CVPR 2019 Papers

Meta-learning has been proposed as a framework to address the challenging few-shot learning setting. The key idea is to leverage a large number of similar few-shot tasks in order to learn how to adapt a base-learner to a new task for which only a few labeled samples are available. As deep neural networks (DNNs) tend to overfit using a few samples only, meta-learning typically uses shallow neural networks (SNNs), thus limiting its effectiveness. In this paper we propose a novel few-shot learning method called meta-transfer learning (MTL) which learns to adapt a deep NN for few shot learning tasks. Specifically, "meta" refers to training multiple tasks, and "transfer" is achieved by learning scaling and shifting functions of DNN weights for each task. In addition, we introduce the hard task (HT) meta-batch scheme as an effective learning curriculum for MTL. We conduct experiments using (5-class, 1-shot) and (5-class, 5-shot) recognition tasks on two challenging few-shot learning benchmarks: miniImageNet and Fewshot-CIFAR100. Extensive comparisons to related works validate that our meta-transfer learning approach trained with the proposed HT meta-batch scheme achieves top performance. An ablation study also shows that both components contribute to fast convergence and high accuracy.

Recent research on super-resolution has achieved greatsuccess due to the development of deep convolutional neu-ral networks (DCNNs). However, super-resolution of arbi-trary scale factor has been ignored for a long time. Mostprevious researchers regard super-resolution of differentscale factors as independent tasks. They train a specificmodel for each scale factor which is inefficient in comput-ing, and prior work only take the super-resolution of sev-eral integer scale factors into consideration. In this work,we propose a novel method called Meta-SR to firstly solvesuper-resolution of arbitrary scale factor (including non-integer scale factors) with a single model. In our Meta-SR,the Meta-Upscale Module is proposed to replace the tradi-tional upscale module. For arbitrary scale factor, the Meta-Upscale Module dynamically predicts the weights of the up-scale filters by taking the scale factor as input and use theseweights to generate the HR image of arbitrary size. For anylow-resolution image, our Meta-SR can continuously zoomin it with arbitrary scale factor by only using a single model.We evaluated the proposed method through extensive exper-iments on widely used benchmark datasets on single imagesuper-resolution. The experimental results show the superi-ority of our Meta-Upscale.

Recognition of defects in concrete infrastructure, especially in bridges, is a costly and time consuming crucial first step in the assessment of the structural integrity. Large variation in appearance of the concrete material, changing illumination and weather conditions, a variety of possible surface markings as well as the possibility for different types of defects to overlap, make it a challenging real-world task. In this work we introduce the novel COncrete DEfect BRidge IMage dataset (CODEBRIM) for multi-target classification of five commonly appearing concrete defects. We investigate and compare two reinforcement learning based meta-learning approaches, MetaQNN and efficient neural architecture search, to find suitable convolutional neural network architectures for this challenging multi-class multi-target task. We show that learned architectures have fewer overall parameters in addition to yielding better multi-target accuracy in comparison to popular neural architectures from the literature evaluated in the context of our application.

Typical techniques for video captioning follow the encoder-decoder framework, which can only focus on one source video being processed. A potential disadvantage of such design is that it cannot capture the multiple visual context information of a word appearing in more than one relevant videos in training data. To tackle this limitation, we propose the Memory-Attended Recurrent Network (MARN) for video captioning, in which a memory structure is designed to explore the full-spectrum correspondence between a word and its various similar visual contexts across videos in training data. Thus, our model is able to achieve a more comprehensive understanding for each word and yield higher captioning quality. Furthermore, the built memory structure enables our method to model the compatibility between adjacent words explicitly instead of asking the model to learn implicitly, as most existing models do. Extensive validation on two real-word datasets demonstrates that our MARN consistently outperforms state-of-the-art methods.

Natural spatiotemporal processes can be highly non-stationary in many ways, e.g. the low-level non-stationarity such as spatial correlations or temporal dependencies of local pixel values; and the high-level variations such as the accumulation, deformation or dissipation of radar echoes in precipitation forecasting. From Cramer's Decomposition, any non-stationary process can be decomposed into deterministic, time-variant polynomials, plus a zero-mean stochastic term. By applying differencing operations appropriately, we may turn time-variant polynomials into a constant, making the deterministic component predictable. However, most previous recurrent neural networks for spatiotemporal prediction do not use the differential signals effectively, and their relatively simple state transition functions prevent them from learning too complicated variations in spacetime. We propose the Memory In Memory (MIM) networks and corresponding recurrent blocks for this purpose. The MIM blocks exploit the differential signals between adjacent recurrent states to model the non-stationary and approximately stationary properties in spatiotemporal dynamics with two cascaded, self-renewed memory modules. By stacking multiple MIM blocks, we could potentially handle higher-order non-stationarity. The MIM networks achieve the state-of-the-art results on four spatiotemporal prediction tasks across both synthetic and real-world datasets. We believe that the general idea of this work can be potentially applied to other time-series forecasting tasks.

Modern convolutional object detectors have improved the detection accuracy significantly, which in turn inspired the development of dedicated hardware accelerators to achieve real-time performance by exploiting inherent parallelism in the algorithm. Non-maximum suppression (NMS) is an indispensable operation in object detection. In stark contrast to most operations, the commonly-adopted GreedyNMS algorithm does not foster parallelism, which can be a major performance bottleneck. In this paper, we introduce MaxpoolNMS, a parallelizable alternative to the NMS algorithm, which is based on max-pooling classification score maps. By employing a novel multi-scale multi-channel max-pooling strategy, our method is 20x faster than GreedyNMS while simultaneously achieves comparable accuracy, when quantified across various benchmarking datasets, i.e., MS COCO, KITTI and PASCAL VOC. Furthermore, our method is better suited for hardware-based acceleration than GreedyNMS.

Portrait editing is a popular subject in photo manipulation.The Generative Adversarial Network (GAN) advances the generating of realistic faces and allows more face editing. In this paper, we argue about three issues in existing techniques: diversity, quality, and controllability for portrait synthesis and editing. To address these issues, we propose a novel end-to-end learning framework that leverages conditional GANs guided by provided face masks for generating faces. The framework learns feature embeddings for every face component (e.g., mouth, hair, eye), separately, contributing to better correspondences for image translation, and local face editing. With the mask, our network is available to many applications, like face synthesis driven by mask, face Swap+ (including hair in swapping), and local manipulation. It can also boost the performance of face parsing a bit as an option of data augmentation.

Zero-shot learning has been well explored to precisely identify new unobserved classes through a visual-semantic function obtained from the existing objects. However, there exist two challenging obstacles: one is that the human-annotated semantics are insufficient to fully describe the visual samples; the other is the domain shift across existing and new classes. In this paper, we attempt to exploit the intrinsic relationship in the semantic manifold when given semantics are not enough to describe the visual objects, and enhance the generalization ability of the visual-semantic function with marginalized strategy. Specifically, we design a Marginalized Latent Semantic Encoder (MLSE), which is learned on the augmented seen visual features and the latent semantic representation. Meanwhile, latent semantics are discovered under an adaptive graph reconstruction scheme based on the provided semantics. Consequently, our proposed algorithm could enrich visual characteristics from seen classes, and well generalize to unobserved classes. Experimental results on zero-shot benchmarks demonstrate that the proposed model delivers superior performance over the state-of-the-art zero-shot learning approaches.

Building on progress in feature representations for image retrieval, image-based localization has seen a surge of research interest. Image-based localization has the advantage of being inexpensive and efficient, often avoiding the use of 3D metric maps altogether. That said, the need to maintain a large amount of reference images as an effective support of localization in a scene, nonetheless calls for them to be organized in a map structure of some kind. The problem of localization often arises as part of a navigation process. We are, therefore, interested in summarizing the reference images as a set of landmarks, which meet the requirements for image-based navigation. A contribution of this paper is to formulate such a set of requirements for the two sub-tasks involved: compact map construction and accurate self localization. These requirements are then exploited for compact map representation and accurate self-localization, using the framework of a network flow problem. During this process, we formulate the map construction and self-localization problems as convex quadratic and second-order cone programs, respectively. We evaluate our methods on publicly available indoor and outdoor datasets, where they outperform existing methods significantly.

To fight against real-life image forgery, which commonly involves different types and combined manipulations, we propose a unified deep neural architecture called ManTra-Net. Unlike many existing solutions, ManTra-Net is an end-to-end network that performs both detection and localization without extra preprocessing and postprocessing. \manifold is a fully convolutional network and handles images of arbitrary sizes and many known forgery types such splicing, copy-move, removal, enhancement, and even unknown types. This paper has three salient contributions. We design a simple yet effective self-supervised learning task to learn robust image manipulation traces from classifying 385 image manipulation types. Further, we formulate the forgery localization problem as a local anomaly detection problem, design a Z-score feature to capture local anomaly, and propose a novel long short-term memory solution to assess local anomalies. Finally, we carefully conduct ablation experiments to systematically optimize the proposed network design. Our extensive experimental results demonstrate the generalizability, robustness and superiority of ManTra-Net, not only in single types of manipulations/forgeries, but also in their complicated combinations.

Cloud based medical image analysis has become popular recently due to the high computation complexities of various deep neural network (DNN) based frameworks and the increasingly large volume of medical images that need to be processed. It has been demonstrated that for medical images the transmission from local to clouds is much more expensive than the computation in the clouds itself. Towards this, 3D image compression techniques have been widely applied to reduce the data traffic. However, most of the existing image compression techniques are developed around human vision, i.e., they are designed to minimize distortions that can be perceived by human eyes. In this paper, we will use deep learning based medical image segmentation as a vehicle and demonstrate that interestingly, machine and human view the compression quality differently. Medical images compressed with good quality w.r.t. human vision may result in inferior segmentation accuracy. We then design a machine vision oriented 3D image compression framework tailored for segmentation using DNNs. Our method automatically extracts and retains image features that are most important to the segmentation. Comprehensive experiments on widely adopted segmentation frameworks with HVSMR 2016 challenge dataset show that our method can achieve significantly higher segmentation accuracy at the same compression rate, or much better compression rate under the same segmentation accuracy, when compared with the existing JPEG 2000 method. To the best of the authors' knowledge, this is the first machine vision guided medical image compression framework for segmentation in the clouds.

The detection of anomalous structures in natural image data is of utmost importance for numerous tasks in the field of computer vision. The development of methods for unsupervised anomaly detection requires data on which to train and evaluate new approaches and ideas. We introduce the MVTec Anomaly Detection (MVTec AD) dataset containing 5354 high-resolution color images of different object and texture categories. It contains normal, i.e., defect-free, images intended for training and images with anomalies intended for testing. The anomalies manifest themselves in the form of over 70 different types of defects such as scratches, dents, contaminations, and various structural changes. In addition, we provide pixel-precise ground truth regions for all anomalies. We also conduct a thorough evaluation of current state-of-the-art unsupervised anomaly detection methods based on deep architectures such as convolutional autoencoders, generative adversarial networks, and feature descriptors using pre-trained convolutional neural networks, as well as classical computer vision methods. This initial benchmark indicates that there is considerable room for improvement. To the best of our knowledge, this is the first comprehensive, multi-object, multi-defect dataset for anomaly detection that provides pixel-accurate ground truth regions and focuses on real-world applications.

We address the problem of recovering the 3D geometry of a human face from a set of facial images in multiple views. While recent studies have shown impressive progress in 3D Morphable Model (3DMM) based facial reconstruction, the settings are mostly restricted to a single view. There is an inherent drawback in the single-view setting: the lack of reliable 3D constraints can cause unresolvable ambiguities. We in this paper explore 3DMM-based shape recovery in a different setting, where a set of multi-view facial images are given as input. A novel approach is proposed to regress 3DMM parameters from multi-view inputs with an end-to-end trainable Convolutional Neural Network (CNN). Multi-view geometric constraints are incorporated into the network by establishing dense correspondences between different views leveraging a novel self-supervised view alignment loss. The main ingredient of the view alignment loss is a differentiable dense optical flow estimator that can backpropagate the alignment errors between an input view and a synthetic rendering from another input view, which is projected to the target view through the 3D shape to be inferred. Through minimizing the view alignment loss, better 3D shapes can be recovered such that the synthetic projections from one view to another can better align with the observed image. Extensive experiments demonstrate the superiority of the proposed method over other 3DMM methods.

Multimodal attentional networks are currently state-of-the-art models for Visual Question Answering (VQA) tasks involving real images. Although attention allows to focus on the visual content relevant to the question, this simple mechanism is arguably insufficient to model complex reasoning features required for VQA or other high-level tasks. In this paper, we propose MuRel, a multimodal relational network which is learned end-to-end to reason over real images. Our first contribution is the introduction of the MuRel cell, an atomic reasoning primitive representing interactions between question and image regions by a rich vectorial representation, and modeling region relations with pairwise combinations. Secondly, we incorporate the cell into a full MuRel network, which progressively refines visual and question interactions, and can be leveraged to define visualization schemes finer than mere attention maps. We validate the relevance of our approach with various ablation studies, and show its superiority to attention-based methods on three datasets: VQA 2.0, VQA-CP v2 and TDIUC. Our final MuRel network is competitive to or outperforms state-of-the-art results in this challenging context. Our code is available: github.com/Cadene/murel.bootstrap.pytorch

In this paper, we propose an adversarial learning network for the task of multi-style image captioning (MSCap) with a standard factual image caption dataset and a multi-stylized language corpus without paired images. How to learn a single model for multi-stylized image captioning with unpaired data is a challenging and necessary task, whereas rarely studied in previous works. The proposed framework mainly includes four contributive modules following a typical image encoder. First, a style dependent caption generator to output a sentence conditioned on an encoded image and a specified style. Second, a caption discriminator is presented to distinguish the input sentence to be real or not. The discriminator and the generator are trained in an adversarial manner to enable more natural and human-like captions. Third, a style classifier is employed to discriminate the specific style of the input sentence. Besides, a back-translation module is designed to enforce the generated stylized captions are visually grounded, with the intuition of the cycle consistency for factual caption and stylized caption. We enable an end-to-end optimization of the whole model with differentiable softmax approximation. At last, we conduct comprehensive experiments using a combined dataset containing four caption styles to demonstrate the outstanding performance of our proposed method.

Temporally locating and classifying action segments in long untrimmed videos is of particular interest to many applications like surveillance and robotics. While traditional approaches follow a two-step pipeline, by generating frame-wise probabilities and then feeding them to high-level temporal models, recent approaches use temporal convolutions to directly classify the video frames. In this paper, we introduce a multi-stage architecture for the temporal action segmentation task. Each stage features a set of dilated temporal convolutions to generate an initial prediction that is refined by the next one. This architecture is trained using a combination of a classification loss and a proposed smoothing loss that penalizes over-segmentation errors. Extensive evaluation shows the effectiveness of the proposed model in capturing long-range dependencies and recognizing action segments. Our model achieves state-of-the-art results on three challenging datasets: 50Salads, Georgia Tech Egocentric Activities (GTEA), and the Breakfast dataset.

This paper extends the popular task of multi-object tracking to multi-object tracking and segmentation (MOTS). Towards this goal, we create dense pixel-level annotations for two existing tracking datasets using a semi-automatic annotation procedure. Our new annotations comprise 65,213 pixel masks for 977 distinct objects (cars and pedestrians) in 10,870 video frames. For evaluation, we extend existing multi-object tracking metrics to this new task. Moreover, we propose a new baseline method which jointly addresses detection, tracking, and segmentation with a single convolutional network. We demonstrate the value of our datasets by achieving improvements in performance when training on MOTS annotations. We believe that our datasets, metrics and baseline will become a valuable resource towards developing multi-object tracking approaches that go beyond 2D bounding boxes. We make our annotations, code, and models available at https://www.vision.rwth-aachen.de/page/mots.

We propose to address the face reconstruction in the wild by using a multi-metric regression network, MMFace, to align a 3D face morphable model (3DMM) to an input image. The key idea is to utilize a volumetric sub-network to estimate an intermediate geometry representation, and a parametric sub-network to regress the 3DMM parameters. Our parametric sub-network consists of identity loss, expression loss, and pose loss which greatly improves the aligned geometry details by incorporating high level loss functions directly defined in the 3DMM parametric spaces. Our high-quality reconstruction is robust under large variations of expressions, poses, illumination conditions, and even with large partial occlusions. We evaluate our method by comparing the performance with state-of-the-art approaches on latest 3D face dataset LS3D-W and Florence. We achieve significant improvements both quantitatively and qualitatively. Due to our high-quality reconstruction, our method can be easily extended to generate high-quality geometry sequences for video inputs.

We tackle the problem of finding good architectures for multimodal classification problems. We propose a novel and generic search space that spans a large number of possible fusion architectures. In order to find an optimal architecture for a given dataset in the proposed search space, we leverage an efficient sequential model-based exploration approach that is tailored for the problem. We demonstrate the value of posing multimodal fusion as a neural architecture search problem by extensive experimentation on a toy dataset and two other real multimodal datasets. We discover fusion architectures that exhibit state-of-the-art performance for problems with different domain and dataset size, including the \ntu dataset, the largest multimodal action recognition dataset available.