ECCV 2020 论文列表

For any recognition system, the ability to identify novel class samples during inference is an important aspect of the system’s robustness. This problem of detecting novel class samples during inference is commonly referred to as Multiple Class Novelty Detection. In this paper, we propose a novel method that makes deep convolutional neural networks robust to novel classes. Specifically, during training one branch performs traditional classification (referred to as global inference), and the other branch provides patch-level information to keep track of the class-specific activation patterns (referred to as local inference). Both global and local branch information are combined to train a novelty detection network, which is used during inference to identify novel classes. We evaluate the proposed method on four datasets (Caltech256, CUB-200, Stanford Dogs and FounderType-200) and show that the proposed method is able to identify novel class samples better compared to the other deep convolutional neural network based methods."

Object tracking is a well-studied problem in computer vision while identifying salient spots of objects in a video is a less explored direction in the literature. Video eye gaze estimation methods aim to tackle a related task but salient spots in those methods are not bounded by objects and tend to produce very scattered, unstable predictions due to the noisy ground truth data. We reformulate the problem of detecting and tracking of salient object spots as a new task called object hotspot tracking. In this paper, we propose to tackle this task jointly with unsupervised video object segmentation, in real-time, with a unified framework to exploit the synergy between the two. Specifically, we propose a Weighted Correlation Siamese Network (WCS-Net) which employs a Weighted Correlation Block (WCB) for encoding the pixel-wise correspondence between a template frame and the search frame. In addition, WCB takes the initial mask / hotspot as guidance to enhance the influence of salient regions for robust tracking. Our system can operate online during inference and jointly produce the object mask and hotspot track-lets at 33 FPS. Experimental results validate the effectiveness of our network design, and show the benefits of jointly solving the hotspot tracking and object segmentation problems. In particular, our method performs favorably against state-of-the-art video eye gaze models in object hotspot tracking, and outperforms existing methods on three benchmark datasets for unsupervised video object segmentation."

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."

Parametric models of humans, faces, hands and animals have been widely used for a range of tasks such as image-based reconstruction, shape correspondence estimation, and animation. Their key strength is the ability to factor surface variations into shape and pose dependent components. Learning such models requires lots of expert knowledge and hand-defined object-specific constraints, making the learning approach unscalable to novel objects. In this paper, we present a simple yet effective approach to learn disentangled shape and pose representations in an unsupervised setting. We use a combination of self-consistency and cross-consistency constraints to learn pose and shape space from registered meshes. We additionally incorporate as-rigid-as-possible deformation(ARAP) into the training loop to avoid degenerate solutions. We demonstrate the usefulness of learned representations through a number of tasks including pose transfer and shape retrieval. The experiments on datasets of 3D humans, faces, hands and animals demonstrate the generality of our approach. Code is made available at https://virtualhumans.mpi-inf.mpg.de/unsup_shape_pose/."

We present an unsupervised 3D deep learning framework based on a ubiquitously true proposition named by us view-object consistency as it states that a 3D object and its projected 2D views always belong to the same object class. To validate its effectiveness, we design a multi-view CNN instantiating it for the salient view selection of 3D objects, which quintessentially cannot be handled by supervised learning due to the difficulty of collecting sufficient and consistent training data. Our unsupervised multi-view CNN branches off two channels which encode the knowledge within each 2D view and the 3D object respectively and also exploits both intra-view and inter-view knowledge of the object. It ends with a new loss layer which formulates the view-object consistency by impelling the two channels to generate consistent classification outcomes. We evaluate our method both qualitatively and quantitatively, demonstrating its superiority over several state-of-the-art methods. In addition, we showcase that our method can be used to select salient views of 3D scenes containing multiple objects."

In this paper, we look into the problem of estimating per-pixel depth maps from unconstrained RGB monocular night-time images which is a difficult task that has not been addressed adequately in the literature. The state-of-the-art day-time depth estimation methods fail miserably when tested with night-time images due to a large domain shift between them. The usual photometric losses used for training these networks may not work for night-time images due to the absence of uniform lighting which is commonly present in day-time images, making it a difficult problem to solve. We propose to solve this problem by posing it as a domain adaptation problem where a network trained with day-time images is adapted to work for night-time images. Specifically, an encoder is trained to generate features from night-time images that are indistinguishable from those obtained from day-time images by using a PatchGAN-based adversarial discriminative learning method. Unlike the existing methods that directly adapt depth prediction (network output), we propose to adapt feature maps obtained from the encoder network so that a pre-trained day-time depth decoder can be directly used for predicting depth from these adapted features. Hence, the resulting method is termed as “Adversarial Domain Feature Adaptation (ADFA)” and its efficacy is demonstrated through experimentation on the challenging Oxford night driving dataset. To the best of our knowledge, this work is a first of its kind to estimate depth from unconstrained night-time monocular RGB images that uses a completely unsupervised learning process. The modular encoder-decoder architecture for the proposed ADFA method allows us to use the encoder module as a feature extractor which can be used in many other applications. One such application is demonstrated where the features obtained from our adapted encoder network are shown to outperform other state-of-the-art methods in a visual place recognition problem, thereby, further establishing the usefulness and effectiveness of the proposed approach."

Deep unsupervised learning for optical flow has been proposed, where the loss measures image similarity with the warping function parameterized by estimated flow. The census transform, instead of image pixel values, is often used for the image similarity. In this work, rather than the handcrafted features i.e. census or pixel values, we propose to use deep self-supervised features with a novel similarity measure, which fuses multi-layer similarities. With the fused similarity, our network better learns flow by minimizing our proposed feature separation loss. The proposed method is a polarizing scheme, resulting in a more discriminative similarity map. In the process, the features are also updated to get high similarity for matching pairs and low for uncertain pairs, given estimated flow. We evaluate our method on FlyingChairs, MPI Sintel, and KITTI benchmarks. In quantitative and qualitative comparisons, our method effectively improves the state-of-the-art techniques."

Automatic discovery of category-specific 3D keypoints from a collection of objects of a category is a challenging problem. The difficulty is added when objects are represented by 3D point clouds, with variations in shape and semantic parts and unknown coordinate frames. We define keypoints to be category-specific, if they meaningfully represent objects’ shape and their correspondences can be simply established order-wise across all objects. This paper aims at learning such 3D keypoints, in an unsupervised manner, using a collection of misaligned 3D point clouds of objects from an unknown category. In order to do so, we model shapes defined by the keypoints, within a category, using the symmetric linear basis shapes without assuming the plane of symmetry to be known. The usage of symmetry prior leads us to learn stable keypoints suitable for higher misalignments. To the best of our knowledge, this is the first work on learning such keypoints directly from 3D point clouds for a general category. Using objects from four benchmark datasets, we demonstrate the quality of our learned keypoints by quantitative and qualitative evaluations. Our experiments also show that the keypoints discovered by our method are geometrically and semantically consistent."

Caricature attributes provide distinctive facial features to help research in Psychology and Neuroscience. However, unlike the facial photo attribute datasets that have a quantity of annotated images, the annotations of caricature attributes are rare. To facility the research in attribute learning of caricatures, we propose a caricature attribute dataset, namely WebCariA. Moreover, to utilize models that trained by face attributes, we propose a novel unsupervised domain adaptation framework for cross-modality (i.e., photos to caricatures) attribute recognition, with an integrated inter- and intra-domain consistency learning scheme. Specifically, the inter-domain consistency learning scheme consisting an image-to-image translator to first fill the domain gap between photos and caricatures by generating intermediate image samples, and a label consistency learning module to align their semantic information. The intra-domain consistency learning scheme integrates the common feature consistency learning module with a novel attribute-aware attention-consistency learning module for a more efficient alignment. We did an extensive ablation study to show the effectiveness of the proposed method. And the proposed method also outperforms the state-of-the-art methods by a margin. The implementation of the proposed method is available at https://github.com/KeleiHe/DAAN."

Unsupervised domain adaptation (UDA) in the task of person re-identification (re-ID) is highly challenging due to large domain divergence and no class overlap between domains. Pseudo-label based self-training is one of the representative techniques to address UDA. However, label noise caused by unsupervised clustering is always a trouble to self-training methods. To depress noises in pseudo-labels, this paper proposes a Noise Resistible Mutual-Training (NRMT) method, which maintains two networks during training to perform collaborative clustering and mutual instance selection. On one hand, collaborative clustering eases the fitting to noisy instances by allowing the two networks to use pseudo-labels provided by each other as an additional supervision. On the other hand, mutual instance selection further selects reliable and informative instances for training according to the peer-confidence and relationship disagreement of the networks. Extensive experiments demonstrate that the proposed method outperforms the state-of-the-art UDA methods for person re-ID."

Person re-identification (ReID) remains a challenging task in many real-word video analytics and surveillance applications, even though state-of-the-art accuracy has improved considerably with the advent of deep learning (DL) models trained on large image datasets. Given the shift in distributions that typically occurs between video data captured from the source and target domains, and absence of labeled data from the target domain, it is difficult to adapt a DL model for accurate recognition of target data. DL models for unsupervised domain adaptation (UDA) are commonly designed in the feature representation space. We argue that for pair-wise matchers that rely on metric learning, e.g., Siamese networks for person ReID, the UDA objective should consist in aligning pair-wise dissimilarity between domains, rather than aligning feature representations. Moreover, dissimilarity representations are more suitable for designing open-set ReID systems, where identities differ in the source and target domains. In this paper, we propose a novel Dissimilarity-based Maximum Mean Discrepancy (D-MMD) loss for aligning pair-wise distances that can be optimized via gradient descent using relatively small batch sizes. From a person ReID perspective, the evaluation of D-MMD loss is straightforward since the tracklet information (provided by a person tracker) allows to label a distance vector as being either within-class (within-tracklet) or between-class (between-tracklet). This allows approximating the underlying distribution of target pair-wise distances for D-MMD loss optimization, and accordingly align source and target distance distributions. Empirical results with three challenging benchmark datasets show that the proposed D-MMD loss decreases as source and domain distributions become more similar. Extensive experimental evaluation also indicates that UDA methods that rely on the D-MMD loss can significantly outperform baseline and state-of-the-art UDA methods for person ReID. The dissimilarity space transformation allows to design reliable pair-wise matchers, without the common requirement for data augmentation and/or complex networks. Code is available on GitHub link: https://github.com/djidje/D-MMD"

Segmentation of the pixels corresponding to human skin is an essential first step in multiple applications ranging from surveillance to heart-rate estimation from remote-photoplethysmography. However, the existing literature considers the problem only in the visible-range of the EM-spectrum which limits their utility in low or no light settings where the criticality of the application is higher. To alleviate this problem, we consider the problem of skin segmentation from the Near-infrared images. However, Deep learning based state-of-the-art segmentation techniques demands large amounts of labelled data that is unavailable for the current problem. Therefore we cast the skin segmentation problem as that of target-independent Unsupervised Domain Adaptation (UDA) where we use the data from the Red-channel of the visible-range to develop skin segmentation algorithm on NIR images. We propose a method for target-independent segmentation where the 'nearest-clone' of a target image in the source domain is searched and used as a proxy in the segmentation network trained only on the source domain. We prove the existence of 'nearest-clone' and propose a method to find it through an optimization algorithm over the latent space of a Deep generative model based on variational inference. We demonstrate the efficacy of the proposed method for NIR skin segmentation over the state-of-the-art UDA segmentation methods on the two newly created skin segmentation datasets in NIR domain despite not having access to the target NIR data. Additionally, we report state-of-the-art results for adaption from Synthia to Cityscapes which is a popular setting in Unsupervised Domain Adaptation for semantic segmentation. The code and datasets are available at https://github.com/ambekarsameer96/GLSS."

Existing approaches for unsupervised metric learning focus on exploring self-supervision information within the input image itself. We observe that, when analyzing images, human eyes often compare images against each other instead of examining images individually. In addition, they often pay attention to certain keypoints, image regions, or objects which are discriminative between image classes but highly consistent within classes. Even if the image is being transformed, the attention pattern will be consistent. Motivated by this observation, we develop a new approach to unsupervised deep metric learning where the network is learned based on self-supervision information across images instead of within one single image. To characterize the consistent pattern of human attention during image comparisons, we introduce the idea of transformed attention consistency. It assumes that visually similar images, even undergoing different image transforms, should share the same consistent visual attention map. This consistency leads to a pairwise self-supervision loss, allowing us to learn a Siamese deep neural network to encode and compare images against their transformed or matched pairs. To further enhance the inter-class discriminative power of the feature generated by this network, we adapt the concept of triplet loss from supervised metric learning to our unsupervised case and introduce the contrastive clustering loss. Our extensive experimental results on benchmark datasets demonstrate that our proposed method outperforms current state-of-the-art methods for unsupervised metric learning by a large margin."

We present a deployment friendly, fast bottom-up framework for multi-person 3D human pose estimation. We adopt a novel neural representation of multi-person 3D pose which unifies the position of person instances with their corresponding 3D pose representation. This is realized by learning a generative pose embedding which not only ensures plausible 3D pose predictions, but also eliminates the usual keypoint grouping operation as employed in prior bottom-up approaches. Further, we propose a practical deployment paradigm where paired 2D or 3D pose annotations are unavailable. In the absence of any paired supervision, we leverage a frozen network, as a teacher model, which is trained on an auxiliary task of multi-person 2D pose estimation. We cast the learning as a cross-modal alignment problem and propose training objectives to realize a shared latent space between two diverse modalities. We aim to enhance the model's ability to perform beyond the limiting teacher network by enriching the latent-to-3D pose mapping using artificially synthesized multi-person 3D scene samples. Our approach not only generalizes to in-the-wild images, but also yields a superior trade-off between speed and performance, compared to prior top-down approaches. Our approach also yields state-of-the-art multi-person 3D pose estimation performance among the bottom-up approaches under consistent supervision levels."

Learning a good 3D human pose representation is important for human pose related tasks, e.g. human 3D pose estimation and action recognition. Within all these problems, preserving the intrinsic pose information and adapting to view variations are two critical issues. In this work, we propose a novel Siamese denoising autoencoder to learn a 3D pose representation by disentangling the pose-dependent and view-dependent feature from the human skeleton data, in a fully unsupervised manner. These two disentangled features are utilized together as the representation of the 3D pose. To consider both the kinematic and geometric dependencies, a sequential bidirectional recursive network (SeBiReNet) is further proposed to model the human skeleton data. Extensive experiments demonstrate that the learned representation 1) preserves the intrinsic information of human pose, 2) shows good transferability across datasets and tasks. Notably, our approach achieves state-of-the-art performance on two inherently different tasks: pose denoising and unsupervised action recognition. Code and models are available at: https://github.com/NIEQiang001/unsupervised-human-pose.git."

Due to the ubiquity of smartphones, it is popular to take photos of one's self, or ""selfies."" Such photos are convenient to take, because they do not require specialized equipment or a third-party photographer. However, in selfies, constraints such as human arm length often make the body pose look unnatural. To address this issue, we introduce unselfie, a novel photographic transformation that automatically translates a selfie into a neutral-pose portrait. To achieve this, we first collect an unpaired dataset, and introduce a way to synthesize paired training data for self-supervised learning. Then, to unselfie a photo, we propose a new three-stage pipeline, where we first find a target neutral pose, inpaint the body texture, and finally refine and composite the person on the background. To obtain a suitable target neutral pose, we propose a novel nearest pose search module that makes the reposing task easier and enables the generation of multiple neural-pose results among which users can choose the best one they like. Qualitative and quantitative evaluations show the superiority of our pipeline over alternatives."

We investigate the task of learning blind image denoising networks from an unpaired set of clean and noisy images. Such problem setting generally is practical and valuable considering that it is feasible to collect unpaired noisy and clean images in most real-world applications. And we further assume that the noise can be signal dependent but is spatially uncorrelated. In order to facilitate unpaired learning of denoising network, this paper presents a two-stage scheme by incorporating self-supervised learning and knowledge distillation. For self-supervised learning, we suggest a dilated blind-spot network (D-BSN) to learn denoising solely from real noisy images. Due to the spatial independence of noise, we adopt a network by stacking $1 imes1$ convolution layers to estimate the noise level map for each image. Both the D-BSN and image-specific noise model ($ ext{CNN}_{ ext{est}}$) can be jointly trained via maximizing the constrained log-likelihood. Given the output of D-BSN and estimated noise level map, improved denoising performance can be further obtained based on the Bayes' rule. As for knowledge distillation, we first apply the learned noise models to clean images to synthesize a paired set of training images, and use the real noisy images and the corresponding denoising results in the first stage to form another paired set. Then, the ultimate denoising model can be distilled by training an existing denoising network using these two paired sets. Experiments show that our unpaired learning method performs favorably on both synthetic noisy images and real-world noisy photographs in terms of quantitative and qualitative evaluation. Code is available at \url{https://github.com/XHWXD/DBSN}."

Unpaired image-to-image translation is a class of vision problems whose goal is to find the mapping between different image domains using unpaired training data. Cycle-consistency loss is a widely used constraint for such problems. However, due to the strict pixel-level constraint, it cannot perform geometric changes, remove large objects, or ignore irrelevant texture. In this paper, we propose a novel adversarial-consistency loss for image-to-image translation. This loss does not require the translated image to be translated back to be a specific source image but can encourage the translated images to retain important features of the source images and overcome the drawbacks of cycle-consistency loss noted above. Our method achieves state-of-the-art results on three challenging tasks: glasses removal, male-to-female translation, and selfie-to-anime translation."

Recent advances in deep neural networks have achieved significant progress in detecting individual objects from an image. However, object detection is not sufficient to fully understand a visual scene. Towards a deeper visual understanding, the interactions between objects, especially humans and objects are essential. Most prior works have obtained this information with a bottom-up approach, where the objects are first detected and the interactions are predicted sequentially by pairing the objects. This is a major bottleneck in HOI detection inference time. To tackle this problem, we propose UnionDet, a one-stage meta-architecture for HOI detection powered by a novel union-level detector that eliminates this additional inference stage by directly capturing the region of interaction. Our first, fastest and best performing one-stage detector for human-object interaction shows a significant reduction in interaction prediction time ($4 imes \sim 14 imes$) while outperforming state-of-the-art methods on two public datasets: V-COCO and HICO-DET."