Models, code, and papers for "Ming Liu":

Learning to Generate Multiple Style Transfer Outputs for an Input Sentence

Feb 16, 2020
Kevin Lin, Ming-Yu Liu, Ming-Ting Sun, Jan Kautz

Text style transfer refers to the task of rephrasing a given text in a different style. While various methods have been proposed to advance the state of the art, they often assume the transfer output follows a delta distribution, and thus their models cannot generate different style transfer results for a given input text. To address the limitation, we propose a one-to-many text style transfer framework. In contrast to prior works that learn a one-to-one mapping that converts an input sentence to one output sentence, our approach learns a one-to-many mapping that can convert an input sentence to multiple different output sentences, while preserving the input content. This is achieved by applying adversarial training with a latent decomposition scheme. Specifically, we decompose the latent representation of the input sentence to a style code that captures the language style variation and a content code that encodes the language style-independent content. We then combine the content code with the style code for generating a style transfer output. By combining the same content code with a different style code, we generate a different style transfer output. Extensive experimental results with comparisons to several text style transfer approaches on multiple public datasets using a diverse set of performance metrics validate effectiveness of the proposed approach.


  Click for Model/Code and Paper
A Closed-form Solution to Photorealistic Image Stylization

Jul 27, 2018
Yijun Li, Ming-Yu Liu, Xueting Li, Ming-Hsuan Yang, Jan Kautz

Photorealistic image stylization concerns transferring style of a reference photo to a content photo with the constraint that the stylized photo should remain photorealistic. While several photorealistic image stylization methods exist, they tend to generate spatially inconsistent stylizations with noticeable artifacts. In this paper, we propose a method to address these issues. The proposed method consists of a stylization step and a smoothing step. While the stylization step transfers the style of the reference photo to the content photo, the smoothing step ensures spatially consistent stylizations. Each of the steps has a closed-form solution and can be computed efficiently. We conduct extensive experimental validations. The results show that the proposed method generates photorealistic stylization outputs that are more preferred by human subjects as compared to those by the competing methods while running much faster. Source code and additional results are available at https://github.com/NVIDIA/FastPhotoStyle .

* Accepted by ECCV 2018 

  Click for Model/Code and Paper
WebSeg: Learning Semantic Segmentation from Web Searches

Mar 27, 2018
Qibin Hou, Ming-Ming Cheng, Jiangjiang 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. To solve such a challenging problem, we leverage several low-level cues (such as saliency, edges, etc.) to help generate a proxy ground truth. Due to the diversity of web-crawled images, we anticipate a large amount of 'label noise' in which other objects might be present. We design an online noise filtering scheme which is able to deal with this label noise, especially in cluttered images. We use this filtering strategy as an auxiliary module to help assist the segmentation network in learning cleaner proxy annotations. Extensive experiments on the popular PASCAL VOC 2012 semantic segmentation benchmark show surprising good results in both our WebSeg (mIoU = 57.0%) and weakly supervised (mIoU = 63.3%) settings.

* Submitted to ECCV2018 

  Click for Model/Code and Paper
Richer Convolutional Features for Edge Detection

Apr 09, 2017
Yun Liu, Ming-Ming Cheng, Xiaowei Hu, Kai Wang, Xiang Bai

In this paper, we propose an accurate edge detector using richer convolutional features (RCF). Since objects in nature images have various scales and aspect ratios, the automatically learned rich hierarchical representations by CNNs are very critical and effective to detect edges and object boundaries. And the convolutional features gradually become coarser with receptive fields increasing. Based on these observations, our proposed network architecture makes full use of multiscale and multi-level information to perform the image-to-image edge prediction by combining all of the useful convolutional features into a holistic framework. It is the first attempt to adopt such rich convolutional features in computer vision tasks. Using VGG16 network, we achieve \sArt results on several available datasets. When evaluating on the well-known BSDS500 benchmark, we achieve ODS F-measure of \textbf{.811} while retaining a fast speed (\textbf{8} FPS). Besides, our fast version of RCF achieves ODS F-measure of \textbf{.806} with \textbf{30} FPS.

* IEEE TPAMI 2019 
* IEEE CVPR 2017 

  Click for Model/Code and Paper
A Simple Pooling-Based Design for Real-Time Salient Object Detection

Apr 21, 2019
Jiang-Jiang Liu, Qibin Hou, Ming-Ming Cheng, Jiashi Feng, Jianmin Jiang

We solve the problem of salient object detection by investigating how to expand the role of pooling in convolutional neural networks. Based on the U-shape architecture, we first build a global guidance module (GGM) upon the bottom-up pathway, aiming at providing layers at different feature levels the location information of potential salient objects. 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. By adding FAMs after the fusion operations in the top-down pathway, coarse-level features from the GGM can be seamlessly merged with features at various scales. These two pooling-based modules allow the high-level semantic features to be progressively refined, yielding detail enriched saliency maps. Experiment results show that our proposed approach can more accurately locate the salient objects with sharpened details and hence substantially improve the performance compared to the previous state-of-the-arts. Our approach is fast as well and can run at a speed of more than 30 FPS when processing a $300 \times 400$ image. Code can be found at http://mmcheng.net/poolnet/.

* Accepted by CVPR2019 

  Click for Model/Code and Paper
Superpixel Sampling Networks

Jul 26, 2018
Varun Jampani, Deqing Sun, Ming-Yu Liu, Ming-Hsuan Yang, Jan Kautz

Superpixels provide an efficient low/mid-level representation of image data, which greatly reduces the number of image primitives for subsequent vision tasks. Existing superpixel algorithms are not differentiable, making them difficult to integrate into otherwise end-to-end trainable deep neural networks. We develop a new differentiable model for superpixel sampling that leverages deep networks for learning superpixel segmentation. The resulting "Superpixel Sampling Network" (SSN) is end-to-end trainable, which allows learning task-specific superpixels with flexible loss functions and has fast runtime. Extensive experimental analysis indicates that SSNs not only outperform existing superpixel algorithms on traditional segmentation benchmarks, but can also learn superpixels for other tasks. In addition, SSNs can be easily integrated into downstream deep networks resulting in performance improvements.

* ECCV2018. Project URL: https://varunjampani.github.io/ssn/ 

  Click for Model/Code and Paper
Structure-measure: A New Way to Evaluate Foreground Maps

Aug 02, 2017
Deng-Ping Fan, Ming-Ming Cheng, Yun Liu, Tao Li, Ali Borji

Foreground map evaluation is crucial for gauging the progress of object segmentation algorithms, in particular in the filed of salient object detection where the purpose is to accurately detect and segment the most salient object in a scene. Several widely-used measures such as Area Under the Curve (AUC), Average Precision (AP) and the recently proposed Fbw have been utilized to evaluate the similarity between a non-binary saliency map (SM) and a ground-truth (GT) map. These measures are based on pixel-wise errors and often ignore the structural similarities. Behavioral vision studies, however, have shown that the human visual system is highly sensitive to structures in scenes. Here, we propose a novel, efficient, and easy to calculate measure known an structural similarity measure (Structure-measure) to evaluate non-binary foreground maps. Our new measure simultaneously evaluates region-aware and object-aware structural similarity between a SM and a GT map. We demonstrate superiority of our measure over existing ones using 5 meta-measures on 5 benchmark datasets.

* Accepted by ICCV 2017 

  Click for Model/Code and Paper
Understanding Adversarial Behavior of DNNs by Disentangling Non-Robust and Robust Components in Performance Metric

Jun 06, 2019
Yujun Shi, Benben Liao, Guangyong Chen, Yun Liu, Ming-Ming Cheng, Jiashi Feng

The vulnerability to slight input perturbations is a worrying yet intriguing property of deep neural networks (DNNs). 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. In this work, we reveal such relation by introducing a metric characterizing the generalization performance of a DNN. The metric can be disentangled into an information-theoretic non-robust component, responsible for adversarial behavior, and a robust component. Then, we show by experiments that current DNNs rely heavily on optimizing the non-robust component in achieving decent performance. We also demonstrate that current state-of-the-art adversarial training algorithms indeed try to robustify the DNNs by preventing them from using the non-robust component to distinguish samples from different categories. Also, based on our findings, we take a step forward and point out the possible direction for achieving decent standard performance and adversarial robustness simultaneously. We believe that our theory could further inspire the community to make more interesting discoveries about the relationship between standard generalization and adversarial generalization of deep learning models.


  Click for Model/Code and Paper
Context-Aware Synthesis and Placement of Object Instances

Dec 07, 2018
Donghoon Lee, Sifei Liu, Jinwei Gu, Ming-Yu Liu, Ming-Hsuan Yang, Jan Kautz

Learning to insert an object instance into an image in a semantically coherent manner is a challenging and interesting problem. Solving it requires (a) determining a location to place an object in the scene and (b) determining its appearance at the location. Such an object insertion model can potentially facilitate numerous image editing and scene parsing applications. In this paper, we propose an end-to-end trainable neural network for the task of inserting an object instance mask of a specified class into the semantic label map of an image. Our network consists of two generative modules where one determines where the inserted object mask should be (i.e., location and scale) and the other determines what the object mask shape (and pose) should look like. The two modules are connected together via a spatial transformation network and jointly trained. We devise a learning procedure that leverage both supervised and unsupervised data and show our model can insert an object at diverse locations with various appearances. We conduct extensive experimental validations with comparisons to strong baselines to verify the effectiveness of the proposed network.


  Click for Model/Code and Paper
Learning Pixel-wise Labeling from the Internet without Human Interaction

May 19, 2018
Yun Liu, Yujun Shi, JiaWang Bian, Le Zhang, Ming-Ming Cheng, Jiashi Feng

Deep learning stands at the forefront in many computer vision tasks. However, deep neural networks are usually data-hungry and require a huge amount of well-annotated training samples. Collecting sufficient annotated data is very expensive in many applications, especially for pixel-level prediction tasks such as semantic segmentation. To solve this fundamental issue, we consider a new challenging vision task, Internetly supervised semantic segmentation, which only uses Internet data with noisy image-level supervision of corresponding query keywords for segmentation model training. We address this task by proposing the following solution. A class-specific attention model unifying multiscale forward and backward convolutional features is proposed to provide initial segmentation "ground truth". The model trained with such noisy annotations is then improved by an online fine-tuning procedure. It achieves state-of-the-art performance under the weakly-supervised setting on PASCAL VOC2012 dataset. The proposed framework also paves a new way towards learning from the Internet without human interaction and could serve as a strong baseline therein. Code and data will be released upon the paper acceptance.


  Click for Model/Code and Paper
Three Birds One Stone: A Unified Framework for Salient Object Segmentation, Edge Detection and Skeleton Extraction

Mar 27, 2018
Qibin Hou, Jiangjiang Liu, Ming-Ming Cheng, Ali Borji, Philip H. S. Torr

In this paper, we aim at solving pixel-wise binary problems, including salient object segmentation, skeleton extraction, and edge detection, by introducing a unified architecture. Previous works have proposed tailored methods for solving each of the three tasks independently. Here, we show that these tasks share some similarities that can be exploited for developing a unified framework. In particular, we introduce a horizontal cascade, each component of which is densely connected to the outputs of previous component. Stringing these components together allows us to effectively exploit features across different levels hierarchically to effectively address the multiple pixel-wise binary regression tasks. To assess the performance of our proposed network on these tasks, we carry out exhaustive evaluations on multiple representative datasets. 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. All the code in this paper will be publicly available.

* Submitted to ECCV2018 

  Click for Model/Code and Paper
Learning Binary Residual Representations for Domain-specific Video Streaming

Dec 14, 2017
Yi-Hsuan Tsai, Ming-Yu Liu, Deqing Sun, Ming-Hsuan Yang, Jan Kautz

We study domain-specific video streaming. Specifically, we target a streaming setting where the videos to be streamed from a server to a client are all in the same domain and they have to be compressed to a small size for low-latency transmission. Several popular video streaming services, such as the video game streaming services of GeForce Now and Twitch, fall in this category. While conventional video compression standards such as H.264 are commonly used for this task, we hypothesize that one can leverage the property that the videos are all in the same domain to achieve better video quality. Based on this hypothesis, we propose a novel video compression pipeline. Specifically, we first apply H.264 to compress domain-specific videos. We then train a novel binary autoencoder to encode the leftover domain-specific residual information frame-by-frame into binary representations. These binary representations are then compressed and sent to the client together with the H.264 stream. In our experiments, we show that our pipeline yields consistent gains over standard H.264 compression across several benchmark datasets while using the same channel bandwidth.

* Accepted in AAAI'18. Project website at https://research.nvidia.com/publication/2018-02_Learning-Binary-Residual 

  Click for Model/Code and Paper
Image Formation Model Guided Deep Image Super-Resolution

Aug 25, 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. The proposed algorithm first uses a deep neural network to estimate intermediate high-resolution images, blurs the intermediate images using known blur kernels, and then substitutes values of the pixels at the un-decimated positions with those of the corresponding pixels from the low-resolution images. The output of the pixel substitution process strictly satisfies the image formation model and is further refined by the same deep neural network in a cascaded manner. The proposed framework is trained in an end-to-end fashion and can work with existing feed-forward deep neural networks for super-resolution and converges fast in practice. Extensive experimental results show that the proposed algorithm performs favorably against state-of-the-art methods.

* We need to improve this paper 

  Click for Model/Code and Paper
EGNet:Edge Guidance Network for Salient Object Detection

Aug 22, 2019
Jia-Xing Zhao, Jiangjiang Liu, Den-Ping Fan, Yang Cao, Jufeng Yang, Ming-Ming Cheng

Fully convolutional neural networks (FCNs) have shown their advantages in the salient object detection task. However, most existing FCNs-based methods still suffer from coarse object boundaries. In this paper, to solve this problem, we focus on the complementarity between salient edge information and salient object information. Accordingly, we present an edge guidance network (EGNet) for salient object detection with three steps to simultaneously model these two kinds of complementary information in a single network. In the first step, we extract the salient object features by a progressive fusion way. In the second step, we integrate the local edge information and global location information to obtain the salient edge features. Finally, to sufficiently leverage these complementary features, we couple the same salient edge features with salient object features at various resolutions. Benefiting from the rich edge information and location information in salient edge features, the fused features can help locate salient objects, especially their boundaries more accurately. Experimental results demonstrate that the proposed method performs favorably against the state-of-the-art methods on six widely used datasets without any pre-processing and post-processing. The source code is available at http: //mmcheng.net/egnet/.


  Click for Model/Code and Paper
Salient Object Detection via High-to-Low Hierarchical Context Aggregation

Dec 28, 2018
Yun Liu, Yu Qiu, Le Zhang, JiaWang Bian, Guang-Yu Nie, Ming-Ming Cheng

Recent progress on salient object detection mainly aims at exploiting how to effectively integrate convolutional side-output features in convolutional neural networks (CNN). Based on this, most of the existing state-of-the-art saliency detectors design complex network structures to fuse the side-output features of the backbone feature extraction networks. However, should the fusion strategies be more and more complex for accurate salient object detection? 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. As we know, the contexts of an image usually refer to the global structures, and the top layers of CNN usually learn to convey global information. On the other hand, it is difficult for the intermediate side-output features to express contextual information. Here, we design an hourglass network with intermediate supervision to learn contextual features in a high-to-low manner. The learned hierarchical contexts are aggregated to generate the hybrid contextual expression for an input image. At last, the hybrid contextual features can be used for accurate saliency estimation. We extensively evaluate our method on six challenging saliency datasets, and our simple method achieves state-of-the-art performance under various evaluation metrics. Code will be released upon paper acceptance.


  Click for Model/Code and Paper
Semantic Edge Detection with Diverse Deep Supervision

Apr 09, 2018
Yun Liu, Ming-Ming Cheng, JiaWang Bian, Le Zhang, Peng-Tao Jiang, Yang Cao

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. SED naturally requires achieving two distinct supervision targets: locating fine detailed edges and identifying high-level semantics. We shed light on how such distracted supervision targets prevent state-of-the-art SED methods from effectively using deep supervision to improve results. In this paper, we propose a novel fully convolutional neural network architecture using diverse deep supervision (DDS) within a multi-task framework where lower layers aim at generating category-agnostic edges, while higher layers are responsible for the detection of category-aware semantic edges. To overcome the distracted supervision challenge, a novel information converter unit is introduced, whose effectiveness has been extensively evaluated in several popular benchmark datasets, including SBD, Cityscapes, and PASCAL VOC2012. Source code will be released upon paper acceptance.


  Click for Model/Code and Paper
AdaSample: Adaptive Sampling of Hard Positives for Descriptor Learning

Nov 27, 2019
Xin-Yu Zhang, Le Zhang, Zao-Yi Zheng, Yun Liu, Jia-Wang Bian, Ming-Ming Cheng

Triplet loss has been widely employed in a wide range of computer vision tasks, including local descriptor learning. 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. For high-informativeness triplet collection, researchers mostly focus on mining hard negatives in the second stage, while paying relatively less attention to constructing informative batches. To alleviate this issue, we propose AdaSample, an adaptive online batch sampler, in this paper. Specifically, hard positives are sampled based on their informativeness. In this way, we formulate a hardness-aware positive mining pipeline within a novel maximum loss minimization training protocol. The efficacy of the proposed method is evaluated on several standard benchmarks, where it demonstrates a significant and consistent performance gain on top of the existing strong baselines.


  Click for Model/Code and Paper
DNA: Deeply-supervised Nonlinear Aggregation for Salient Object Detection

Mar 28, 2019
Yun Liu, Deng-Ping Fan, Guang-Yu Nie, Xinyu Zhang, Vahan Petrosyan, Ming-Ming Cheng

Recent progress on salient object detection mainly aims at exploiting how to effectively integrate multi-scale convolutional features in convolutional neural networks (CNNs). Many state-of-the-art methods impose deep supervision to perform side-output predictions that are linearly aggregated for final saliency prediction. In this paper, we theoretically and experimentally demonstrate that linear aggregation of side-output predictions is suboptimal, and it only makes limited use of the side-output information obtained by deep supervision. To solve this problem, we propose Deeply-supervised Nonlinear Aggregation (DNA) for better leveraging the complementary information of various side-outputs. Compared with existing methods, it i) aggregates side-output features rather than predictions, and ii) adopts nonlinear instead of linear transformations. Experiments demonstrate that DNA can successfully break through the bottleneck of current linear approaches. Specifically, the proposed saliency detector, a modified U-Net architecture with DNA, performs favorably against state-of-the-art methods on various datasets and evaluation metrics without bells and whistles. Code and data will be released upon paper acceptance.

* arXiv admin note: text overlap with arXiv:1812.10956" 

  Click for Model/Code and Paper
CubemapSLAM: A Piecewise-Pinhole Monocular Fisheye SLAM System

Feb 27, 2019
Yahui Wang, Shaojun Cai, Shi-Jie Li, Yun Liu, Yangyan Guo, Tao Li, Ming-Ming Cheng

We present a real-time feature-based SLAM (Simultaneous Localization and Mapping) system for fisheye cameras featured by a large field-of-view (FoV). Large FoV cameras are beneficial for large-scale outdoor SLAM applications, because they increase visual overlap between consecutive frames and capture more pixels belonging to the static parts of the environment. However, current feature-based SLAM systems such as PTAM and ORB-SLAM limit their camera model to pinhole only. To compensate for the vacancy, we propose a novel SLAM system with the cubemap model that utilizes the full FoV without introducing distortion from the fisheye lens, which greatly benefits the feature matching pipeline. In the initialization and point triangulation stages, we adopt a unified vector-based representation to efficiently handle matches across multiple faces, and based on this representation we propose and analyze a novel inlier checking metric. In the optimization stage, we design and test a novel multi-pinhole reprojection error metric that outperforms other metrics by a large margin. We evaluate our system comprehensively on a public dataset as well as a self-collected dataset that contains real-world challenging sequences. The results suggest that our system is more robust and accurate than other feature-based fisheye SLAM approaches. The CubemapSLAM system has been released into the public domain.

* The paper has been accepted by ACCV 2018 

  Click for Model/Code and Paper