CVPR 2018 论文列表

In this work, we address the problem of improving robustness of convolutional neural networks (CNNs) to image distortion. We argue that higher moment statistics of feature distributions can be shifted due to image distortion, and the shift leads to performance decrease and cannot be reduced by ordinary normalization methods as observed in our experimental analyses. In order to mitigate this effect, we propose an approach base on feature quantization. To be specific, we propose to employ three different types of additional non-linearity in CNNs: i) a floor function with scalable resolution, ii) a power function with learnable exponents, and iii) a power function with data-dependent exponents. In the experiments, we observe that CNNs which employ the proposed methods obtain better performance in both generalization performance and robustness for various distortion types for large scale benchmark datasets. For instance, a ResNet-50 model equipped with the proposed method (+HPOW) obtains 6.95%, 5.26% and 5.61% better accuracy on the ILSVRC-12 classification tasks using images distorted with motion blur, salt and pepper and mixed distortions.

We propose a simple and efficient method for exploiting synthetic images when training a Deep Network to predict a 3D pose from an image. The ability of using synthetic images for training a Deep Network is extremely valuable as it is easy to create a virtually infinite training set made of such images, while capturing and annotating real images can be very cumbersome. However, synthetic images do not resemble real images exactly, and using them for training can result in suboptimal performance. It was recently shown that for exemplar-based approaches, it is possible to learn a mapping from the exemplar representations of real images to the exemplar representations of synthetic images. In this paper, we show that this approach is more general, and that a network can also be applied after the mapping to infer a 3D pose: At run-time, given a real image of the target object, we first compute the features for the image, map them to the feature space of synthetic images, and finally use the resulting features as input to another network which predicts the 3D pose. Since this network can be trained very effectively by using synthetic images, it performs very well in practice, and inference is faster and more accurate than with an exemplar-based approach. We demonstrate our approach on the LINEMOD dataset for 3D object pose estimation from color images, and the NYU dataset for 3D hand pose estimation from depth maps. We show that it allows us to outperform the state-of-the-art on both datasets.

Suffering from the extreme training data imbalance between seen and unseen classes, most of existing state-of-the-art approaches fail to achieve satisfactory results for the challenging generalized zero-shot learning task. To circumvent the need for labeled examples of unseen classes, we propose a novel generative adversarial network(GAN) that synthesizes CNN features conditioned on class-level semantic information, offering a shortcut directly from a semantic descriptor of a class to a class-conditional feature distribution. Our proposed approach, pairing a Wasserstein GAN with a classification loss, is able to generate sufficiently discriminative CNN features to train softmax classifiers or any multimodal embedding method. Our experimental results demonstrate a significant boost in accuracy over the state of the art on five challenging datasets -- CUB, FLO, SUN, AWA and ImageNet -- in both the zero-shot learning and generalized zero-shot learning settings.

Convolutional neural networks (CNNs) have massively impacted visual recognition in 2D images, and are now ubiquitous in state-of-the-art approaches. CNNs do not easily extend, however, to data that are not represented by regular grids, such as 3D shape meshes or other graph-structured data, to which traditional local convolution operators do not directly apply. To address this problem, we propose a novel graph-convolution operator to establish correspondences between filter weights and graph neighborhoods with arbitrary connectivity. The key novelty of our approach is that these correspondences are dynamically computed from features learned by the network, rather than relying on predefined static coordinates over the graph as in previous work. We obtain excellent experimental results that significantly improve over previous state-of-the-art shape correspondence results. This shows that our approach can learn effective shape representations from raw input coordinates, without relying on shape descriptors.

M-estimator using iteratively reweighted least squares (IRLS) is one of the best-known methods for robust estimation. However, IRLS is ineffective for robust unit-norm constrained linear fitting (UCLF) problems, such as fundamental matrix estimation because of a poor initial solution. We overcome this problem by developing a novel objective function and its optimization, named iteratively reweighted eigenvalues minimization (IREM). IREM is guaranteed to decrease the objective function and achieves fast convergence and high robustness. In robust fundamental matrix estimation, IREM performs approximately 5-500 times faster than random sampling consensus (RANSAC) while preserving comparable or superior robustness.

In this paper we propose a novel deep neural network that is able to jointly reason about 3D detection, tracking and motion forecasting given data captured by a 3D sensor. By jointly reasoning about these tasks, our holistic approach is more robust to occlusion as well as sparse data at range. Our approach performs 3D convolutions across space and time over a bird's eye view representation of the 3D world, which is very efficient in terms of both memory and computation. Our experiments on a new very large scale dataset captured in several north american cities, show that we can outperform the state-of-the-art by a large margin. Importantly, by sharing computation we can perform all tasks in as little as 30 ms.

Recently, deep convolutional neural networks (CNNs) have been demonstrated remarkable progress on single image super-resolution. However, as the depth and width of the networks increase, CNN-based super-resolution methods have been faced with the challenges of computational complexity and memory consumption in practice. In order to solve the above questions, we propose a deep but compact convolutional network to directly reconstruct the high resolution image from the original low resolution image. In general, the proposed model consists of three parts, which are feature extraction block, stacked information distillation blocks and reconstruction block respectively. By combining an enhancement unit with a compression unit into a distillation block, the local long and short-path features can be effectively extracted. Specifically, the proposed enhancement unit mixes together two different types of features and the compression unit distills more useful information for the sequential blocks. In addition, the proposed network has the advantage of fast execution due to the comparatively few number of filters per layer and the use of group convolution. Experimental results demonstrate that the proposed method is superior to the state-of-the-art methods, especially in terms of time performance.

Online video object segmentation is a challenging task as it entails to process the image sequence timely and accurately. To segment a target object through the video, numerous CNN-based methods have been developed by heavily finetuning on the object mask in the first frame, which is time-consuming for online applications. In this paper, we propose a fast and accurate video object segmentation algorithm that can immediately start the segmentation process once receiving the images. We first utilize a part-based tracking method to deal with challenging factors such as large deformation, occlusion, and cluttered background. Based on the tracked bounding boxes of parts, we construct a region-of-interest segmentation network to generate part masks. Finally, a similarity-based scoring function is adopted to refine these object parts by comparing them to the visual information in the first frame. Our method performs favorably against state-of-the-art algorithms in accuracy on the DAVIS benchmark dataset, while achieving much faster runtime performance.

We present an efficient method for the semi-supervised video object segmentation. Our method achieves accuracy competitive with state-of-the-art methods while running in a fraction of time compared to others. To this end, we propose a deep Siamese encoder-decoder network that is designed to take advantage of mask propagation and object detection while avoiding the weaknesses of both approaches. Our network, learned through a two-stage training process that exploits both synthetic and real data, works robustly without any online learning or post-processing. We validate our method on four benchmark sets that cover single and multiple object segmentation. On all the benchmark sets, our method shows comparable accuracy while having the order of magnitude faster runtime. We also provide extensive ablation and add-on studies to analyze and evaluate our framework.

Despite the success of deep learning on representing images for particular object retrieval, recent studies show that the learned representations still lie on manifolds in a high dimensional space. This makes the Euclidean nearest neighbor search biased for this task. Exploring the manifolds online remains expensive even if a nearest neighbor graph has been computed offline. This work introduces an explicit embedding reducing manifold search to Euclidean search followed by dot product similarity search. This is equivalent to linear graph filtering of a sparse signal in the frequency domain. To speed up online search, we compute an approximate Fourier basis of the graph offline. We improve the state of art on particular object retrieval datasets including the challenging Instre dataset containing small objects. At a scale of 10^5 images, the offline cost is only a few hours, while query time is comparable to standard similarity search.

Size, weight, and power constrained platforms impose constraints on computational resources that introduce unique challenges in implementing localization algorithms. We present a framework to perform fast localization on such platforms enabled by the compressive capabilities of Gaussian Mixture Model representations of point cloud data. Given raw structural data from a depth sensor and pitch and roll estimates from an on-board attitude reference system, a multi-hypothesis particle filter localizes the vehicle by exploiting the likelihood of the data originating from the mixture model. We demonstrate analysis of this likelihood in the vicinity of the ground truth pose and detail its utilization in a particle filter-based vehicle localization strategy, and later present results of real-time implementations on a desktop system and an off-the-shelf embedded platform that outperform localization results from running a state-of-the-art algorithm on the same environment.

Image processing and pixel-wise dense prediction have been advanced by harnessing the capabilities of deep learning. One central issue of deep learning is the limited capacity to handle joint upsampling. We present a deep learning building block for joint upsampling, namely guided filtering layer. This layer aims at efficiently generating the high-resolution output given the corresponding low-resolution one and a high-resolution guidance map. The proposed layer is composed of a guided filter, which is reformulated as a fully differentiable block. To this end, we show that a guided filter can be expressed as a group of spatial varying linear transformation matrices. This layer could be integrated with the convolutional neural networks (CNNs) and jointly optimized through end-to-end training. To further take advantage of end-to-end training, we plug in a trainable transformation function that generates task-specific guidance maps. By integrating the CNNs and the proposed layer, we form deep guided filtering networks. The proposed networks are evaluated on five advanced image processing tasks. Experiments on MIT-Adobe FiveK Dataset demonstrate that the proposed approach runs 10-100 times faster and achieves the state-of-the-art performance. We also show that the proposed guided filtering layer helps to improve the performance of multiple pixel-wise dense prediction tasks.

The goal of this paper is to take a single 2D image of a scene and recover the 3D structure in terms of a small set of factors: a layout representing the enclosing surfaces as well as a set of objects represented in terms of shape and pose. We propose a convolutional neural network-based approach to predict this representation and benchmark it on a large dataset of indoor scenes. Our experiments evaluate a number of practical design questions, demonstrate that we can infer this representation, and quantitatively and qualitatively demonstrate its merits compared to alternate representations.

A facial expression is a combination of an expressive component and a neutral component of a person. In this paper, we propose to recognize facial expressions by extracting information of the expressive component through a de-expression learning procedure, called De-expression Residue Learning (DeRL). First, a generative model is trained by cGAN. This model generates the corresponding neutral face image for any input face image. We call this procedure de-expression because the expressive information is filtered out by the generative model; however, the expressive information is still recorded in the intermediate layers. Given the neutral face image, unlike previous works using pixel-level or feature-level difference for facial expression classification, our new method learns the deposition (or residue) that remains in the intermediate layers of the generative model. Such a residue is essential as it contains the expressive component deposited in the generative model from any input facial expression images. Seven public facial expression databases are employed in our experiments. With two databases (BU-4DFE and BP4D-spontaneous) for pre-training, the DeRL method has been evaluated on five databases, CK+, Oulu-CASIA, MMI, BU- 3DFE, and BP4D+. The experimental results demonstrate the superior performance of the proposed method.

Digital face manipulation has become a popular and fascinating way to touch images with the prevalence of smart phones and social networks. With a wide variety of user preferences, facial expressions, and accessories, a general and flexible model is necessary to accommodate different types of facial editing. In this paper, we propose a model to achieve this goal based on an end-to-end convolutional neural network that supports fast inference, edit-effect control, and quick partial-model update. In addition, this model learns from unpaired image sets with different attributes. Experimental results show that our framework can handle a wide range of expressions, accessories, and makeup effects. It produces high-resolution and high-quality results in fast speed.

Face synthesis has achieved advanced development by using generative adversarial networks (GANs). Existing methods typically formulate GAN as a two-player game, where a discriminator distinguishes face images from the real and synthesized domains, while a generator reduces its discriminativeness by synthesizing a face of photo-realistic quality. Their competition converges when the discriminator is unable to differentiate these two domains. Unlike two-player GANs, this work generates identity-preserving faces by proposing FaceID-GAN, which treats a classifier of face identity as the third player, competing with the generator by distinguishing the identities of the real and synthesized faces (see Fig.1). A stationary point is reached when the generator produces faces that have high quality as well as preserve identity. Instead of simply modeling the identity classifier as an additional discriminator, FaceID-GAN is formulated by satisfying information symmetry, which ensures that the real and synthesized images are projected into the same feature space. In other words, the identity classifier is used to extract identity features from both input (real) and output (synthesized) face images of the generator, substantially alleviating training difficulty of GAN. Extensive experiments show that FaceID-GAN is able to generate faces of arbitrary viewpoint while preserve identity, outperforming recent advanced approaches.

Face aging is of great importance for cross-age recognition and entertainment related applications. However, the lack of labeled faces of the same person across a long age range makes it challenging. Because of different aging speed of different persons, our face aging approach aims at synthesizing a face whose target age lies in some given age group instead of synthesizing a face with a certain age. By grouping faces with target age together, the objective of face aging is equivalent to transferring aging patterns of faces within the target age group to the face whose aged face is to be synthesized. Meanwhile, the synthesized face should have the same identity with the input face. Thus we propose an Identity-Preserved Conditional Generative Adversarial Networks (IPCGANs) framework, in which a Conditional Generative Adversarial Networks module functions as generating a face that looks realistic and is with the target age, an identity-preserved module preserves the identity information and an age classifier forces the generated face with the target age. Both qualitative and quantitative experiments show that our method can generate more realistic faces in terms of image quality, person identity and age consistency with human observations.

Face Super-Resolution (SR) is a domain-specific superresolution problem. The facial prior knowledge can be leveraged to better super-resolve face images. We present a novel deep end-to-end trainable Face Super-Resolution Network (FSRNet), which makes use of the geometry prior, i.e., facial landmark heatmaps and parsing maps, to superresolve very low-resolution (LR) face images without wellaligned requirement. Specifically, we first construct a coarse SR network to recover a coarse high-resolution (HR) image. Then, the coarse HR image is sent to two branches: a fine SR encoder and a prior information estimation network, which extracts the image features, and estimates landmark heatmaps/parsing maps respectively. Both image features and prior information are sent to a fine SR decoder to recover the HR image. To generate realistic faces, we also propose the Face Super-Resolution Generative Adversarial Network (FSRGAN) to incorporate the adversarial loss into FSRNet. Further, we introduce two related tasks, face alignment and parsing, as the new evaluation metrics for face SR, which address the inconsistency of classic metrics w.r.t. visual perception. Extensive experiments show that FSRNet and FSRGAN significantly outperforms state of the arts for very LR face SR, both quantitatively and qualitatively.

Incidental scene text spotting is considered one of the most difficult and valuable challenges in the document analysis community. Most existing methods treat text detection and recognition as separate tasks. In this work, we propose a unified end-to-end trainable Fast Oriented Text Spotting (FOTS) network for simultaneous detection and recognition, sharing computation and visual information among the two complementary tasks. Specifically, RoIRotate is introduced to share convolutional features between detection and recognition. Benefiting from convolution sharing strategy, our FOTS has little computation overhead compared to baseline text detection network, and the joint training method makes our method perform better than these two-stage methods. Experiments on ICDAR 2015, ICDAR 2017 MLT, and ICDAR 2013 datasets demonstrate that the proposed method outperforms state-of-the-art methods significantly, which further allows us to develop the first real-time oriented text spotting system which surpasses all previous state-of-the-art results by more than 5% on ICDAR 2015 text spotting task while keeping 22.6 fps.