Future prediction, especially in long-range videos, requires reasoning from current and past observations. In this work, we address questions of temporal extent, scaling, and level of semantic abstraction with a flexible multi-granular temporal aggregation framework. We show that it is possible to achieve state of the art in both next action and dense anticipation with simple techniques such as max-pooling and attention. To demonstrate the anticipation capabilities of our model, we conduct experiments on Breakfast, 50Salads, and EPIC-Kitchens datasets, where we achieve state-of-the-art results. With minimal modifications, our model can also be extended for video segmentation and action recognition.
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
已筛选
ECCV 2020
1,358篇论文
第 34 / 68 页
Requirement of large annotated datasets restricts the use of deep convolutional neural networks (CNNs) for many practical applications. The problem can be mitigated by using active learning (AL) techniques which, under a given annotation budget, allow to select a subset of data that yields maximum accuracy upon fine tuning. State of the art AL approaches typically relies on measures of visual diversity or prediction uncertainty, which are unable to effectively capture the variations in the spatial context. On the other hand, modern CNN architectures make heavy use of spatial context for achieving highly accurate predictions. Since the context is difficult to evaluate in the absence of ground-truth labels, we introduce the notion of contextual diversity that captures the confusion associated with spatially co-occurring classes. Contextual Diversity (CD) hinges on a crucial observation that the probability vector predicted by a CNN for a region of interest typically contains information from a larger receptive field. Exploiting this observation, we use the proposed CD measure within two AL frameworks: (1) a core-set based strategy and (2) a reinforcement learning based policy, for the active frame selection. Our extensive empirical evaluation establishes state of the art results for active learning on benchmark datasets of Semantic Segmentation, Object Detection and Image classification. Our ablation studies show clear advantages of using contextual diversity for active learning.
Particle Imaging Velocimetry (PIV) estimates the fluid flow by analyzing the motion of injected particles. The problem is challenging as the particles lie at different depths but have similar appearances. Tracking a large number of moving particles is particularly difficult due to the heavy occlusion. In this paper, we present a PIV solution that uses a compact lenslet-based light field camera to track dense particles floating in the fluid and reconstruct the 3D fluid flow. We exploit the focal symmetry property in the light field focal stacks for recovering the depths of similar-looking particles. We further develop a motion-constrained optical flow estimation algorithm by enforcing the local motion rigidity and the Navier-Stoke fluid constraint. Finally, the estimated particle motion trajectory is used to visualize the 3D fluid flow. Comprehensive experiments on both synthetic and real data show that using a compact light field camera, our technique can recover dense and accurate 3D fluid flow.
Geometric Correspondence Fields: Learned Differentiable Rendering for 3D Pose Refinement in the Wild
PDF ↗We present a novel 3D pose refinement approach based on differentiable rendering for objects of arbitrary categories in the wild. In contrast to previous methods, we make two main contributions: First, instead of comparing real-world images and synthetic renderings in the RGB or mask space, we compare them in a feature space optimized for 3D pose refinement. Second, we introduce a novel differentiable renderer that learns to approximate the rasterization backward pass from data instead of relying on a hand-crafted algorithm. For this purpose, we predict deep cross-domain correspondences between RGB images and 3D model renderings in the form of what we call geometric correspondence fields. These correspondence fields serve as pixel-level gradients which are analytically propagated backward through the rendering pipeline to perform a gradient-based optimization directly on the 3D pose. In this way, we precisely align 3D models to objects in RGB images which results in significantly improved 3D pose estimates. We evaluate our approach on the challenging Pix3D dataset and achieve up to 55% relative improvement compared to state-of-the-art refinement methods in multiple metrics.
Novel vision sensors such as thermal, hyperspectral, polarization, and event cameras provide information that is not available from conventional intensity cameras. An obstacle to using these sensors with current powerful deep neural networks is the lack of large labeled training datasets. This paper proposes a Network Grafting Algorithm (NGA), where a new front end network driven by unconventional visual inputs replaces the front end network of a pretrained deep network that processes intensity frames. The self-supervised training uses only synchronously-recorded intensity frames and novel sensor data to maximize feature similarity between the pretrained network and the grafted network. We show that the enhanced grafted network reaches competitive average precision (AP50) scores to the pretrained network on an object detection task using thermal and event camera datasets, with no increase in inference costs. Particularly, the grafted network driven by thermal frames showed a relative improvement of 49.11% over the use of intensity frames. The grafted front end has only 5--8% of the total parameters and can be trained in a few hours on a single GPU equivalent to 5% of the time that would be needed to train the entire object detector from labeled data. NGA allows new vision sensors to capitalize on previously pretrained powerful deep models, saving on training cost and widening a range of applications for novel sensors.
The existing action tubelet detectors often depend on heuristic anchor design and placement, which might be computationally expensive and sub-optimal for precise localization. In this paper, we present a conceptually simple, computationally efficient, and more precise action tubelet detection framework, termed as MovingCenter Detector (MOC-detector), by treating an action instance as a trajectory of moving points. Based on the insight that movement information could simplify and assist action tubelet detection, our MOC-detector is composed of three crucial head branches: (1) Center Branch for instance center detection and action recognition, (2) Movement Branch for movement estimation at adjacent frames to form trajectories of moving points, (3) Box Branch for spatial extent detection by directly regressing bounding box size at each estimated center. These three branches work together to generate the tubelet detection results, which could be further linked to yield video-level tubes with a matching strategy. Our MOC-detector outperforms the existing state-of-the-art methods for both metrics of frame-mAP and video-mAP on the JHMDB and UCF101-24 datasets. The performance gap is more evident for higher video IoU, demonstrating that our MOC-detector is particularly effective for more precise action detection. We provide the code at https://github.com/MCG-NJU/MOC-Detector .
This work addresses the problems of generalization and flexibility for text recognition in documents. We introduce a new model that exploits the repetitive nature of characters in languages, and decouples the visual decoding and linguistic modelling stages through intermediate representations in the form of similarity maps. By doing this, we turn text recognition into a visual matching problem, thereby achieving generalization in appearance and flexibility in classes. We evaluate the model on both synthetic and real datasets across different languages and alphabets, and show that it can handle challenges that traditional architectures are unable to solve without expensive re-training, including: (i) it can change the number of classes simply by changing the exemplars; and (ii) it can generalize to novel languages and characters (not in the training data) simply by providing a new glyph exemplar set. In essence, it is able to carry out one-shot sequence recognition. We also demonstrate that the model can generalize to unseen fonts without requiring new exemplars from them.
Object Permanence allows people to reason about the location of non-visible objects, by understanding that they continue to exist even when not perceived directly. Object Permanence is critical for building a model of the world, since objects in natural visual scenes dynamically occlude and contain each-other. Intensive studies in developmental psychology, suggesting that object permanence is a challenging task that is learned through extensive experience.Here we introduce the setup of learning Object Permanence from data. We explain why the learning problem should be dissected into four components, where objects are (1) visible, (2) occluded, (3) contained by another object and (4) carried by a containing object. The fourth subtask, where a target object is carried by a containing object, is particularly challenging because it requires a system to reason about a moving location of an invisible object. We then present a unified deep architecture that learns to predict object location under these four scenarios. We evaluate the architecture and system on a new dataset based on CATER, and find that it outperforms previous methods and various baselines.
Transferring existing image-based detectors to the video is non-trivial since the quality of frames is always deteriorated by part occlusion, rare pose, and motion blur. Previous approaches exploit to propagate and aggregate features across video frames by using optical flow-warping. However, directly applying image-level optical flow onto the high-level features might not establish accurate spatial correspondences. Therefore, a novel module called Learnable Spatio-Temporal Sampling (LSTS) has been proposed to learn semantic-level correspondences among frame features accurately. The sampled locations are first randomly initialized, then updated iteratively to find better spatial correspondences guided by detection supervision progressively. Besides, Sparsely Recursive Feature Updating (SRFU) module and Dense Feature Aggregation (DFA) module are also introduced to model temporal relations and enhance per-frame features, respectively. Without bells and whistles, the proposed method achieves state-of-the-art performance on the ImageNet VID dataset with less computational complexity and real-time speed. Code will be made available.
Partially-Shared Variational Auto-encoders for Unsupervised Domain Adaptation with Target Shift
PDF ↗This paper discusses unsupervised domain adaptation (UDA) with target shift, i.e., UDA with the non-identical label distributions of the source and target domains. In practice, this is an important problem; as we do not know labels in target domain datasets, we do not know whether or not its distribution is identical to that in the source domain dataset. Despite the inaccessibility to the shape of label distribution in the target domain, a common approach of modern UDA methods reduces the gap between the feature distributions of source and target domains, which implicitly assumes that the label distributions are identical, resulting in an unsatisfactory performance upon target shift. To overcome this problem, the proposed method, partially shared variational autoencoders (PS-VAEs), uses a pair-wise feature alignment instead of feature distribution matching. PS-VAEs inter-convert domain of each sample by a CycleGAN-based architecture while preserving its label-related content by sharing weights of two domain conversion branches as much as possible. To evaluate the performance of PS-VAEs, we carried out two experiments: UDA from synthesized data to real observation in human-pose estimation (regression) and UDA under controlled target shift intensities with digits datasets (classification). The proposed method outperformed the other methods in the regression task with a large margin while presenting its robustness with various levels of target shift.
We present a conceptually simple, flexible and effective framework for weight generating networks. Our approach is general that unifies two current distinct and extremely effective SENet and CondConv into the same framework on weight space. The method, called WeightNet, generalizes the two methods by simply adding one more grouped fully-connected layer to the attention activation layer. We use the WeightNet, composed entirely of (grouped) fully-connected layers, to directly output the convolutional weight. WeightNet is easy and memory-conserving to train, on the kernel space instead of the feature space. Because of the flexibility, our method outperforms existing approaches on both ImageNet and COCO detection tasks, achieving better Accuracy-FLOPs and Accuracy-Parameter trade-offs. The framework on the flexible weight space has the potential to further improve the performance.
After observing that the features used in most online discriminatively trained trackers are not optimal, in this paper, we propose a novel and effective architecture to learn optimal feature embeddings for online discriminative tracking. Our method, called DCFST, integrates the solver of a discriminant model that is differentiable and has a closed-form solution into convolutional neural networks. Then, the resulting network can be trained in an end-to-end way, obtaining optimal feature embeddings for the discriminant model-based tracker. As an instance, we apply the popular ridge regression model in this work to demonstrate the power of DCFST. Extensive experiments on six public benchmarks, OTB2015, NFS, GOT10k, TrackingNet, VOT2018, and VOT2019, show that our approach is efficient and generalizes well to class-agnostic target objects in online tracking, thus achieves state-of-the-art accuracy, while running beyond the real-time speed. Code will be made available.
Although deep learning techniques have largely improved face recognition, unconstrained surveillance face recognition (FR) is still an unsolved challenge, due to the limited training data and the gap of domain distribution. Previous methods mostly match low-resolution and high-resolution faces in different domains, which tend to deteriorate the original feature space in the common recognition scenarios. To avoid this problem, we propose a novel resolution adaption network (RAN) which contains Multi-Resolution Generative Adversarial Networks (MR-GAN) followed by a feature adaption network. MR-GAN learns multi-resolution representations and randomly selects one resolution to generate realistic low-resolution (LR) faces that can avoid the artifacts of down-sampled faces. A novel feature adaption network with translation gate is developed to fuse the discriminative information of the generated LR faces into backbone network, while preserving the discrimination ability of original face representations. The experimental results on IJB-C TinyFace, SCface, QMUL-SurvFace datasets have demonstrated the superiority of our proposed method compared with state-of-the-art surveillance face recognition methods, while showing stable performance on the common recognition scenarios.
Modern methods for counting people in crowded scenes rely on deep networks to estimate people densities in individual images. As such, only very few take advantage of temporal consistency in video sequences, and those that do only impose weak smoothness constraints across consecutive frames. In this paper, we advocate estimating people flows across image locations between consecutive images and inferring the people densities from these flows instead of directly regressing. This enables us to impose much stronger constraints encoding the conservation of the number of people. As a result, it significantly boosts performance without requiring a more complex architecture. Furthermore, it also enables us to exploit the correlation between people flow and optical flow to further improve the results. We will demonstrate that we consistently outperform state-of-the-art methods on five benchmark datasets.
Recent advances in unsupervised domain adaptation for semantic segmentation have shown great potentials to relieve the demand of expensive per-pixel annotations. However, most existing works address the domain discrepancy by aligning the data distributions of two domains at a global image level whereas the local consistencies are largely neglected. This paper presents an innovative local contextual-relation consistent domain adaptation (CrCDA) technique that aims to achieve local-level consistencies during the global-level alignment. The idea is to take a closer look at region-wise feature representations and align them for local-level consistencies. Specifically, CrCDA learns and enforces the prototypical local contextual-relations explicitly in the feature space of a labelled source domain while transferring them to an unlabelled target domain via backpropagation-based adversarial learning. An adaptive entropy max-min adversarial learning scheme is designed to optimally align these hundreds of local contextual-relations across domain without requiring discriminator or extra computation overhead. The proposed CrCDA has been evaluated extensively over two challenging domain adaptive segmentation tasks (e.g., GTA5 to Cityscapes and SYNTHIA to Cityscapes), and experiments demonstrate its superior segmentation performance as compared with state-of-the-art methods.
We address the curve lane detection problem which poses more real-world challenges than conventional lane detection for better facilitating modern assisted/autonomous driving systems. Current hand-designed lane detection methods are not robust enough to capture the curve lanes especially the remote ones due to the lack of modeling both long-range contextual information and detailed curve trajectory. In this paper, we propose a novel lane-sensitive architecture search framework named CurveLane-NAS to automatically capture both long-ranged coherent and accurate short-range curve information while unifying both architecture search and post-processing on curve lane predictions via point blending. It consists of three search modules: a) a feature fusion search module to find a better fusion of the local and global context for multi-level hierarchy features; b) an elastic backbone search module to explore an efficient feature extractor with good semantics and latency; c) an adaptive point blending module to search a multi-level post-processing refinement strategy to combine multi-level head prediction. The unified framework ensures lane-sensitive predictions by the mutual guidance between NAS and adaptive point blending. Furthermore, we also steer forward to release a more challenging benchmark named CurveLanes for addressing the most difficult curve lanes. It consists of 150K images with 680K labels. Experiments on the new CurveLanes show that the SOTA lane detection methods suffer substantial performance drop while our model can still reach an 80+% F1-score. Extensive experiments on traditional lane benchmarks such as CULane also demonstrate the superiority of our CurveLane-NAS, e.g. achieving a new SOTA result 74.8% of F1-score on CULane dataset.
We introduce OmniSource, a novel framework for leveraging web data to train video recognition models. OmniSource overcomes the barriers between data formats, such as images, short videos, and long untrimmed videos for webly-supervised learning. First, data samples with multiple formats, curated by task-specific data collection and automatically filtered by a teacher model, are transformed into a unified form. Then a joint-training strategy is proposed to deal with the domain gaps between multiple data sources and formats in webly-supervised learning. Several good practices, including data balancing, resampling, and cross-dataset mixup are adopted in joint training. Experiments show that by utilizing data from multiple sources and formats, OmniSource is more data-efficient in training. With only 3.5M images and 800K minutes videos crawled from the internet without human labeling (less than 2% of prior works), our models learned with OmniSource improve Top-1 accuracy of 2D- and 3D-ConvNet baseline models by 3.0% and 3.9%, respectively, on the Kinetics-400 benchmark. With OmniSource, we establish new records with different pretraining strategies for video recognition. Our best models achieve 80.4%, 80.5%, and 83.6% Top-1 accuracies on the Kinetics-400 benchmark respectively for training-from-scratch, ImageNet pre-training and IG-65M pre-training.
The remarkable performance of convolutional neural networks (CNNs) is entangled with their huge number of uninterpretable parameters, which has become the bottleneck limiting the exploitation of their full potential. Towards network interpretation, previous endeavors mainly resort to the single filter analysis, which however ignores the relationship between filters. In this paper, we propose a novel architecture decoupling method to interpret the network from a perspective of investigating its calculation paths. More specifically, we introduce a novel architecture controlling module in each layer to encode the network architecture by a vector. By maximizing the mutual information between the vectors and input images, the module is trained to select specific filters to distill a unique calculation path for each input. Furthermore, to improve the interpretability and compactness of the decoupled network, the output of each layer is encoded to align the architecture encoding vector with the constraint of sparsity regularization. Unlike conventional pixel-level or filter-level network interpretation methods, we propose a path-level analysis to explore the relationship between the combination of filter and semantic concepts, which is more suitable to interpret the working rationale of the network. Extensive experiments show that the decoupled network achieves several applications, i.e., network interpretation, network acceleration, and adversarial samples detection.
In this paper, we consider the task of one-shot object detection, which consists in detecting objects defined by a single demonstration. Differently from the standard object detection, the classes of objects used for training and testing do not overlap. We build the one-stage system that performs localization and recognition jointly. We use dense correlation matching of learned local features to find correspondences, a feed-forward geometric transformation model to align features and bilinear resampling of the correlation tensor to compute the detection score of the aligned features. All the components are differentiable, which allows end-to-end training. Experimental evaluation on several challenging domains (retail products, 3D objects, buildings and logos) shows that our method can detect unseen classes (e.g., toothpaste when trained on groceries) and outperforms several baselines by a significant margin. Our code is available online: https://github.com/aosokin/os2d
Weakly supervised object localization (WSOL) is a task of localizing an object in an image only using image-level labels. To tackle the WSOL problem, most previous studies have followed the conventional class activation mapping (CAM) pipeline: (i) training CNNs for a classification objective, (ii) generating a class activation map via global average pooling (GAP) on feature maps, and (iii) extracting bounding boxes by thresholding based on the maximum value of the class activation map. In this work, we reveal the current CAM approach suffers from three fundamental issues: (i) the bias of GAP that assigns a higher weight to a channel with a small activation area, (ii) negatively weighted activations inside the object regions and (iii) instability from the use of the maximum value of a class activation map as a thresholding reference. They collectively cause the problem that the localization to be highly limited to small regions of an object. We propose three simple but robust techniques that alleviate the problems, including thresholded average pooling, negative weight clamping, and percentile as a standard for thresholding. Our solutions are universally applicable to any WSOL methods using CAM and improve their performance drastically. As a result, we achieve the new state-of-the-art performance on three benchmark datasets of CUB-200-2011, ImageNet-1K, and OpenImages30K.