-the-art methods.
no code implementations • 27 Mar 2018 • Qibin Hou, Ming-Ming Cheng, Jiang-Jiang Liu, Philip H. S. Torr
In this paper, we improve semantic segmentation by automatically learning from Flickr images associated with a particular keyword, without relying on any explicit user annotations, thus substantially alleviating the dependence on accurate annotations when compared to previous weakly supervised methods.
no code implementations • ECCV 2018 • Deng-Ping Fan, Ming-Ming Cheng, Jiang-Jiang Liu, Shang-Hua Gao, Qibin Hou, Ali Borji
Our analysis identifies a serious design bias of existing SOD datasets which assumes that each image contains at least one clearly outstanding salient object in low clutter.
no code implementations • 9 Mar 2018 • Runmin Cong, Jianjun Lei, Huazhu Fu, Ming-Ming Cheng, Weisi Lin, Qingming Huang
With the acquisition technology development, more comprehensive information, such as depth cue, inter-image correspondence, or temporal relationship, is available to extend image saliency detection to RGBD saliency detection, co-saliency detection, or video saliency detection.
1 code implementation • CVPR 2018 • Wenguan Wang, Jianbing Shen, Fang Guo, Ming-Ming Cheng, Ali Borji
Existing video saliency datasets lack variety and generality of common dynamic scenes and fall short in covering challenging situations in unconstrained environments.
no code implementations • 5 Jan 2018 • Kai Zhao, Wei Shen, Shang-Hua Gao, Dandan Li, Ming-Ming Cheng
In natural images, the scales (thickness) of object skeletons may dramatically vary among objects and object parts, making object skeleton detection a challenging problem.
Ranked #2 on Object Skeleton Detection on SK-LARGE
1 code implementation • CVPR 2019 • Ruochen Fan, Ming-Ming Cheng, Qibin Hou, Tai-Jiang Mu, Jingdong Wang, Shi-Min Hu
Taking into account the category-independent property of each target, we design a single stage salient instance segmentation framework, with a novel segmentation branch.
no code implementations • 12 Sep 2017 • Jia-Wang Bian, Le Zhang, Yun Liu, Wen-Yan Lin, Ming-Ming Cheng, Ian D. Reid
To this end, we present a uniform benchmark with novel evaluation metrics and a large-scale dataset for evaluating the overall performance of image matching methods.
1 code implementation • ICCV 2017 • Deng-Ping Fan, Ming-Ming Cheng, Yun Liu, Tao Li, Ali Borji
Our new measure simultaneously evaluates region-aware and object-aware structural similarity between a SM and a GT map.
1 code implementation • CVPR 2017 • Jia-Wang Bian, Wen-Yan Lin, Yasuyuki Matsushita, Sai-Kit Yeung, Tan-Dat Nguyen, Ming-Ming Cheng
Incorporating smoothness constraints into feature matching is known to enable ultra-robust matching.
no code implementations • CVPR 2017 • Yunchao Wei, Jiashi Feng, Xiaodan Liang, Ming-Ming Cheng, Yao Zhao, Shuicheng Yan
We investigate a principle way to progressively mine discriminative object regions using classification networks to address the weakly-supervised semantic segmentation problems.
3 code implementations • CVPR 2017 • Yun Liu, Ming-Ming Cheng, Xiao-Wei Hu, Kai Wang, Xiang Bai
Using VGG16 network, we achieve \sArt results on several available datasets.
Ranked #5 on Edge Detection on BIPED
no code implementations • 7 Dec 2016 • Qinbin Hou, Puneet Kumar Dokania, Daniela Massiceti, Yunchao Wei, Ming-Ming Cheng, Philip Torr
We focus on the following three aspects of EM: (i) initialization; (ii) latent posterior estimation (E-step) and (iii) the parameter update (M-step).
Weakly supervised Semantic Segmentation Weakly-Supervised Semantic Segmentation
no code implementations • 6 Dec 2016 • Jia-Xing Zhao, Ren Bo, Qibin Hou, Ming-Ming Cheng, Paul L. Rosin
It also has drawbacks on convergence rate as a result of both the fixed search region and separately doing the assignment step and the update step.
2 code implementations • CVPR 2017 • Qibin Hou, Ming-Ming Cheng, Xiao-Wei Hu, Ali Borji, Zhuowen Tu, Philip Torr
Recent progress on saliency detection is substantial, benefiting mostly from the explosive development of Convolutional Neural Networks (CNNs).
Ranked #4 on RGB Salient Object Detection on SBU
no code implementations • 14 Nov 2015 • Ziming Zhang, Yun Liu, Xi Chen, Yanjun Zhu, Ming-Ming Cheng, Venkatesh Saligrama, Philip H. S. Torr
We propose a novel object proposal algorithm, BING++, which inherits the virtue of good computational efficiency of BING but significantly improves its proposal localization quality.
no code implementations • 13 Oct 2015 • Stuart Golodetz, Michael Sapienza, Julien P. C. Valentin, Vibhav Vineet, Ming-Ming Cheng, Anurag Arnab, Victor A. Prisacariu, Olaf Kähler, Carl Yuheng Ren, David W. Murray, Shahram Izadi, Philip H. S. Torr
We present an open-source, real-time implementation of SemanticPaint, a system for geometric reconstruction, object-class segmentation and learning of 3D scenes.
1 code implementation • 10 Sep 2015 • Yunchao Wei, Xiaodan Liang, Yunpeng Chen, Xiaohui Shen, Ming-Ming Cheng, Jiashi Feng, Yao Zhao, Shuicheng Yan
Then, a better network called Enhanced-DCNN is learned with supervision from the predicted segmentation masks of simple images based on the Initial-DCNN as well as the image-level annotations.
no code implementations • 5 Jan 2015 • Ali Borji, Ming-Ming Cheng, Huaizu Jiang, Jia Li
We extensively compare, qualitatively and quantitatively, 40 state-of-the-art models (28 salient object detection, 10 fixation prediction, 1 objectness, and 1 baseline) over 6 challenging datasets for the purpose of benchmarking salient object detection and segmentation methods.
no code implementations • 18 Nov 2014 • Ali Borji, Ming-Ming Cheng, Qibin Hou, Huaizu Jiang, Jia Li
Detecting and segmenting salient objects from natural scenes, often referred to as salient object detection, has attracted great interest in computer vision.
no code implementations • CVPR 2013 • Huaizu Jiang, Zejian yuan, Ming-Ming Cheng, Yihong Gong, Nanning Zheng, Jingdong Wang
Our method, which is based on multi-level image segmentation, utilizes the supervised learning approach to map the regional feature vector to a saliency score.
no code implementations • CVPR 2014 • Ming-Ming Cheng, Ziming Zhang, Wen-Yan Lin, Philip Torr
Training a generic objectness measure to produce a small set of candidate object windows, has been shown to speed up the classical sliding window object detection paradigm.
no code implementations • CVPR 2014 • Shuai Zheng, Ming-Ming Cheng, Jonathan Warrell, Paul Sturgess, Vibhav Vineet, Carsten Rother, Philip H. S. Torr
The concepts of objects and attributes are both important for describing images precisely, since verbal descriptions often contain both adjectives and nouns (e. g. "I see a shiny red chair').
no code implementations • 16 Oct 2013 • Ming-Ming Cheng, Shuai Zheng, Wen-Yan Lin, Jonathan Warrell, Vibhav Vineet, Paul Sturgess, Nigel Crook, Niloy Mitra, Philip Torr
This allows us to formulate the image parsing problem as one of jointly estimating per-pixel object and attribute labels from a set of training images.
no code implementations • ACM Transactions on Graphics 2009 • Tao Chen, Ming-Ming Cheng, Ping Tan, Ariel Shamir, Shi-Min Hu
The composed picture is generated by seamlessly stitching several photographs in agreement with the sketch and text labels; these are found by searching the Internet.