CVPR 2020 Papers

We present an interactive approach to synthesizing realistic variations in facial hair in images, ranging from subtle edits to existing hair to the addition of complex and challenging hair in images of clean-shaven subjects. To circumvent the tedious and computationally expensive tasks of modeling, rendering and compositing the 3D geometry of the target hairstyle using the traditional graphics pipeline, we employ a neural network pipeline that synthesizes realistic and detailed images of facial hair directly in the target image in under one second. The synthesis is controlled by simple and sparse guide strokes from the user defining the general structural and color properties of the target hairstyle. We qualitatively and quantitatively evaluate our chosen method compared to several alternative approaches. We show compelling interactive editing results with a prototype user interface that allows novice users to progressively refine the generated image to match their desired hairstyle, and demonstrate that our approach also allows for flexible and high-fidelity scalp hair synthesis.

Current methods for action recognition primarily rely on deep convolutional networks to derive feature embeddings of visual and motion features. While these methods have demonstrated remarkable performance on standard benchmarks, we are still in need of a better understanding as to how the videos, in particular their internal structures, relate to high-level semantics, which may lead to benefits in multiple aspects, e.g. interpretable predictions and even new methods that can take the recognition performances to a next level. Towards this goal, we construct TAPOS, a new dataset developed on sport videos with manual annotations of sub-actions, and conduct a study on temporal action parsing on top. Our study shows that a sport activity usually consists of multiple sub-actions and that the awareness of such temporal structures is beneficial to action recognition. We also investigate a number of temporal parsing methods, and thereon devise an improved method that is capable of mining sub-actions from training data without knowing the labels of them. On the constructed TAPOS, the proposed method is shown to reveal intra-action information, i.e. how action instances are made of sub-actions, and inter-action information, i.e. one specific sub-action may commonly appear in various actions.

Medicine is an important application area for deep learning models. Research in this field is a combination of medical expertise and data science knowledge. In this paper, instead of 2D medical images, we introduce an open-access 3D intracranial aneurysm dataset, IntrA, that makes the application of points-based and mesh-based classification and segmentation models available. Our dataset can be used to diagnose intracranial aneurysms and to extract the neck for a clipping operation in medicine and other areas of deep learning, such as normal estimation and surface reconstruction. We provide a large-scale benchmark of classification and part segmentation by testing state-of-the-art networks. We also discuss the performance of each method and demonstrate the challenges of our dataset. The published dataset can be accessed here: https://github.com/intra2d2019/IntrA.

Despite the recent advance of Generative Adversarial Networks (GANs) in high-fidelity image synthesis, there lacks enough understanding of how GANs are able to map a latent code sampled from a random distribution to a photo-realistic image. Previous work assumes the latent space learned by GANs follows a distributed representation but observes the vector arithmetic phenomenon. In this work, we propose a novel framework, called InterFaceGAN, for semantic face editing by interpreting the latent semantics learned by GANs. In this framework, we conduct a detailed study on how different semantics are encoded in the latent space of GANs for face synthesis. We find that the latent code of well-trained generative models actually learns a disentangled representation after linear transformations. We explore the disentanglement between various semantics and manage to decouple some entangled semantics with subspace projection, leading to more precise control of facial attributes. Besides manipulating gender, age, expression, and the presence of eyeglasses, we can even vary the face pose as well as fix the artifacts accidentally generated by GAN models. The proposed method is further applied to achieve real image manipulation when combined with GAN inversion methods or some encoder-involved models. Extensive results suggest that learning to synthesize faces spontaneously brings a disentangled and controllable facial attribute representation.

We present an interpretable deep model for fine-grained visual recognition. At the core of our method lies the integration of region-based part discovery and attribution within a deep neural network. Our model is trained using image-level object labels, and provides an interpretation of its results via the segmentation of object parts and the identification of their contributions towards classification. To facilitate the learning of object parts without direct supervision, we explore a simple prior of the occurrence of object parts. We demonstrate that this prior, when combined with our region-based part discovery and attribution, leads to an interpretable model that remains highly accurate. Our model is evaluated on major fine-grained recognition datasets, including CUB-200, CelebA and iNaturalist. Our results compares favourably to state-of-the-art methods on classification tasks, and outperforms previous approaches on the localization of object parts.

Recently, contour information largely improves the performance of saliency detection. However, the discussion on the correlation between saliency and contour remains scarce. In this paper, we first analyze such correlation and then propose an interactive two-stream decoder to explore multiple cues, including saliency, contour and their correlation. Specifically, our decoder consists of two branches, a saliency branch and a contour branch. Each branch is assigned to learn distinctive features for predicting the corresponding map. Meanwhile, the intermediate connections are forced to learn the correlation by interactively transmitting the features from each branch to the other one. In addition, we develop an adaptive contour loss to automatically discriminate hard examples during learning process. Extensive experiments on six benchmarks well demonstrate that our network achieves competitive performance with a fast speed around 50 FPS. Moreover, our VGG-based model only contains 17.08 million parameters, which is significantly smaller than other VGG-based approaches. Code has been made available at: https://github.com/moothes/ITSD-pytorch.

This paper explores how to harvest precise object segmentation masks while minimizing the human interaction cost. To achieve this, we propose an Inside-Outside Guidance (IOG) approach in this work. Concretely, we leverage an inside point that is clicked near the object center and two outside points at the symmetrical corner locations (top-left and bottom-right or top-right and bottom-left) of a tight bounding box that encloses the target object. This results in a total of one foreground click and four background clicks for segmentation. The advantages of our IOG is four-fold: 1) the two outside points can help to remove distractions from other objects or background; 2) the inside point can help to eliminate the unrelated regions inside the bounding box; 3) the inside and outside points are easily identified, reducing the confusion raised by the state-of-the-art DEXTR in labeling some extreme samples; 4) our approach naturally supports additional clicks annotations for further correction. Despite its simplicity, our IOG not only achieves state-of-the-art performance on several popular benchmarks, but also demonstrates strong generalization capability across different domains such as street scenes, aerial imagery and medical images, without fine-tuning. In addition, we also propose a simple two-stage solution that enables our IOG to produce high quality instance segmentation masks from existing datasets with off-the-shelf bounding boxes such as ImageNet and Open Images, demonstrating the superiority of our IOG as an annotation tool.

We address the problem of efficient end-to-end learning a multi-label Convolutional Neural Network (CNN) on training images with partial labels. Training a CNN with partial labels, hence a small number of images for every label, using the standard cross-entropy loss is prone to overfitting and performance drop. We introduce a new loss function that regularizes the cross-entropy loss with a cost function that measures the smoothness of labels and features of images on the data manifold. Given that optimizing the new loss function over the CNN parameters requires learning similarities among labels and images, which itself depends on knowing the parameters of the CNN, we develop an efficient interactive learning framework in which the two steps of similarity learning and CNN training interact and improve the performance of each another. Our method learns the CNN parameters without requiring keeping all training data in the memory, allows to learn few informative similarities only for images in each mini-batch and handles changing feature representations. By extensive experiments on Open Images, CUB and MS-COCO datasets,we demonstrate the effectiveness of our method. In particular, on the large-scale Open Images dataset, we improve the state of the art by 1.02% in mAP score over 5,000 classes.

In the task of interactive image segmentation, users initially click one point to segment the main body of the target object and then provide more points on mislabeled regions iteratively for a precise segmentation. Existing methods treat all interaction points indiscriminately, ignoring the difference between the first click and the remaining ones. In this paper, we demonstrate the critical role of the first click about providing the location and main body information of the target object. A deep framework, named First Click Attention Network (FCA-Net), is proposed to make better use of the first click. In this network, the interactive segmentation result can be much improved with the following benefits: focus invariance, location guidance, and error-tolerant ability. We then put forward a click-based loss function and a structural integrity strategy for better segmentation effect. The visualized segmentation results and sufficient experiments on five datasets demonstrate the importance of the first click and the superiority of our FCA-Net.

Person images captured by unconstrained surveillance cameras often have low resolutions (LR). This causes the resolution mismatch problem when matched against the high-resolution (HR) gallery images, negatively affecting the performance of person re-identification (re-id). An effective approach is to leverage image super-resolution (SR) along with person re-id in a joint learning manner. However, this scheme is limited due to dramatically more difficult gradients backpropagation during training. In this paper, we introduce a novel model training regularisation method, called Inter-Task Association Critic (INTACT), to address this fundamental problem. Specifically, INTACT discovers the underlying association knowledge between image SR and person re-id, and leverages it as an extra learning constraint for enhancing the compatibility of SR model with person re-id in HR image space. This is realised by parameterising the association constraint which enables it to be automatically learned from the training data. Extensive experiments validate the superiority of INTACT over the state-of-the-art approaches on the cross-resolution re-id task using five standard person re-id datasets.

We study the problem of distilling knowledge from a large deep teacher network to a much smaller student network for the task of road marking segmentation. In this work, we explore a novel knowledge distillation (KD) approach that can transfer 'knowledge' on scene structure more effectively from a teacher to a student model. Our method is known as Inter-Region Affinity KD (IntRA-KD). It decomposes a given road scene image into different regions and represents each region as a node in a graph. An inter-region affinity graph is then formed by establishing pairwise relationships between nodes based on their similarity in feature distribution. To learn structural knowledge from the teacher network, the student is required to match the graph generated by the teacher. The proposed method shows promising results on three large-scale road marking segmentation benchmarks, i.e., ApolloScape, CULane and LLAMAS, by taking various lightweight models as students and ResNet-101 as the teacher. IntRA-KD consistently brings higher performance gains on all lightweight models, compared to previous distillation methods. Our code is available at https://github.com/ cardwing/Codes-for-IntRA-KD.

Home design is a complex task that normally requires architects to finish with their professional skills and tools. It will be fascinating that if one can produce a house plan intuitively without knowing much knowledge about home design and experience of using complex designing tools, for example, via natural language. In this paper, we formulate it as a language conditioned visual content generation problem that is further divided into a floor plan generation and an interior texture (such as floor and wall) synthesis task. The only control signal of the generation process is the linguistic expression given by users that describe the house details. To this end, we propose a House Plan Generative Model (HPGM) that first translates the language input to a structural graph representation and then predicts the layout of rooms with a Graph Conditioned Layout Prediction Network (GC-LPN) and generates the interior texture with a Language Conditioned Texture GAN (LCT-GAN). With some post-processing, the final product of this task is a 3D house model. To train and evaluate our model, we build the first Text--to--3D House Model dataset, which will be released at: https:// hidden-link-for-submission.

Weakly supervised learning has emerged as a compelling tool for object detection by reducing the need for strong supervision during training. However, major challenges remain: (1) differentiation of object instances can be ambiguous; (2) detectors tend to focus on discriminative parts rather than entire objects; (3) without ground truth, object proposals have to be redundant for high recalls, causing significant memory consumption. Addressing these challenges is difficult, as it often requires to eliminate uncertainties and trivial solutions. To target these issues we develop an instance-aware and context-focused unified framework. It employs an instance-aware self-training algorithm and a learnable Concrete DropBlock while devising a memory-efficient sequential batch back-propagation. Our proposed method achieves state-of-the-art results on COCO (12.1% AP, 24.8% AP50), VOC 2007 (54.9% AP), and VOC 2012 (52.1% AP), improving baselines by great margins. In addition, the proposed method is the first to benchmark ResNet based models and weakly supervised video object detection. Refer to our project page for code, models, and more details: https://github.com/NVlabs/wetectron.

Image colorization is inherently an ill-posed problem with multi-modal uncertainty. Previous methods leverage the deep neural network to map input grayscale images to plausible color outputs directly. Although these learning-based methods have shown impressive performance, they usually fail on the input images that contain multiple objects. The leading cause is that existing models perform learning and colorization on the entire image. In the absence of a clear figure-ground separation, these models cannot effectively locate and learn meaningful object-level semantics. In this paper, we propose a method for achieving instance-aware colorization. Our network architecture leverages an off-the-shelf object detector to obtain cropped object images and uses an instance colorization network to extract object-level features. We use a similar network to extract the full-image features and apply a fusion module to full object-level and image-level features to predict the final colors. Both colorization networks and fusion modules are learned from a large-scale dataset. Experimental results show that our work outperforms existing methods on different quality metrics and achieves state-of-the-art performance on image colorization.

Instance shadow detection is a brand new problem, aiming to find shadow instances paired with object instances. To approach it, we first prepare a new dataset called SOBA, named after Shadow-OBject Association, with 3,623 pairs of shadow and object instances in 1,000 photos, each with individual labeled masks. Second, we design LISA, named after Light-guided Instance Shadow-object Association, an end-to-end framework to automatically predict the shadow and object instances, together with the shadow-object associations and light direction. Then, we pair up the predicted shadow and object instances, and match them with the predicted shadow-object associations to generate the final results. In our evaluations, we formulate a new metric named the shadow-object average precision to measure the performance of our results. Further, we conducted various experiments and demonstrate our method's applicability on light direction estimation and photo editing.

We present a new instance segmentation approach tailored to biological images, where instances may correspond to individual cells, organisms or plant parts. Unlike instance segmentation for user photographs or road scenes, in biological data object instances may be particularly densely packed, the appearance variation may be particularly low, the processing power may be restricted, while, on the other hand, the variability of sizes of individual instances may be limited. The proposed approach successfully addresses these peculiarities. Our approach describes each object instance using an expectation of a limited number of sine waves with frequencies and phases adjusted to particular object sizes and densities. At train time, a fully-convolutional network is learned to predict the object embeddings at each pixel using a simple pixelwise regression loss, while at test time the instances are recovered using clustering in the embedding space. In the experiments, we show that our approach outperforms previous embedding-based instance segmentation approaches on a number of biological datasets, achieving state-of-the-art on a popular CVPPP benchmark. This excellent performance is combined with computational efficiency that is needed for deployment to domain specialists. The source code of the approach is available at https://github.com/kulikovv/harmonic .

Person detection networks have been widely used in person search. These detectors discriminate persons from the background and generate proposals of all the persons from a gallery of scene images for each query. However, such a large number of proposals have a negative influence on the following identity matching process because many distractors are involved. In this paper, we propose a new detection network for person search, named Instance Guided Proposal Network (IGPN), which can learn the similarity between query persons and proposals. Thus, we can decrease proposals according to the similarity scores. To incorporate information of the query into the detection network, we introduce the Siamese region proposal network to Faster-RCNN and we propose improved cross-correlation layers to alleviate the imbalance of parameters distribution. Furthermore, we design a local relation block and a global relation branch to leverage the proposal-proposal relations and query-scene relations, respectively. Extensive experiments show that our method improves the person search performance through decreasing proposals and achieves competitive performance on two large person search benchmark datasets, CUHK-SYSU and PRW.

Few-shot learning (FSL) aims to recognize new objects with extremely limited training data for each category. Previous efforts are made by either leveraging meta-learning paradigm or novel principles in data augmentation to alleviate this extremely data-scarce problem. In contrast, this paper presents a simple statistical approach, dubbed Instance Credibility Inference (ICI) to exploit the distribution support of unlabeled instances for few-shot learning. Specifically, we first train a linear classifier with the labeled few-shot examples and use it to infer the pseudo-labels for the unlabeled data. To measure the credibility of each pseudo-labeled instance, we then propose to solve another linear regression hypothesis by increasing the sparsity of the incidental parameters and rank the pseudo-labeled instances with their sparsity degree. We select the most trustworthy pseudo-labeled instances alongside the labeled examples to re-train the linear classifier. This process is iterated until all the unlabeled samples are included in the expanded training set, i.e. the pseudo-label is converged for unlabeled data pool. Extensive experiments under two few-shot settings show that our simple approach can establish new state-of-the-arts on four widely used few-shot learning benchmark datasets including miniImageNet, tieredImageNet, CIFAR-FS, and CUB. Our code is available at: https://github.com/Yikai-Wang/ICI-FSL

This paper presents an information-theoretic approach to point selection in direct RGB-D odometry. The aim is to select only the most informative measurements, in order to reduce the optimization problem with a minimal impact in the accuracy. It is usual practice in visual odometry/SLAM to track several hundreds of points, achieving real-time performance in high-end desktop PCs. Reducing their computational footprint will facilitate the implementation of odometry and SLAM in low-end platforms such as small robots and AR/VR glasses. Our experimental results show that our novel information-based selection criterion allows us to reduce the number of tracked points an order of magnitude (down to only 24 of them), achieving an accuracy similar to the state of the art (sometimes outperforming it) while reducing 10 times the computational demand.