CVPR 2019 论文列表

Recent success of semantic segmentation approaches on demanding road driving datasets has spurred interest in many related application fields. Many of these applications involve real-time prediction on mobile platforms such as cars, drones and various kinds of robots. Real-time setup is challenging due to extraordinary computational complexity involved. Many previous works address the challenge with custom lightweight architectures which decrease computational complexity by reducing depth, width and layer capacity with respect to general purpose architectures. We propose an alternative approach which achieves a significantly better performance across a wide range of computing budgets. First, we rely on a light-weight general purpose architecture as the main recognition engine. Then, we leverage light-weight upsampling with lateral connections as the most cost-effective solution to restore the prediction resolution. Finally, we propose to enlarge the receptive field by fusing shared features at multiple resolutions in a novel fashion. Experiments on several road driving datasets show a substantial advantage of the proposed approach, either with ImageNet pre-trained parameters or when we learn from scratch. Our Cityscapes test submission entitled SwiftNetRN-18 delivers 75.5% MIoU and achieves 39.9 Hz on 1024x2048 images on GTX1080Ti.

We present an efficient approach for leveraging the knowledge from multiple modalities in training unimodal 3D convolutional neural networks (3D-CNNs) for the task of dynamic hand gesture recognition. Instead of explicitly combining multimodal information, which is commonplace in many state-of-the-art methods, we propose a different framework in which we embed the knowledge of multiple modalities in individual networks so that each unimodal network can achieve an improved performance. In particular, we dedicate separate networks per available modality and enforce them to collaborate and learn to develop networks with common semantics and better representations. We introduce a "spatiotemporal semantic alignment" loss (SSA) to align the content of the features from different networks. In addition, we regularize this loss with our proposed "focal regularization parameter" to avoid negative knowledge transfer. Experimental results show that our framework improves the test time recognition accuracy of unimodal networks, and provides the state-of-the-art performance on various dynamic hand gesture recognition datasets.

Though CNNs have achieved the state-of-the-art performance on various vision tasks, they are vulnerable to adversarial examples --- crafted by adding human-imperceptible perturbations to clean images. However, most of the existing adversarial attacks only achieve relatively low success rates under the challenging black-box setting, where the attackers have no knowledge of the model structure and parameters. To this end, we propose to improve the transferability of adversarial examples by creating diverse input patterns. Instead of only using the original images to generate adversarial examples, our method applies random transformations to the input images at each iteration. Extensive experiments on ImageNet show that the proposed attack method can generate adversarial examples that transfer much better to different networks than existing baselines. By evaluating our method against top defense solutions and official baselines from NIPS 2017 adversarial competition, the enhanced attack reaches an average success rate of 73.0%, which outperforms the top-1 attack submission in the NIPS competition by a large margin of 6.6%. We hope that our proposed attack strategy can serve as a strong benchmark baseline for evaluating the robustness of networks to adversaries and the effectiveness of different defense methods in the future. Code is available at https://github.com/cihangxie/DI-2-FGSM.

Referring expression grounding aims at locating certain objects or persons in an image with a referring expression, where the key challenge is to comprehend and align various types of information from visual and textual domain, such as visual attributes, location and interactions with surrounding regions. Although the attention mechanism has been successfully applied for cross-modal alignments, previous attention models focus on only the most dominant features of both modalities, and neglect the fact that there could be multiple comprehensive textual-visual correspondences between images and referring expressions. To tackle this issue, we design a novel cross-modal attention-guided erasing approach, where we discard the most dominant information from either textual or visual domains to generate difficult training samples online, and to drive the model to discover complementary textual-visual correspondences. Extensive experiments demonstrate the effectiveness of our proposed method, which achieves state-of-the-art performance on three referring expression grounding datasets.

As an indicator of human attention gaze is a subtle behavioral cue which can be exploited in many applications. However, inferring 3D gaze direction is challenging even for deep neural networks given the lack of large amount of data (groundtruthing gaze is expensive and existing datasets use different setups) and the inherent presence of gaze biases due to person-specific difference. In this work, we address the problem of person-specific gaze model adaptation from only a few reference training samples. The main and novel idea is to improve gaze adaptation by generating additional training samples through the synthesis of gaze-redirected eye images from existing reference samples. In doing so, our contributions are threefold:(i) we design our gaze redirection framework from synthetic data, allowing us to benefit from aligned training sample pairs to predict accurate inverse mapping fields; (ii) we proposed a self-supervised approach for domain adaptation; (iii) we exploit the gaze redirection to improve the performance of person-specific gaze estimation. Extensive experiments on two public datasets demonstrate the validity of our gaze retargeting and gaze estimation framework.

Spatio-temporal action localization consists of three levels of tasks: spatial localization, action classification, and temporal segmentation. In this work, we propose a new Progressive Cross-stream Cooperation (PCSC) framework to iterative improve action localization results and generate better bounding boxes for one stream (i.e., Flow/RGB) by leveraging both region proposals and features from another stream (i.e., RGB/Flow) in an iterative fashion. Specifically, we first generate a larger set of region proposals by combining the latest region proposals from both streams, from which we can readily obtain a larger set of labelled training samples to help learn better action detection models. Second, we also propose a new message passing approach to pass information from one stream to another stream in order to learn better representations, which also leads to better action detection models. As a result, our iterative framework progressively improves action localization results at the frame level. To improve action localization results at the video level, we additionally propose a new strategy to train class-specific actionness detectors for better temporal segmentation, which can be readily learnt by using the training samples around temporal boundaries. Comprehensive experiments on two benchmark datasets UCF-101-24 and J-HMDB demonstrate the effectiveness of our newly proposed approaches for spatio-temporal action localization in realistic scenarios.

Road network extraction from satellite images often produce fragmented road segments leading to road maps unfit for real applications. Pixel-wise classification fails to predict topologically correct and connected road masks due to the absence of connectivity supervision and difficulty in enforcing topological constraints. In this paper, we propose a connectivity task called Orientation Learning, motivated by the human behavior of annotating roads by tracing it at a specific orientation. We also develop a stacked multi-branch convolutional module to effectively utilize the mutual information between orientation learning and segmentation tasks. These contributions ensure that the model predicts topologically correct and connected road masks. We also propose Connectivity Refinement approach to further enhance the estimated road networks. The refinement model is pre-trained to connect and refine the corrupted ground-truth masks and later fine-tuned to enhance the predicted road masks. We demonstrate the advantages of our approach on two diverse road extraction datasets SpaceNet and DeepGlobe. Our approach improves over the state-of-the-art techniques by 9% and 7.5% in road topology metric on SpaceNet and DeepGlobe, respectively.

Structural pruning of neural network parameters reduces computational, energy, and memory transfer costs during inference. We propose a novel method that estimates the contribution of a neuron (filter) to the final loss and iteratively removes those with smaller scores. We describe two variations of our method using the first and second-order Taylor expansions to approximate a filter's contribution. Both methods scale consistently across any network layer without requiring per-layer sensitivity analysis and can be applied to any kind of layer, including skip connections. For modern networks trained on ImageNet, we measured experimentally a high (>93%) correlation between the contribution computed by our methods and a reliable estimate of the true importance. Pruning with the proposed methods led to an improvement over state-of-the-art in terms of accuracy, FLOPs, and parameter reduction. On ResNet-101, we achieve a 40% FLOPS reduction by removing 30% of the parameters, with a loss of 0.02% in the top-1 accuracy on ImageNet.

The image, question (combined with the history for de-referencing), and the corresponding answer are three vital components of visual dialog. Classical visual dialog systems integrate the image, question, and history to search for or generate the best matched answer, and so, this approach significantly ignores the role of the answer. In this paper, we devise a novel image-question-answer synergistic network to value the role of the answer for precise visual dialog. We extend the traditional one-stage solution to a two-stage solution. In the first stage, candidate answers are coarsely scored according to their relevance to the image and question pair. Afterward, in the second stage, answers with high probability of being correct are re-ranked by synergizing with image and question. On the Visual Dialog v1.0 dataset, the proposed synergistic network boosts the discriminative visual dialog model to achieve a new state-of-the-art of 57.88% normalized discounted cumulative gain. A generative visual dialog model equipped with the proposed technique also shows promising improvements.

Due to the significant information loss in low-resolution (LR) images, it has become extremely challenging to further advance the state-of-the-art of single image super-resolution (SISR). Reference-based super-resolution (RefSR), on the other hand, has proven to be promising in recovering high-resolution (HR) details when a reference (Ref) image with similar content as that of the LR input is given. However, the quality of RefSR can degrade severely when Ref is less similar. This paper aims to unleash the potential of RefSR by leveraging more texture details from Ref images with stronger robustness even when irrelevant Ref images are provided. Inspired by the recent work on image stylization, we formulate the RefSR problem as neural texture transfer. We design an end-to-end deep model which enriches HR details by adaptively transferring the texture from Ref images according to their textural similarity. Instead of matching content in the raw pixel space as done by previous methods, our key contribution is a multi-level matching conducted in the neural space. This matching scheme facilitates multi-scale neural transfer that allows the model to benefit more from those semantically related Ref patches, and gracefully degrade to SISR performance on the least relevant Ref inputs. We build a benchmark dataset for the general research of RefSR, which contains Ref images paired with LR inputs with varying levels of similarity. Both quantitative and qualitative evaluations demonstrate the superiority of our method over state-of-the-art.

We propose a high-quality photo-to-pencil translation method with fine-grained control over the drawing style. This is a challenging task due to multiple stroke types (e.g., outline and shading), structural complexity of pencil shading (e.g., hatching), and the lack of aligned training data pairs. To address these challenges, we develop a two-branch model that learns separate filters for generating sketchy outlines and tonal shading from a collection of pencil drawings. We create training data pairs by extracting clean outlines and tonal illustrations from original pencil drawings using image filtering techniques, and we manually label the drawing styles. In addition, our model creates different pencil styles (e.g., line sketchiness and shading style) in a user-controllable manner. Experimental results on different types of pencil drawings show that the proposed algorithm performs favorably against existing methods in terms of quality, diversity and user evaluations.

In this paper, we propose an inverse reinforcement learning method for architecture search (IRLAS), which trains an agent to learn to search network structures that are topologically inspired by human-designed network. Most existing architecture search approaches totally neglect the topological characteristics of architectures, which results in complicated architecture with a high inference latency. Motivated by the fact that human-designed networks are elegant in topology with a fast inference speed, we propose a mirror stimuli function inspired by biological cognition theory to extract the abstract topological knowledge of an expert human-design network (ResNeXt). To avoid raising a too strong prior over the search space, we introduce inverse reinforcement learning to train the mirror stimuli function and exploit it as a heuristic guidance for architecture search, easily generalized to different architecture search algorithms. On CIFAR-10, the best architecture searched by our proposed IRLAS achieves 2.60% error rate. For ImageNet mobile setting, our model achieves a state-of-the-art top-1 accuracy 75.28%, while being 2 4x faster than most auto-generated architectures. A fast version of this model achieves 10% faster than MobileNetV2, while maintaining a higher accuracy.

Inferring 3D scene information from 2D observations is an open problem in computer vision. We propose using a deep-learning based energy minimization framework to learn a consistency measure between 2D observations and a proposed world model, and demonstrate that this framework can be trained end-to-end to produce consistent and realistic inferences. We evaluate the framework on human pose estimation and voxel-based object reconstruction benchmarks and show competitive results can be achieved with relatively shallow networks with drastically fewer learned parameters and floating point operations than conventional deep-learning approaches.

Hyperspectral images can provide rich clues for various computer vision tasks. However, the requirements of professional and expensive hardware for capturing hyperspectral images impede its wide applications. In this paper, based on a simple but not widely noticed phenomenon that the color printer can print color masks with a large number of independent spectral transmission responses, we propose a simple and low-budget scheme to capture the hyperspectral images with a random mask printed by the consumer-level color printer. Specifically, we notice that the printed dots with different colors are stacked together, forming multiplicative, instead of additive, spectral transmission responses. Therefore, new spectral transmission response uncorrelated with that of the original printer dyes are generated. With the random printed color mask, hyperspectral images could be captured in a snapshot way. A convolutional neural network (CNN) based method is developed to reconstruct the hyperspectral images from the captured image. The effectiveness and accuracy of the proposed system are verified on both synthetic and real captured images.

To overcome the limitations of existing hyperspectral cameras on spatial/temporal resolution, fusing a low resolution hyperspectral image (HSI) with a high resolution RGB (or multispectral) image into a high resolution HSI has been prevalent. Previous methods for this fusion task usually employ hand-crafted priors to model the underlying structure of the latent high resolution HSI, and the effect of the camera spectral response (CSR) of the RGB camera on super-resolution accuracy has rarely been investigated. In this paper, we first present a simple and efficient convolutional neural network (CNN) based method for HSI super-resolution in an unsupervised way, without any prior training. Later, we append a CSR optimization layer onto the HSI super-resolution network, either to automatically select the best CSR in a given CSR dataset, or to design the optimal CSR under some physical restrictions. Experimental results show our method outperforms the state-of-the-arts, and the CSR optimization can further boost the accuracy of HSI super-resolution.

Regularization is a fundamental technique to solve an ill-posed optimization problem robustly and is essential to reconstruct compressive hyperspectral images. Various hand-crafted priors have been employed as a regularizer but are often insufficient to handle the wide variety of spectra of natural hyperspectral images, resulting in poor reconstruction quality. Moreover, the prior-regularized optimization requires manual tweaking of its weight parameters to achieve a balance between the spatial and spectral fidelity of result images. In this paper, we present a novel hyperspectral image reconstruction algorithm that substitutes the traditional hand-crafted prior with a data-driven prior, based on an optimization-inspired network. Our method consists of two main parts: First, we learn a novel data-driven prior that regularizes the optimization problem with a goal to boost the spatial-spectral fidelity. Our data-driven prior learns both local coherence and dynamic characteristics of natural hyperspectral images. Second, we combine our regularizer with an optimization-inspired network to overcome the heavy computation problem in the traditional iterative optimization methods. We learn the complete parameters in the network through end-to-end training, enabling robust performance with high accuracy. Extensive simulation and hardware experiments validate the superior performance of our method over the state-of-the-art methods.

In zero-shot image retrieval (ZSIR) task, embedding learning becomes more attractive, however, many methods follow the traditional metric learning idea and omit the problems behind zero-shot settings. In this paper, we first emphasize the importance of learning visual discriminative metric and preventing the partial/selective learning behavior of learner in ZSIR, and then propose the Decoupled Metric Learning (DeML) framework to achieve these individually. Instead of coarsely optimizing an unified metric, we decouple it into multiple attention-specific parts so as to recurrently induce the discrimination and explicitly enhance the generalization. And they are mainly achieved by our object-attention module based on random walk graph propagation and the channel-attention module based on the adversary constraint, respectively. We demonstrate the necessity of addressing the vital problems in ZSIR on the popular benchmarks, outperforming the state-of-the-art methods by a significant margin. Code is available at http://www.bhchen.cn

Cascade is a classic yet powerful architecture that has boosted performance on various tasks. However, how to introduce cascade to instance segmentation remains an open question. A simple combination of Cascade R-CNN and Mask R-CNN only brings limited gain. In exploring a more effective approach, we find that the key to a successful instance segmentation cascade is to fully leverage the reciprocal relationship between detection and segmentation. In this work, we propose a new framework, Hybrid Task Cascade (HTC), which differs in two important aspects: (1) instead of performing cascaded refinement on these two tasks separately, it interweaves them for a joint multi-stage processing; (2) it adopts a fully convolutional branch to provide spatial context, which can help distinguishing hard foreground from cluttered background. Overall, this framework can learn more discriminative features progressively while integrating complementary features together in each stage. Without bells and whistles, a single HTC obtains 38.4% and 1.5% improvement over a strong Cascade Mask R-CNN baseline on MSCOCO dataset. Moreover, our overall system achieves 48.6 mask AP on the test-challenge split, ranking 1st in the COCO 2018 Challenge Object Detection Task. Code is available at https://github.com/open-mmlab/mmdetection.

Localizing an image w.r.t. a 3D scene model represents a core task for many computer vision applications. An increasing number of real-world applications of visual localization on mobile devices, e.g., Augmented Reality or autonomous robots such as drones or self-driving cars, demand localization approaches to minimize storage and bandwidth requirements. Compressing the 3D models used for localization thus becomes a practical necessity. In this work, we introduce a new hybrid compression algorithm that uses a given memory limit in a more effective way. Rather than treating all 3D points equally, it represents a small set of points with full appearance information and an additional, larger set of points with compressed information. This enables our approach to obtain a more complete scene representation without increasing the memory requirements, leading to a superior performance compared to previous compression schemes. As part of our contribution, we show how to handle ambiguous matches arising from point compression during RANSAC. Besides outperforming previous compression techniques in terms of pose accuracy under the same memory constraints, our compression scheme itself is also more efficient. Furthermore, the localization rates and accuracy obtained with our approach are comparable to state-of-the-art feature-based methods, while using a small fraction of the memory.