In this paper, we introduce a novel self-supervised visual representation learning method which understands both images and videos in a joint learning fashion. The proposed neural network architecture and objectives are designed to obtain two different Convolutional Neural Networks for solving visual recognition tasks in the domain of videos and images. Our method called Video/Image for Visual Contrastive Learning of Representation(Vi2CLR) uses unlabeled videos to exploit dynamic and static visual cues for self-supervised and instances similarity/dissimilarity learning. Vi2CLR optimization pipeline consists of visual clustering part and representation learning based on groups of similar positive instances within a cluster and negative ones from other clusters and learning visual clusters and their distances. We show how a joint self-supervised visual clustering and instance similarity learning with 2D (image) and 3D (video) CovNet encoders yields such robust and near to supervised learning performance. We extensively evaluate the method on downstream tasks like large scale action recognition and image and object classification on datasets like Kinetics, ImageNet, Pascal VOC'07 and UCF101 and achieve outstanding results compared to state-of-the-art self-supervised methods. To the best of our knowledge, the Vi2CLR is the first of its kind self-supervised neural network to tackle both video and image recognition task simultaneously by only using one source of data.
论文检索
输入标题、作者或关键词，从 1,612 篇学术成果中精准定位
Multi-object tracking and segmentation (MOTS) is important for understanding dynamic scenes in video data. Existing methods perform well on multi-object detection and segmentation for independent video frames, but tracking of objects over time remains a challenge. MOTS methods formulate tracking locally, i.e., frame-by-frame, leading to sub-optimal results. Classical global methods on tracking operate directly on object detections, which leads to a combinatorial growth in the detection space. In contrast, we formulate a global method for MOTS over the space of assignments rather than detections: First, we find all top-k assignments of objects detected and segmented between any two consecutive frames and develop a structured prediction formulation to score assignment sequences across any number of consecutive frames. We use dynamic programming to find the global optimizer of this formulation in polynomial time. Second, we connect objects which reappear after having been out of view for some time. For this we formulate an assignment problem. On the challenging KITTI-MOTS and MOTSChallenge datasets, this achieves state-of-the-art results among methods which don't use depth data.
We present a method, Neural Radiance Flow (NeRFlow), to learn a 4D spatial-temporal representation of a dynamic scene from a set of RGB images. Key to our approach is the use of a neural implicit representation that learns to capture the 3D occupancy, radiance, and dynamics of the scene. By enforcing consistency across different modalities, our representation enables multi-view rendering in diverse dynamic scenes, including water pouring, robotic interaction, and real images, outperforming state-of-the-art methods for spatial-temporal view synthesis. Our approach works even when being provided only a single monocular real video. We further demonstrate that the learned representation can serve as an implicit scene prior, enabling video processing tasks such as image super-resolution and de-noising without any additional supervision.
How would a static scene react to a local poke? What are the effects on other parts of an object if you could locally push it? There will be distinctive movement, despite evident variations caused by the stochastic nature of our world. These outcomes are governed by the characteristic kinematics of objects that dictate their overall motion caused by a local interaction. Conversely, the movement of an object provides crucial information about its underlying distinctive kinematics and the interdependencies between its parts. This two-way relation motivates learning a bijective mapping between object kinematics and plausible future image sequences. Therefore, we propose iPOKE -- invertible Prediction of Object Kinematics -- that, conditioned on an initial frame and a local poke, allows to sample object kinematics and establishes a one-to-one correspondence to the corresponding plausible videos, thereby providing a controlled stochastic video synthesis. In contrast to previous works, we do not generate arbitrary realistic videos, but provide efficient control of movements, while still capturing the stochastic nature of our environment and the diversity of plausible outcomes it entails. Moreover, our approach can transfer kinematics onto novel object instances and is not confined to particular object classes. Our project page is available at https://bit.ly/3dJN4Lf.
When capturing panoramas, people tend to align their cameras with the vertical axis, i.e., the direction of gravity. Moreover, modern devices, e.g. smartphones and tablets, are equipped with an IMU (Inertial Measurement Unit) that can measure the gravity vector accurately. Using this prior, the y-axes of the cameras can be aligned or assumed to be already aligned, reducing the relative orientation to 1-DOF (degree of freedom). Exploiting this assumption, we propose new minimal solutions to panoramic stitching of images taken by cameras with coinciding optical centers, i.e. undergoing pure rotation. We consider six practical camera configurations, from fully calibrated ones up to a camera with unknown fixed or varying focal length and with or without radial distortion. The solvers are tested both on synthetic scenes, on more than 500k real image pairs from the Sun360 dataset, and from scenes captured by us using two smartphones equipped with IMUs. The new solvers have similar or better accuracy than the state-of-the-art ones and outperform them in terms of processing time.
Can a user create a deep generative model by sketching a single example? Traditionally, creating a GAN model has required the collection of a large-scale dataset of exemplars and specialized knowledge in deep learning. In contrast, sketching is possibly the most universally accessible way to convey a visual concept. In this work, we present a method, GAN Sketching, for rewriting GANs with one or more sketches, to make GANs training easier for novice users. In particular, we change the weights of an original GAN model according to user sketches. We encourage the model's output to match the user sketches through a cross-domain adversarial loss. Furthermore, we explore different regularization methods to preserve the original model's diversity and image quality. Experiments have shown that our method can mold GANs to match shapes and poses specified by sketches while maintaining realism and diversity. Finally, we demonstrate a few applications of the resulting GAN, including latent space interpolation and image editing.
We explore the zero-shot setting for day-night domain adaptation. The traditional domain adaptation setting is to train on one domain and adapt to the target domain by exploiting unlabeled data samples from the test set. As gathering relevant test data is expensive and sometimes even impossible, we do not rely on test data and instead exploit a visual inductive prior derived from physics-based reflection models for domain adaptation. We cast a number of color invariant edge detectors as trainable layers in a convolutional neural network and evaluate their robustness to illumination changes. We show that the color invariant layer reduces the day-night distribution shift in feature map activations throughout the network. We demonstrate improved performance for zero-shot day to night domain adaptation on both synthetic as well as natural datasets in various tasks, including classification, segmentation and place recognition.
Exploiting convolutional neural networks for point cloud processing is quite challenging, due to the inherent irregular distribution and discrete shape representation of point clouds. To address these problems, many handcrafted convolution variants have sprung up in recent years. Though with elaborate design, these variants could be far from optimal in sufficiently capturing diverse shapes formed by discrete points. In this paper, we propose PointSeaConv, i.e., a novel differential convolution search paradigm on point clouds. It can work in a purely data-driven manner and thus is capable of auto-creating a group of suitable convolutions for geometric shape modeling. We also propose a joint optimization framework for simultaneous search of internal convolution and external architecture, and introduce epsilon-greedy algorithm to alleviate the effect of discretization error. As a result, PointSeaNet, a deep network that is sufficient to capture geometric shapes at both convolution level and architecture level, can be searched out for point cloud processing. Extensive experiments strongly evidence that our proposed PointSeaNet surpasses current handcrafted deep models on challenging benchmarks across multiple tasks with remarkable margins.
In recent years, research on adversarial attacks has become a hot spot. Although current literature on the transfer-based adversarial attack has achieved promising results for improving the transferability to unseen black-box models, it still leaves a long way to go. Inspired by the idea of meta-learning, this paper proposes a novel architecture called Meta Gradient Adversarial Attack (MGAA), which is plug-and-play and can be integrated with any existing gradient-based attack method for improving the cross-model transferability. Specifically, we randomly sample multiple models from a model zoo to compose different tasks and iteratively simulate a white-box attack and a black-box attack in each task. By narrowing the gap between the gradient directions in white-box and black-box attacks, the transferability of adversarial examples on the black-box setting can be improved. Extensive experiments on the CIFAR10 and ImageNet datasets show that our architecture outperforms the state-of-the-art methods for both black-box and white-box attack settings.
The conventional detectors tend to make imbalanced classification and suffer performance drop, when the distribution of the training data is severely skewed. In this paper, we propose to use the mean classification score to indicate the classification accuracy for each category during training. Based on this indicator, we balance the classification via an Equilibrium Loss (EBL) and a Memory-augmented Feature Sampling (MFS) method. Specifically, EBL increases the intensity of the adjustment of the decision boundary for the weak classes by a designed score-guided loss margin between any two classes. On the other hand, MFS improves the frequency and accuracy of the adjustments of the decision boundary for the weak classes through over-sampling the instance features of those classes. Therefore, EBL and MFS work collaboratively for finding the classification equilibrium in long-tailed detection, and dramatically improve the performance of tail classes while maintaining or even improving the performance of head classes. We conduct experiments on LVIS using Mask R-CNN with various backbones including ResNet-50-FPN and ResNet-101-FPN to show the superiority of the proposed method. It improves the detection performance of tail classes by 15.6 AP, and outperforms the most recent long-tailed object detectors by more than 1 AP. Code is available at https://github.com/fcjian/LOCE.
Transferability of adversarial examples is of central importance for attacking an unknown model, which facilitates adversarial attacks in more practical scenarios, e.g., blackbox attacks. Existing transferable attacks tend to craft adversarial examples by indiscriminately distorting features to degrade prediction accuracy in a source model without aware of intrinsic features of objects in the images. We argue that such brute-force degradation would introduce model-specific local optimum into adversarial examples, thus limiting the transferability. By contrast, we propose the Feature Importance-aware Attack (FIA), which disrupts important object-aware features that dominate model decisions consistently. More specifically, we obtain feature importance by introducing the aggregate gradient, which averages the gradients with respect to feature maps of the source model, computed on a batch of random transforms of the original clean image. The gradients will be highly correlated to objects of interest, and such correlation presents invariance across different models. Besides, the random transforms will preserve intrinsic features of objects and suppress model-specific information. Finally, the feature importance guides to search for adversarial examples towards disrupting critical features, achieving stronger transferability. Extensive experimental evaluation demonstrates the effectiveness and superior performance of the proposed FIA, i.e., improving the success rate by 9.5% against normally trained models and 12.8% against defense models as compared to the state-of-the-art transferable attacks. Code is available at: https://github.com/hcguoO0/FIA
Self-Supervised 3D Skeleton Action Representation Learning With Motion Consistency and Continuity
PDF ↗Recently, self-supervised learning (SSL) has been proved very effective and it can help boost the performance in learning representations from unlabeled data in the image domain. Yet, very little is explored about its usefulness in 3D skeleton-based action recognition understanding. Directly applying existing SSL techniques for 3D skeleton learning, however, suffers from trivial solutions and imprecise representations. To tackle these drawbacks, we consider perceiving the consistency and continuity of motion at different playback speeds are two critical issues. To this end, we propose a novel SSL method to learn the 3D skeleton representation in an efficacious way. Specifically, by constructing a positive clip (speed-changed) and a negative clip (motion-broken) of the sampled action sequence, we encourage the positive pairs closer while pushing the negative pairs to force the network to learn the intrinsic dynamic motion consistency information. Moreover, to enhance the learning features, skeleton interpolation is further exploited to model the continuity of human skeleton data. To validate the effectiveness of the proposed method, extensive experiments are conducted on Kinetics, NTU60, NTU120, and PKUMMD datasets with several alternative network architectures. Experimental evaluations demonstrate the superiority of our approach and through which, we can gain significant performance improvement without using extra labeled data.
Learning from noisy data has attracted much attention, where most methods focus on label noise. In this work, we propose a new learning framework which simultaneously addresses three types of noise commonly seen in real-world data: label noise, out-of-distribution input, and input corruption. In contrast to most existing methods, we combat noise by learning robust representation. Specifically, we embed images into a low-dimensional subspace, and regularize the geometric structure of the subspace with robust contrastive learning, which includes an unsupervised consistency loss and a supervised mixup prototypical loss. We also propose a new noise cleaning method which leverages the learned representation to enforce a smoothness constraint on neighboring samples. Experiments on multiple benchmarks demonstrate state-of-the-art performance of our method and robustness of the learned representation. Code is available at https://github.com/salesforce/RRL/.
Panoptic segmentation as an integrated task of both static environmental understanding and dynamic object identification, has recently begun to receive broad research interest. In this paper, we propose a new computationally efficient LiDAR based panoptic segmentation framework, called GP-S3Net. GP-S3Net is a proposal-free approach in which no object proposals are needed to identify the objects in contrast to conventional two-stage panoptic systems, where a detection network is incorporated for capturing instance information. Our new design consists of a novel instance-level network to process the semantic results by constructing a graph convolutional network to identify objects (foreground), which later on are fused with the background classes. Through the fine-grained clusters of the foreground objects from the semantic segmentation backbone, over-segmentation priors are generated and subsequently processed by 3D sparse convolution to embed each cluster. Each cluster is treated as a node in the graph and its corresponding embedding is used as its node feature. Then a GCNN predicts whether edges exist between each cluster pair. We utilize the instance label to generate ground truth edge labels for each constructed graph in order to supervise the learning. Extensive experiments demonstrate that GP-S3Net outperforms the current state-of-the-art approaches, by a significant margin across available datasets such as, nuScenes and SemanticPOSS, ranking first on the competitive public SemanticKITTI leaderboard upon publication.
Synthetic data is emerging as a promising solution to the scalability issue of supervised deep learning, especially when real data are difficult to acquire or hard to annotate. Synthetic data generation, however, can itself be prohibitively expensive when domain experts have to manually and painstakingly oversee the process. Moreover, neural networks trained on synthetic data often do not perform well on real data because of the domain gap. To solve these challenges, we propose Sim2SG, a self-supervised automatic scene generation technique for matching the distribution of real data. Importantly, Sim2SG does not require supervision from the real-world dataset, thus making it applicable in situations for which such annotations are difficult to obtain. Sim2SG is designed to bridge both the content and appearance gaps, by matching the content of real data, and by matching the features in the source and target domains. We select scene graph (SG) generation as the downstream task, due to the limited availability of labeled datasets. Experiments demonstrate significant improvements over leading baselines in reducing the domain gap both qualitatively and quantitatively, on several synthetic datasets as well as the real-world KITTI dataset.
We extend the task of composed image retrieval, where an input query consists of an image and short textual description of how to modify the image. Existing methods have only been applied to non-complex images within narrow domains, such as fashion products, thereby limiting the scope of study on in-depth visual reasoning in rich image and language contexts. To address this issue, we collect the Compose Image Retrieval on Real-life images (CIRR) dataset, which consists of over 36,000 pairs of crowd-sourced, open-domain images with human-generated modifying text. To extend current methods to the open-domain, we propose CIRPLANT, a transformer based model that leverages rich pre-trained vision-and-language (V&L) knowledge for modifying visual features conditioned on natural language. Retrieval is then done by nearest neighbor lookup on the modified features. We demonstrate that with a relatively simple architecture, CIRPLANT outperforms existing methods on open-domain images, while matching state-of-the-art accuracy on the existing narrow datasets, such as fashion. Together with the release of CIRR, we believe this work will inspire further research on composed image retrieval. Our dataset, code and pre-trained models are available at https://cuberick-orion.github.io/CIRR/.
Recent works have made great success in semantic segmentation by exploiting contextual information in a local or global manner within individual image and supervising the model with pixel-wise cross entropy loss. However, from the holistic view of the whole dataset, semantic relations not only exist inside one single image, but also prevail in the whole training data, which makes solely considering intra-image correlations insufficient. Inspired by recent progress in unsupervised contrastive learning, we propose the region-aware contrastive learning (RegionContrast) for semantic segmentation in the supervised manner. In order to enhance the similarity of semantically similar pixels while keeping the discrimination from others, we employ contrastive learning to realize this objective. With the help of memory bank, we explore to store all the representative features into the memory. Without loss of generality, to efficiently incorporate all training data into the memory bank while avoiding taking too much computation resource, we propose to construct region centers to represent features from different categories for every image. Hence, the proposed region-aware contrastive learning is performed in a region level for all the training data, which saves much more memory than methods exploring the pixel-level relations. The proposed RegionContrast brings little computation cost during training and requires no extra overhead for testing. Extensive experiments demonstrate that our method achieves state-of-the-art performance on three benchmark datasets including Cityscapes, ADE20K and COCO Stuff.
Env-QA: A Video Question Answering Benchmark for Comprehensive Understanding of Dynamic Environments
PDF ↗Visual understanding goes well beyond the study of images or videos on the web. To achieve complex tasks in volatile situations, the human can deeply understand the environment, quickly perceive events happening around, and continuously track objects' state changes, which are still challenging for current AI systems. To equip AI system with the ability to understand dynamic ENVironments, we build a video Question Answering dataset named Env-QA. Env-QA contains 23K egocentric videos, where each video is composed of a series of events about exploring and interacting in the environment. It also provides 85K questions to evaluate the ability of understanding the composition, layout, and state changes of the environment presented by the events in videos. Moreover, we propose a video QA model, Temporal Segmentation and Event Attention network (TSEA), which introduces event-level video representation and corresponding attention mechanisms to better extract environment information and answer questions. Comprehensive experiments demonstrate the effectiveness of our framework and show the formidable challenges of Env-QA in terms of long-term state tracking, multi-event temporal reasoning and event counting, etc.
Multi-view pedestrian detection aims to predict a bird's eye view (BEV) occupancy map from multiple camera views. This task is confronted with two challenges: how to establish the 3D correspondences from views to the BEV map and how to assemble occupancy information across views. In this paper, we propose a novel Stacked HOmography Transformations (SHOT) approach, which is motivated by approximating projections in 3D world coordinates via a stack of homographies. We first construct a stack of transformations for projecting views to the ground plane at different height levels. Then we design a soft selection module so that the network learns to predict the likelihood of the stack of transformations. Moreover, we provide an in-depth theoretical analysis on constructing SHOT and how well SHOT approximates projections in 3D world coordinates. SHOT is empirically verified to be capable of estimating accurate correspondences from individual views to the BEV map, leading to new state-of-the-art performance on standard evaluation benchmarks.
Many emerging applications of intelligent robots need to explore and understand new environments, where it is desirable to detect objects of novel categories on the fly with minimum online efforts. This is an object detection on demand (ODOD) task. It is challenging, because it is impossible to annotate large data on the fly, and the embedded systems are usually unable to perform back-propagation which is essential for training. Most existing few-shot detection methods are confronted here as they need extra training. We propose a novel morphable detector (MD), that simply "morphs"" some of its changeable parameters online estimated from the few samples, so as to detect novel categories without any extra training. The MD has two sets of parameters, one for the feature embedding and the other for category representation(called "prototypes""). Each category is associated with a hidden prototype to be learned by integrating the visual and semantic embeddings. The learning of the MD is based on the alternate learning of the feature embedding and the prototypes in an EM-like approach which allows the recovery of an unknown prototype from a few samples of a novel category. Once an MD is learned, it is able to use a few samples of a novel category to directly compute its prototype to fulfill the online morphing process. We have shown the superiority of the MD in Pascal, COCO and FSOD datasets.