Current age datasets lie in a long-tailed distribution, which brings difficulties to describe the aging mechanism for the imbalance ages. To alleviate it, we design a novel facial age prior to guide the aging mechanism modeling. To explore the age effects on facial images, we propose a Disentangled Adversarial Autoencoder (DAAE) to disentangle the facial images into three independent factors: age, identity and extraneous information. To avoid the ""wash away"" of age and identity information in face aging process, we propose a hierarchical conditional generator by passing the disentangled identity and age embeddings to the high-level and low-level layers with class-conditional BatchNorm. Finally, a disentangled adversarial learning mechanism is introduced to boost the image quality for face aging. In this way, when manipulating the age distribution, DAAE can achieve face aging with arbitrary ages. Further, given an input face image, the mean value of the learned age posterior distribution can be treated as an age estimator. These indicate that DAAE can efficiently and accurately estimate the age distribution by a disentangling manner. DAAE is the first attempt to achieve facial age analysis tasks, including face aging with arbitrary ages, exemplar-based face aging and age estimation, in an universal framework. The qualitative and quantitative experiments demonstrate the superiority of DAAE on five popular datasets, including CACD2000, Morph, UTKFace, FG-NET and AgeDB.
论文检索
输入标题、作者或关键词，从 1,358 篇学术成果中精准定位
Point clouds are often the default choice for many applications as they exhibit more flexibility and efficiency than volumetric data. Nevertheless, their unorganized nature - points are stored in an unordered way - makes them less suited to be processed by deep learning pipelines. In this paper, we propose a method for 3D object completion and classification based on point clouds. We introduce a new way of organizing the extracted features based on their activations, which we name soft pooling. For the decoder stage, we propose regional convolutions, a novel operator aimed at maximizing the global activation entropy. Furthermore, inspired by the local refining procedure in Point Completion Network (PCN), we also propose a patch-deforming operation to simulate deconvolutional operations for point clouds. This paper proves that our regional activation can be incorporated in many point cloud architectures like AtlasNet and PCN, leading to better performance for geometric completion. We evaluate our approach on different 3D tasks such as object completion and classification, achieving state-of-the-art accuracy.
The human visual system is remarkably robust against a wide range of naturally occurring variations and corruptions like rain or snow. In contrast, the performance of modern image recognition models strongly degrades when evaluated on previously unseen corruptions. Here, we demonstrate that a simple but properly tuned training with additive Gaussian and Speckle noise generalizes surprisingly well to unseen corruptions, easily reaching the state of the art on the corruption benchmark ImageNet-C (with ResNet50) and on MNIST-C. We build on top of these strong baseline results and show that an adversarial training of the recognition model against locally correlated worst-case noise distributions leads to an additional increase in performance. This regularization can be combined with previously proposed defense methods for further improvement.
Humans can envision a realistic photo given a free-hand sketch that is not only spatially imprecise and geometrically distorted but also without colors and visual details. We study unsupervised sketch to photo synthesis for the first time, learning from unpaired sketch and photo data where the target photo for a sketch is unknown during training. Existing works only deal with either style difference or spatial deformation alone, synthesizing photos from edge-aligned line drawings or transforming shapes within the same modality, e.g., color images. Our insight is to decompose the unsupervised sketch to photo synthesis task into two stages of translation: First shape translation from sketches to grayscale photos and then content enrichment from grayscale to color photos. We also incorporate a self-supervised denoising objective and an attention module to handle abstraction and style variations that are specific to sketches. Our synthesis is sketch-faithful and photo-realistic, enabling sketch-based image retrieval and automatic sketch generation that captures human visual perception beyond the edge map of a photo.
In this paper, we advocate the adoption of metric preservation as a powerful prior for learning latent representations of deformable 3D shapes. Key to our construction is the introduction of a geometric distortion criterion, defined directly on the decoded shapes, translating the preservation of the metric on the decoding to the formation of linear paths in the underlying latent space. Our rationale lies in the observation that training samples alone are often insufficient to endow generative models with high fidelity, motivating the need for large training datasets. In contrast, metric preservation provides a rigorous way to control the amount of geometric distortion incurring in the construction of the latent space, leading in turn to synthetic samples of higher quality. We further demonstrate, for the first time, the adoption of differentiable intrinsic distances in the backpropagation of a geodesic loss. Our geometric priors are particularly relevant in the presence of scarce training data, where learning any meaningful latent structure can be especially challenging. The effectiveness and potential of our generative model is showcased in applications of style transfer and content generation using triangle meshes and point clouds.
While models of 3D clothing learned from real data exist, no method can predict clothing deformation as a function of garment size. In this paper, we introduce SizerNet to predict 3D clothing conditioned on human body shape and garment size parameters, and ParserNet to infer garment meshes and shape under clothing with personal details in a single pass from an input mesh. SizerNet allows to estimate and visualize the dressing effect of a garment in various sizes, and ParserNet allows to edit clothing of an input mesh directly, removing the need for scan segmentation, which is a challenging problem in itself. To learn these models, we introduce the SIZER dataset of clothing size variation which includes 100 different subjects wearing casual clothing items in various sizes, totaling to approximately 2000 scans. This dataset includes the scans, registrations to the SMPL model, scans segmented in clothing parts, garment category and size labels. Our experiments show better parsing accuracy and size prediction than baseline methods trained on SIZER. The code, model and dataset will be released for research purposes at: https://virtualhumans.mpi-inf.mpg.de/sizer/.
Video object segmentation (VOS) is a highly challenging problem, since the target object is only defined by a first-frame reference mask during inference. The problem of how to capture and utilize this limited information to accurately segment the target remains a fundamental research question. We address this by introducing an end-to-end trainable VOS architecture that integrates a differentiable few-shot learner. Our learner is designed to predict a powerful parametric model of the target by minimizing a segmentation error in the first frame. We further go beyond the standard few-shot learning paradigm by learning what our target model should learn in order to maximize segmentation accuracy. We perform extensive experiments on standard benchmarks. Our approach sets a new state-of-the-art on the large-scale YouTube-VOS 2018 dataset by achieving an overall score of 81.5, corresponding to a 2.6% relative improvement over the previous best result. The code and models are available at https://github.com/visionml/pytracking.
Human trajectory forecasting with multiple socially interact-ing agents is of critical importance for autonomous navigation in human environments, e.g., for self-driving cars and social robots. In this work, we present Predicted Endpoint Conditioned Network (PECNet) for flexible human trajectory prediction. PECNet infers distant trajectory endpoints to assist in long-range multi-modal trajectory prediction. A novel non-local social pooling layer enables PECNet to infer diverse yet socially compliant trajectories. Additionally, we present a simple “truncation-trick” for improving few-shot multi-modal trajectory prediction performance. We show that PECNet improves state-of-the-art performance on the Stanford Drone trajectory prediction benchmark by ~20.9% and on the ETH/UCY benchmark by ∼40.8%. Code available at the home page: https://karttikeya.github.io/publication/htf/
Image descriptions can help visually impaired people to quickly understand the image content. While we made significant progress in automatically describing images and optical character recognition, current approaches are unable to include written text in their descriptions, although text is omnipresent in human environments and frequently critical to understand our surroundings. To study how to comprehend text in the context of an image we collect a novel dataset, TextCaps, with 145k captions for 28k images. Our dataset challenges a model to recognize text, relate it to its visual context, and decide what part of the text to copy or paraphrase, requiring spatial, semantic, and visual reasoning between multiple text tokens and visual entities, such as objects. We study baselines and adapt existing approaches to this new task, which we refer to as image captioning with reading comprehension. Our analysis with automatic and human studies shows that our new TextCaps dataset provides many new technical challenges over previous datasets.
Deep encoder-decoder based CNNs have advanced image inpainting methods for hole filling. While existing methods recover structures and textures step-by-step in the hole regions, they typically use two encoder-decoders for separate recovery. The CNN features of each encoder are learned to capture either missing structures or textures without considering them as a whole. The insufficient utilization of these encoder features hampers the performance of recovering both structures and textures. In this paper, we propose a mutual encoder-decoder CNN for joint recovery of both. We use CNN features from the deep and shallow layers of the encoder to represent structures and textures of an input image, respectively. The deep layer features are sent to a structure branch, while the shallow layer features are sent to a texture branch. In each branch, we fill holes in multiple scales of the CNN features. The filled CNN features from both branches are concatenated and then equalized. During feature equalization, we reweigh channel attentions first and propose a bilateral propagation activation function to enable spatial equalization. To this end, the filled CNN features of structure and texture mutually benefit each other to represent image content at all feature levels. We then use the equalized feature to supplement decoder features for output image generation through skip connections. Experiments on benchmark datasets show that the proposed method is effective to recover structures and textures and performs favorably against state-of-the-art approaches.
To be invariant, or not to be invariant: that is the question formulated in this work about local descriptors. A limitation of current feature descriptors is the trade-off between generalization and discriminative power: more invariance means less informative descriptors. We propose to overcome this limitation with a disentanglement of invariance in local descriptors and with an online selection of the most appropriate invariance given the context. Our framework consists in a joint learning of multiple local descriptors with different levels of invariance and of meta descriptors encoding the regional variations of an image. The similarity of these meta descriptors across images is used to select the right invariance when matching the local descriptors. Our approach, named Local Invariance Selection at Runtime for Descriptors (LISRD), enables descriptors to adapt to adverse changes in images, while remaining discriminative when invariance is not required. We demonstrate that our method can boost the performance of current descriptors and outperforms state-of-the-art descriptors in several matching tasks, when evaluated on challenging datasets with day-night illumination as well as viewpoint changes.
no landmarks!"" - Unsupervised, model-based dense face alignment","In this paper, we show how to train an image-to-image network to predict dense correspondence between a face image and a 3D morphable model using only the model for supervision. We show that both geometric parameters (shape, pose and camera intrinsics) and photometric parameters (texture and lighting) can be inferred directly from the correspondence map using linear least squares and our novel inverse spherical harmonic lighting model. The least squares residuals provide an unsupervised training signal that allows us to avoid artefacts common in the literature such as shrinking and conservative underfitting. Our approach uses a network that is 10$ imes$ smaller than parameter regression networks, significantly reduces sensitivity to image alignment and allows known camera calibration or multi-image constraints to be incorporated during inference. We achieve results competitive with state-of-the-art but without any auxiliary supervision used by previous methods.
In recent years we have witnessed tremendous progress in unpaired image-to-image translation, propelled by the emergence of DNNs and adversarial training strategies. However, most existing methods focus on transfer of style and appearance, rather than on shape translation. The latter task is challenging, due to its intricate non-local nature, which calls for additional supervision. We mitigate this by descending the deep layers of a pre-trained network, where the deep features contain more semantics, and applying the translation between these deep features. Our translation is performed in a cascaded, deep-to-shallow, fashion, along the deep feature hierarchy: we first translate between the deepest layers that encode the higher-level semantic content of the image, proceeding to translate the shallower layers, conditioned on the deeper ones. We further demonstrate the effectiveness of using pre-trained deep features in the context of unconditioned image generation.
We present a learning-based method for interpolating and manipulating 3D shapes represented as point clouds, that is explicitly designed to preserve intrinsic shape properties. Our approach is based on constructing a dual encoding space that enables shape synthesis and, at the same time, provides links to the intrinsic shape metric, which is typically not available on point cloud data. Our method works in a single pass and avoids expensive optimization, employed by existing techniques. Furthermore, the strong regularization provided by our dual latent space approach also helps to improve shape recovery in challenging settings from noisy point clouds across datasets. Extensive experiments show that our method results in more realistic and smoother interpolations compared to baselines.
Finding out the computational redundant part of a trained Deep Neural Network (DNN) is the key question that pruning algorithms target on. Many algorithms try to predict model performance of the pruned sub-nets by introducing various evaluation methods. But they are either inaccurate or very complicated for general application. In this work, we present a pruning method called EagleEye, in which a simple yet efficient evaluation component based on adaptive batch normalization is applied to unveil a strong correlation between different pruned DNN structures and their final settled accuracy. This strong correlation allows us to fast spot the pruned candidates with highest potential accuracy without actually fine-tuning them. This module is also general to plug-in and improve some existing pruning algorithms. EagleEye achieves better pruning performance than all of the studied pruning algorithms in our experiments. Concretely, to prune MobileNet V1 and ResNet-50, EagleEye outperforms all compared methods by up to 3.8%. Even in the more challenging experiments of pruning the compact model of MobileNet V1, EagleEye achieves the highest accuracy of 70.9% with an overall 50% operations (FLOPs) pruned. All accuracy results are Top-1 ImageNet classification accuracy. Source code and models are accessible to open-source community.https://github.com/anonymous47823493/EagleEye
Training Interpretable Convolutional Neural Networks by Differentiating Class-specific Filters
PDF ↗Convolutional neural networks (CNNs) have been successfully used in a range of tasks. However, CNNs are often viewed as ""black-box"" and lack of interpretability. One main reason is due to the filter-class entanglement -- an intricate many-to-many correspondence between filters and classes. Most existing works attempt post-hoc interpretation on a pre-trained model, while neglecting to reduce the entanglement underlying the model. In contrast, we focus on alleviating filter-class entanglement during training. Inspired by cellular differentiation, we propose a novel strategy to train interpretable CNNs by encouraging class-specific filters, among which each filter responds to only one (or few) class. Concretely, we design a learnable sparse Class-Specific Gate (CSG) structure to assign each filter with one (or few) class in a flexible way. The gate allows a filter's activation to pass only when the input samples come from the specific class. Extensive experiments demonstrate the fabulous performance of our method in generating a sparse and highly class-related representation of the input, which leads to stronger interpretability. Moreover, comparing with the standard training strategy, our model displays benefits in applications like object localization and adversarial sample detection. Code link: https://github.com/hyliang96/CSGCNN .
In this paper, we explore the use of vehicle-to-vehicle (V2V) communication to improve the perception and motion forecasting performance of self-driving vehicles. By intelligently aggregating the information received from multiple nearby vehicles, we can observe the same scene from different viewpoints. This allows us to see through occlusions and detect actors at long range, where the observations are very sparse or non-existent. We also show that our approach of sending compressed deep feature map activations achieves high accuracy while satisfying communication bandwidth requirements.
Learning-based methods produce remarkable results on single image depth tasks when trained on well-established benchmarks, however, there is a large gap from these benchmarks to real-world performance that is usually obscured by the common practice of fine-tuning on the target dataset. We introduce a new depth dataset that is an order of magnitude larger than previous offerings, but more importantly, contains an unprecedented gamut of locations, camera models and scene types while offering metric depth (not just up-to-scale). Additionally, we investigate the problem of training single image depth networks using images captured with many different cameras, validating an existing approach and proposing a simpler alternative. With our contributions we achieve excellent results on challenging benchmarks before fine-tuning, and set the state of the art on the popular KITTI dataset after fine-tuning.
Automatic satellite-based reconstruction enables large and widespread creation of urban areas. However, satellite imagery is often noisy and incomplete, and is not suitable for reconstructing detailed building facades. We present a machine learning-based inverse procedural modeling method to automatically create synthetic facades from satellite imagery. Our key observation is that building facades exhibit regular, grid-like structures. Hence, we can overcome the low-resolution, noisy, and partial building data obtained from satellite imagery by synthesizing the underlying facade layout. Our method infers regular facade details from satellite-based image-fragments of a building, and applies them to occluded or under-sampled parts of the building, resulting in plausible, crisp facades. Using urban areas from six cities, we compare our approach to several state-of-the-art image completion/in-filling methods and our approach consistently creates better facade images.
We systematically compare and analyze a set of key components in unsupervised optical flow to identify which photometric loss, occlusion handling, and smoothness regularization is most effective. Alongside this investigation we construct a number of novel improvements to unsupervised flow models, such as cost volume normalization, stopping the gradient at the occlusion mask, encouraging smoothness before upsampling the flow field, and continual self-supervision with image resizing. By combining the results of our investigation with our improved model components, we are able to present a new unsupervised flow technique that significantly outperforms the previous unsupervised state-of-the-art and performs on par with supervised FlowNet2 on the KITTI 2015 dataset, while also being significantly simpler than related approaches.