A neural radiance field (NeRF) is a scene model supporting high-quality view synthesis, optimized per scene. In this paper, we explore enabling user editing of a category-level NeRF trained on a shape category. Specifically, we propose a method for propagating coarse 2D user scribbles to the 3D space, to modify the color or shape of a local region. First, we propose a conditional radiance field that incorporates new modular network components, including a branch that is shared across object instances in the category. Observing multiple instances of the same category, our model learns underlying part semantics without any supervision, thereby allowing the propagation of coarse 2D user scribbles to the entire 3D region (e.g., chair seat) in a consistent fashion. Next, we investigate for the editing tasks which components of our network require updating. We propose a hybrid network update strategy that targets the later network components, which balances efficiency and accuracy. During user interaction, we formulate an optimization problem that both satisfies the user's constraints and preserves the original object structure. We demonstrate our approach on a variety of editing tasks over three shape datasets and show that it outperforms prior neural editing approaches. Finally, we edit the appearance and shape of a real photograph and show that the edit propagates to extrapolated novel views.
论文检索
输入标题、作者或关键词，从 8,216 篇学术成果中精准定位
3D reconstruction of large scenes is a challenging problem due to the high-complexity nature of the solution space, in particular for generative neural networks. In contrast to traditional generative learned models which encode the full generative process into a neural network and can struggle with maintaining local details at the scene level, we introduce a new method that directly leverages scene geometry from the training database. First, we learn to synthesize an initial estimate for a 3D scene, constructed by retrieving a top-k set of volumetric chunks from the scene database. These candidates are then refined to a final scene generation with an attention-based refinement that can effectively select the most consistent set of geometry from the candidates and combine them together to create an output scene, facilitating transfer of coherent structures and local detail from train scene geometry. We demonstrate our neural scene reconstruction with a database for the tasks of 3D super-resolution and surface reconstruction from sparse point clouds, showing that our approach enables generation of more coherent, accurate 3D scenes, improving on average by over 8% in IoU over state-of-the-art scene reconstruction.
In this work, we address the challenging task of referring segmentation. The query expression in referring segmentation typically indicates the target object by describing its relationship with others. Therefore, to find the target one among all instances in the image, the model must have a holistic understanding of the whole image. To achieve this, we reformulate referring segmentation as a direct attention problem: finding the region in the image where the query language expression is most attended to. We introduce transformer and multi-head attention to build a network with an encoder-decoder attention mechanism architecture that "queries" the given image with the language expression. Furthermore, we propose a Query Generation Module, which produces multiple sets of queries with different attention weights that represent the diversified comprehensions of the language expression from different aspects. At the same time, to find the best way from these diversified comprehensions based on visual clues, we further propose a Query Balance Module to adaptively select the output features of these queries for a better mask generation. Without bells and whistles, our approach is light-weight and achieves new state-of-the-art performance consistently on three referring segmentation datasets, RefCOCO, RefCOCO+, and G-Ref. Our code is available at https://github.com/henghuiding/Vision-Language-Transformer.
Recently, there has been an increasing number of efforts to introduce models capable of generating natural language explanations (NLEs) for their predictions on vision-language (VL) tasks. Such models are appealing, because they can provide human-friendly and comprehensive explanations. However, there is a lack of comparison between existing methods, which is due to a lack of re-usable evaluation frameworks and a scarcity of datasets. In this work, we introduce e-ViL and e-SNLI-VE. e-ViL is a benchmark for explainable vision-language tasks that establishes a unified evaluation framework and provides the first comprehensive comparison of existing approaches that generate NLEs for VL tasks. It spans four models and three datasets and both automatic metrics and human evaluation are used to assess model-generated explanations. e-SNLI-VE is currently the largest existing VL dataset with NLEs (over 430k instances). We also propose a new model that combines UNITER, which learns joint embeddings of images and text, and GPT-2, a pre-trained language model that is well-suited for text generation. It surpasses the previous state of the art by a large margin across all datasets. Code and data are available here: https://github.com/maximek3/e-ViL.
In this paper, we present a novel Dynamic DETR (Detection with Transformers) approach by introducing dynamic attentions into both the encoder and decoder stages of DETR to break its two limitations on small feature resolution and slow training convergence. To address the first limitation, which is due to the quadratic computational complexity of the self-attention module in Transformer encoders, we propose a dynamic encoder to approximate the Transformer encoder's attention mechanism using a convolution-based dynamic encoder with various attention types. Such an encoder can dynamically adjust attentions based on multiple factors such as scale importance, spatial importance, and representation (i.e., feature dimension) importance. To mitigate the second limitation of learning difficulty, we introduce a dynamic decoder by replacing the cross-attention module with a ROI-based dynamic attention in the Transformer decoder. Such a decoder effectively assists Transformers to focus on region of interests from a coarse-to-fine manner and dramatically lowers the learning difficulty, leading to a much faster convergence with fewer training epochs. We conduct a series of experiments to demonstrate our advantages. Our Dynamic DETR significantly reduces the training epochs (by \bf 14x ), yet results in a much better performance (by \bf 3.6 on mAP). Meanwhile, in the standard 1x setup with ResNet-50 backbone, we archive a new state-of-the-art performance that further proves the learning effectiveness of the proposed approach. Code will be released soon.
We present a "learning to learn" approach for discovering white-box classification loss functions that are robust to label noise in the training data. We parameterise a flexible family of loss functions using Taylor polynomials, and apply evolutionary strategies to search for noise-robust losses in this space. To learn re-usable loss functions that can apply to new tasks, our fitness function scores their performance in aggregate across a range of training datasets and architectures. The resulting white-box loss provides a simple and fast "plug-and-play" module that enables effective label-noise-robust learning in diverse downstream tasks, without requiring a special training procedure or network architecture. The efficacy of our loss is demonstrated on a variety of datasets with both synthetic and real label noise, where we compare favourably to prior work.
We present a two-stage pre-training approach that improves the generalization ability of standard single-domain pre-training. While standard pre-training on a single large dataset (such as ImageNet) can provide a good initial representation for transfer learning tasks, this approach may result in biased representations that impact the success of learning with new multi-domain data (e.g., different artistic styles) via methods like domain adaptation. We propose a novel pre-training approach called Cross-Domain Self-supervision (CDS), which directly employs unlabeled multi-domain data for downstream domain transfer tasks. Our approach uses self-supervision not only within a single domain but also across domains. In-domain instance discrimination is used to learn discriminative features on new data in a domain-adaptive manner, while cross-domain matching is used to learn domain-invariant features. We apply our method as a second pre-training step (after ImageNet pre-training), resulting in a significant target accuracy boost to diverse domain transfer tasks compared to standard one-stage pre-training.
Predicting accurate future trajectories of multiple agents is essential for autonomous systems but is challenging due to the complex interaction between agents and the uncertainty in each agent's future behavior. Forecasting multi-agent trajectories requires modeling two key dimensions: (1) time dimension, where we model the influence of past agent states over future states; (2) social dimension, where we model how the state of each agent affects others. Most prior methods model these two dimensions separately, e.g., first using a temporal model to summarize features over time for each agent independently and then modeling the interaction of the summarized features with a social model. This approach is suboptimal since independent feature encoding over either the time or social dimension can result in a loss of information. Instead, we would prefer a method that allows an agent's state at one time to directly affect another agent's state at a future time. To this end, we propose a new Transformer, termed AgentFormer, that simultaneously models the time and social dimensions. The model leverages a sequence representation of multi-agent trajectories by flattening trajectory features across time and agents. Since standard attention operations disregard the agent identity of each element in the sequence, AgentFormer uses a novel agent-aware attention mechanism that preserves agent identities by attending to elements of the same agent differently than elements of other agents. Based on AgentFormer, we propose a stochastic multi-agent trajectory prediction model that can attend to features of any agent at any previous timestep when inferring an agent's future position. The latent intent of all agents is also jointly modeled, allowing the stochasticity in one agent's behavior to affect other agents. Extensive experiments show that our method significantly improves the state of the art on well-established pedestrian and autonomous driving datasets.
Monocular object detection and tracking have improved drastically in recent years, but rely on a key assumption: that objects are visible to the camera. Many offline tracking approaches reason about occluded objects post-hoc, by linking together tracklets after the object re-appears, making use of reidentification (ReID). However, online tracking in embodied robotic agents (such as a self-driving vehicle) fundamentally requires object permanence, which is the ability to reason about occluded objects before they re-appear. In this work, we re-purpose tracking benchmarks and propose new metrics for the task of detecting invisible objects, focusing on the illustrative case of people. We demonstrate that current detection and tracking systems perform dramatically worse on this task. We introduce two key innovations to recover much of this performance drop. We treat occluded object detection in temporal sequences as a short-term forecasting challenge, bringing to bear tools from dynamic sequence prediction. Second, we build dynamic models that explicitly reason in 3D from monocular videos without calibration, using observations produced by monocular depth estimators. To our knowledge, ours is the first work to demonstrate the effectiveness of monocular depth estimation for the task of tracking and detecting occluded objects. Our approach strongly improves by 11.4% over the baseline in ablations and by 5.0% over the state-of-the-art in F1 score.
Deep neural representations of 3D shapes as implicit functions have been shown to produce high fidelity models surpassing the resolution-memory trade-off faced by the explicit representations using meshes and point clouds. However, most such approaches focus on representing closed shapes. Unsigned distance function (UDF) based approaches have been proposed recently as a promising alternative to represent both open and closed shapes. However, since the gradients of UDFs vanish on the surface, it is challenging to estimate local (differential) geometric properties like the normals and tangent planes which are needed for many downstream applications in vision and graphics. There are additional challenges in computing these properties efficiently with a low-memory footprint. This paper presents a novel approach that models such surfaces using a new class of implicit representations called the closest surface-point CSP representation. We show that CSP allows us to represent complex surfaces of any topology (open or closed) with high fidelity. It also allows for accurate and efficient computation of local geometric properties. We further demonstrate that it leads to efficient implementation of downstream algorithms like sphere-tracing for rendering the 3D surface as well as to create explicit mesh-based representations. Extensive experimental evaluation on the ShapeNet dataset validate the above contributions with results surpassing the state-of-the-art. Code and data are available at https://sites.google.com/view/cspnet
We address the problem of generalized zero-shot semantic segmentation (GZS3) predicting pixel-wise semantic labels for seen and unseen classes. Most GZS3 methods adopt a generative approach that synthesizes visual features of unseen classes from corresponding semantic ones (e.g., word2vec) to train novel classifiers for both seen and unseen classes. Although generative methods show decent performance, they have two limitations: (1) the visual features are biased towards seen classes; (2) the classifier should be retrained whenever novel unseen classes appear. We propose a discriminative approach to address these limitations in a unified framework. To this end, we leverage visual and semantic encoders to learn a joint embedding space, where the semantic encoder transforms semantic features to semantic prototypes that act as centers for visual features of corresponding classes. Specifically, we introduce boundary-aware regression (BAR) and semantic consistency (SC) losses to learn discriminative features. Our approach to exploiting the joint embedding space, together with BAR and SC terms, alleviates the seen bias problem. At test time, we avoid the retraining process by exploiting semantic prototypes as a nearest-neighbor (NN) classifier. To further alleviate the bias problem, we also propose an inference technique, dubbed Apollonius calibration (AC), that modulates the decision boundary of the NN classifier to the Apollonius circle adaptively. Experimental results demonstrate the effectiveness of our framework, achieving a new state of the art on standard benchmarks.
The data poisoning attack has raised serious security concerns on the safety of deep neural networks since it can lead to neural backdoor that misclassifies certain inputs crafted by an attacker. In particular, the sample-targeted backdoor attack is a new challenge. It targets at one or a few specific samples, called target samples, to misclassify them to a target class. Without a trigger planted in the backdoor model, the existing backdoor detection schemes fail to detect the sample-targeted backdoor as they depend on reverse-engineering the trigger or strong features of the trigger. In this paper, we propose a novel scheme to detect and mitigate sample-targeted backdoor attacks. We discover and demonstrate a unique property of the sample-targeted backdoor, which forces a boundary change such that small "pockets" are formed around the target sample. Based on this observation, we propose a novel defense mechanism to pinpoint a malicious pocket by "wrapping" them into a tight convex hull in the feature space. We design an effective algorithm to search for such a convex hull and remove the backdoor by fine-tuning the model using the identified malicious samples with the corrected label according to the convex hull. The experiments show that the proposed approach is highly efficient for detecting and mitigating a wide range of sample-targeted backdoor attacks.
Dance With Self-Attention: A New Look of Conditional Random Fields on Anomaly Detection in Videos
PDF ↗This paper proposes a novel weakly supervised approach for anomaly detection, which begins with a relation-aware feature extractor to capture the multi-scale convolutional neural network (CNN) features from a video. Afterwards, self-attention is integrated with conditional random fields (CRFs), the core of the network, to make use of the ability of self-attention in capturing the short-range correlations of the features and the ability of CRFs in learning the inter-dependencies of these features. Such a framework can learn not only the spatio-temporal interactions among the actors which are important for detecting complex movements, but also their short- and long-term dependencies across frames. Also, to deal with both local and non-local relationships of the features, a new variant of self-attention is developed by taking into consideration a set of cliques with different temporal localities. Moreover, a contrastive multi-instance learning scheme is considered to broaden the gap between the normal and abnormal instances, resulting in more accurate abnormal discrimination. Simulations reveal that the new method provides superior performance to the state-of-the-art works on the widespread UCF-Crime and ShanghaiTech datasets.
Contaminants such as dust, dirt and moisture adhering to the camera lens can greatly affect the quality and clarity of the resulting image or video. In this paper, we propose a video restoration method to automatically remove these contaminants and produce a clean video. Our approach first seeks to detect attention maps that indicate the regions that need to be restored. In order to leverage the corresponding clean pixels from adjacent frames, we propose a flow completion module to hallucinate the flow of the background scene to the attention regions degraded by the contaminants. Guided by the attention maps and completed flows, we propose a recurrent technique to restore the input frame by fetching clean pixels from adjacent frames. Finally, a multi-frame processing stage is used to further process the entire video sequence in order to enforce temporal consistency. The entire network is trained on a synthetic dataset that approximates the physical lighting properties of contaminant artifacts. This new dataset and our novel framework lead to our method that is able to address different contaminants and outperforms competitive restoration approaches both qualitatively and quantitatively.
Today's state-of-the-art methods for 3D object detection are based on lidar, stereo, or monocular cameras. Lidar-based methods achieve the best accuracy, but have a large footprint, high cost, and mechanically-limited angular sampling rates, resulting in low spatial resolution at long ranges. Recent approaches using low-cost monocular or stereo cameras promise to overcome these limitations but struggle in low-light or low-contrast regions as they rely on passive CMOS sensors. We propose a novel 3D object detection modality that exploits temporal illumination cues from a low-cost monocular gated imager. We introduce a novel deep detection architecture, Gated3D, that is tailored to temporal illumination cues in gated images. This modality allows us to exploit mature 2D object feature extractors that guide the 3D predictions through a frustum segment estimation. We assess the proposed method experimentally on a 3D detection dataset that includes gated images captured over 10,000 km of driving data. We validate that our method outperforms state-of-the-art monocular and stereo methods, opening up a new sensor modality as an avenue to replace lidar in autonomous driving. https://light.princeton.edu/gated3d
This paper presents a new vision Transformer, called Swin Transformer, that capably serves as a general-purpose backbone for computer vision. Challenges in adapting Transformer from language to vision arise from differences between the two domains, such as large variations in the scale of visual entities and the high resolution of pixels in images compared to words in text. To address these differences, we propose a hierarchical Transformer whose representation is computed with Shifted windows. The shifted windowing scheme brings greater efficiency by limiting self-attention computation to non-overlapping local windows while also allowing for cross-window connection. This hierarchical architecture has the flexibility to model at various scales and has linear computational complexity with respect to image size. These qualities of Swin Transformer make it compatible with a broad range of vision tasks, including image classification (87.3 top-1 accuracy on ImageNet-1K) and dense prediction tasks such as object detection (58.7 box AP and 51.1 mask AP on COCO test-dev) and semantic segmentation (53.5 mIoU on ADE20K val). Its performance surpasses the previous state-of-the-art by a large margin of +2.7 box AP and +2.6 mask AP on COCO, and +3.2 mIoU on ADE20K, demonstrating the potential of Transformer-based models as vision backbones. The hierarchical design and the shifted window approach also prove beneficial for all-MLP architectures. The code and models are publicly available at https://github.com/microsoft/Swin-Transformer.
Interaction and navigation defined by natural language instructions in dynamic environments pose significant challenges for neural agents. This paper focuses on addressing two challenges: handling long sequence of subtasks, and understanding complex human instructions. We propose Episodic Transformer (E.T.), a multimodal transformer that encodes language inputs and the full episode history of visual observations and actions. To improve training, we leverage synthetic instructions as an intermediate representation that decouples understanding the visual appearance of an environment from the variations of natural language instructions. We demonstrate that encoding the history with a transformer is critical to solve compositional tasks, and that pretraining and joint training with synthetic instructions further improve the performance. Our approach sets a new state of the art on the challenging ALFRED benchmark, achieving 38.4% and 8.5% task success rates on seen and unseen test splits.
Inspired by the human learning principle that learning easier concepts first and then gradually paying more attention to harder ones, curriculum learning uses the non-uniform sampling of mini-batches according to the order of examples' difficulty. Just as a teacher adjusts the curriculum according to the learning progress of each student, a proper curriculum should be adapted to the current state of the model. Therefore, in contrast to recent works using a fixed curriculum, we devise a new curriculum learning method, Adaptive Curriculum Learning (Adaptive CL), adapting the difficulty of examples to the current state of the model. Specifically, we make use of the loss of the current model to adjust the difficulty score while retaining previous useful learned knowledge by KL divergence. Moreover, under a non-linear model and binary classification, we theoretically prove that the expected convergence rate of curriculum learning monotonically decreases with respect to the loss of a point regarding the optimal hypothesis, and monotonically increases with respect to the loss of a point regarding the current hypothesis. The analyses indicate that Adaptive CL could improve the convergence properties during the early stages of learning. Extensive experimental results demonstrate the superiority of the proposed approach over existing competitive curriculum learning methods.
A large body of recent work has identified transformations in the latent spaces of generative adversarial networks (GANs) that consistently and interpretably transform generated images. But existing techniques for identifying these transformations rely on either a fixed vocabulary of pre-specified visual concepts, or on unsupervised disentanglement techniques whose alignment with human judgments about perceptual salience is unknown. This paper introduces a new method for building open-ended vocabularies of primitive visual concepts represented in a GAN's latent space. Our approach is built from three components: (1) automatic identification of perceptually salient directions based on their layer selectivity; (2) human annotation of these directions with free-form, compositional natural language descriptions; and (3) decomposition of these annotations into a visual concept vocabulary, consisting of distilled directions labeled with single words. Experiments show that concepts learned with our approach are reliable and composable--generalizing across classes, contexts, and observers, and enabling fine-grained manipulation of image style and content.
Annotation burden has become one of the biggest barriers to semantic segmentation. Approaches based on click-level annotations have therefore attracted increasing attention due to their superior trade-off between supervision and annotation cost. In this paper, we propose seminar learning, a new learning paradigm for semantic segmentation with click-level supervision. The fundamental rationale of seminar learning is to leverage the knowledge from different networks to compensate for insufficient information provided in click-level annotations. Mimicking a seminar, our seminar learning involves a teacher-student and a student-student module, where a student can learn from both skillful teachers and other students. The teacher-student module uses a teacher network based on the exponential moving average to guide the training of the student network. In the student-student module, heterogeneous pseudo-labels are proposed to bridge the transfer of knowledge among students to enhance each other's performance. Experimental results demonstrate the effectiveness of seminar learning, which achieves the new state-of-the-art performance of 72.51% (mIOU), surpassing previous methods by a large margin of up to 16.88% on the Pascal VOC 2012 dataset.