Contrastive learning has been widely used to train transformer-based vision-language models for video-text alignment and multi-modal representation learning. This paper presents a new algorithm called Token-Aware Cascade contrastive learning (TACo) that improves contrastive learning using two novel techniques. The first is the token-aware contrastive loss which is computed by taking into account the syntactic classes of words. This is motivated by the observation that for a video-text pair, the content words in the text, such as nouns and verbs, are more likely to be aligned with the visual contents in the video than the function words. Second, a cascade sampling method is applied to generate a small set of hard negative examples for efficient loss estimation for multi-modal fusion layers. To validate the effectiveness of TACo, in our experiments we finetune pretrained models for a set of downstream tasks including text-video retrieval (YouCook2, MSR-VTT and ActivityNet), video action step localization (CrossTask), video action segmentation (COIN). Our results show that our models attain consistent improvements across different experimental settings over previous methods, setting new state-of-the-art on three public text-video retrieval benchmarks of YouCook2, MSR-VTT and ActivityNet.
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
Self-supervised video representation methods typically focus on the representation of temporal attributes in videos. However, the role of stationary versus non-stationary attributes is less explored: Stationary features, which remain similar throughout the video, enable the prediction of video-level action classes. Non-stationary features, which represent temporally varying attributes, are more beneficial for downstream tasks involving more fine-grained temporal understanding, such as action segmentation. We argue that a single representation to capture both types of features is sub-optimal, and propose to decompose the representation space into stationary and non-stationary features via contrastive learning from long and short views, i.e. long video sequences and their shorter sub-sequences. Stationary features are shared between the short and long views, while non-stationary features aggregate the short views to match the corresponding long view. To empirically verify our approach, we demonstrate that our stationary features work particularly well on an action recognition downstream task, while our non-stationary features perform better on action segmentation. Furthermore, we analyse the learned representations and find that stationary features capture more temporally stable, static attributes, while non-stationary features encompass more temporally varying ones.
We consider the problem of filling in missing spatio-temporal regions of a video. We provide a novel flow-based solution by introducing a generative model of images in relation to the scene (without missing regions) and mappings from the scene to images. We use the model to jointly infer the scene template, a 2D representation of the scene, and the mappings. This ensures consistency of the frame-to-frame flows generated to the underlying scene, reducing geometric distortions in flow-based inpainting. The template is mapped to the missing regions in the video by a new (L2-L1) interpolation scheme, creating crisp inpaintings, reducing common blur and distortion artifacts. We show on two benchmark datasets that our approach outperforms state-of-the-art quantitatively and in user studies.
Vector graphic documents present visual elements in a resolution free, compact format and are often seen in creative applications. In this work, we attempt to learn a generative model of vector graphic documents. We define vector graphic documents by a multi-modal set of attributes associated to a canvas and a sequence of visual elements such as shapes, images, or texts, and train variational auto-encoders to learn the representation of the documents. We collect a new dataset of design templates from an online service that features complete document structure including occluded elements. In experiments, we show that our model, named CanvasVAE, constitutes a strong baseline for generative modeling of vector graphic documents.
Though 3D object detection from point clouds has achieved rapid progress in recent years, the lack of flexible and high-performance proposal refinement remains a great hurdle for existing state-of-the-art two-stage detectors. Previous works on refining 3D proposals have relied on human-designed components such as keypoints sampling, set abstraction and multi-scale feature fusion to produce powerful 3D object representations. Such methods, however, have limited ability to capture rich contextual dependencies among points. In this paper, we leverage the high-quality region proposal network and a Channel-wise Transformer architecture to constitute our two-stage 3D object detection framework (CT3D) with minimal hand-crafted design. The proposed CT3D simultaneously performs proposal-aware embedding and channel-wise context aggregation for the point features within each proposal. Specifically, CT3D uses proposal's keypoints for spatial contextual modelling and learns attention propagation in the encoding module, mapping the proposal to point embeddings. Next, a new channel-wise decoding module enriches the query-key interaction via channel-wise re-weighting to effectively merge multi-level contexts, which contributes to more accurate object predictions. Extensive experiments demonstrate that our CT3D method has superior performance and excellent scalability. Remarkably, CT3D achieves the AP of 81.77% in the moderate car category on the KITTI test 3D detection benchmark, outperforms state-of-the-art 3D detectors.
Semantic segmentation is a challenging task in the absence of densely labelled data. Only relying on class activation maps (CAM) with image-level labels provides deficient segmentation supervision. Prior works thus consider pre-trained models to produce coarse saliency maps to guide the generation of pseudo segmentation labels. However, the commonly used off-line heuristic generation process cannot fully exploit the benefits of these coarse saliency maps. Motivated by the significant inter-task correlation, we propose a novel weakly supervised multi-task framework termed as AuxSegNet, to leverage saliency detection and multi-label image classification as auxiliary tasks to improve the primary task of semantic segmentation using only image-level ground-truth labels. Inspired by their similar structured semantics, we also propose to learn a cross-task global pixel-level affinity map from the saliency and segmentation representations. The learned cross-task affinity can be used to refine saliency predictions and propagate CAM maps to provide improved pseudo labels for both tasks. The mutual boost between pseudo label updating and cross-task affinity learning enables iterative improvements on segmentation performance. Extensive experiments demonstrate the effectiveness of the proposed auxiliary learning network structure and the cross-task affinity learning method. The proposed approach achieves state-of-the-art weakly supervised segmentation performance on the challenging PASCAL VOC 2012 and MS COCO benchmarks.
Learning with noisy labels is an important and challenging task for training accurate deep neural networks. However, some commonly-used loss functions, such as Cross Entropy (CE), always suffer from severe overfitting to noisy labels. Although robust loss functions have been designed, they often encounter underfitting. In this paper, we theoretically prove that any loss will be robust to noisy labels when restricting the output of a network to the set of permutations over any fixed vector. When the fixed vector is one-hot, we only need to constrain the output to be one-hot, which means a discrete image and thus zero gradients almost everywhere. This prohibits gradient-based learning of models. In this work, we introduce two sparse regularization strategies to approximate the one-hot constraint: output sharpening and l_p-norm (p\le 1). Output sharpening directly modifies the output distribution of a network to be sharp by adjusting the "temperature" parameter. l_p-norm plays the role of a regularization term to make the output to be sparse. These two simple strategies guarantee the robustness of arbitrary loss functions while not hindering the fitting ability of networks. Experiments on baseline and real-world datasets demonstrate that the sparse regularization can significantly improve the performance of commonly-used loss functions in the presence of noisy labels, and outperform state-of-the-art methods.
Different from traditional video cameras, event cameras capture asynchronous events stream in which each event encodes pixel location, trigger time, and the polarity of the brightness changes. In this paper, we introduce a novel graph-based framework for event cameras, namely SlideGCN. Unlike some recent graph-based methods that use groups of events as input, our approach can efficiently process data event-by-event, unlock the low latency nature of events data while still maintaining the graph's structure internally. For fast graph construction, we develop a radius search algorithm, which better exploits the partial regular structure of event cloud against k-d tree based generic methods. Experiments show that our method reduces the computational complexity up to 100 times with respect to current graph-based methods while keeping state-of-the-art performance on object recognition. Moreover, we verify the superiority of event-wise processing with our method. When the state becomes stable, we can give a prediction with high confidence, thus making an early recognition.
Generating high-fidelity talking head video by fitting with the input audio sequence is a challenging problem that receives considerable attentions recently. In this paper, we address this problem with the aid of neural scene representation networks. Our method is completely different from existing methods that rely on intermediate representations like 2D landmarks or 3D face models to bridge the gap between audio input and video output. Specifically, the feature of input audio signal is directly fed into a conditional implicit function to generate a dynamic neural radiance field, from which a high-fidelity talking-head video corresponding to the audio signal is synthesized using volume rendering. Another advantage of our framework is that not only the head (with hair) region is synthesized as previous methods did, but also the upper body is generated via two individual neural radiance fields. Experimental results demonstrate that our novel framework can (1) produce high-fidelity and natural results, and (2) support free adjustment of audio signals, viewing directions, and background images. Code is available at https://github.com/YudongGuo/AD-NeRF.
High quality facial image editing is a challenging problem in the movie post-production industry, requiring a high degree of control and identity preservation. Previous works that attempt to tackle this problem may suffer from the entanglement of facial attributes and the loss of the person's identity. Furthermore, many algorithms are limited to a certain task. To tackle these limitations, we propose to edit facial attributes via the latent space of a StyleGAN generator, by training a dedicated latent transformation network and incorporating explicit disentanglement and identity preservation terms in the loss function. We further introduce a pipeline to generalize our face editing to videos. Our model achieves a disentangled, controllable, and identity-preserving facial attribute editing, even in the challenging case of real (i.e., non-synthetic) images and videos. We conduct extensive experiments on image and video datasets and show that our model outperforms other state-of-the-art methods in visual quality and quantitative evaluation. Source codes are available at https://github.com/InterDigitalInc/latent-transformer.
Point cloud registration is a fundamental problem in 3D computer vision. Outdoor LiDAR point clouds are typically large-scale and complexly distributed, which makes the registration challenging. In this paper, we propose an efficient hierarchical network named HRegNet for large-scale outdoor LiDAR point cloud registration. Instead of using all points in the point clouds, HRegNet performs registration on hierarchically extracted keypoints and descriptors. The overall framework combines the reliable features in deeper layer and the precise position information in shallower layers to achieve robust and precise registration. We present a correspondence network to generate correct and accurate keypoints correspondences. Moreover, bilateral consensus and neighborhood consensus are introduced for keypoints matching and novel similarity features are designed to incorporate them into the correspondence network, which significantly improves the registration performance. Besides, the whole network is also highly efficient since only a small number of keypoints are used for registration. Extensive experiments are conducted on two large-scale outdoor LiDAR point cloud datasets to demonstrate the high accuracy and efficiency of the proposed HRegNet. The project website is https://ispc-group.github.io/hregnet.
Editing raster text is a promising but challenging task. We propose to apply text vectorization for the task of raster text editing in display media, such as posters, web pages, or advertisements. In our approach, instead of applying image transformation or generation in the raster domain, we learn a text vectorization model to parse all the rendering parameters including text, location, size, font, style, effects, and hidden background, then utilize those parameters for reconstruction and any editing task. Our text vectorization takes advantage of differentiable text rendering to accurately reproduce the input raster text in a resolution-free parametric format. We show in the experiments that our approach can successfully parse text, styling, and background information in the unified model, and produces artifact-free text editing compared to a raster baseline.
Cross-resolution image alignment is a key problem in multiscale gigapixel photography, which requires to estimate homography matrix using images with large resolution gap. Existing deep homography methods concatenate the input images or features, neglecting the explicit formulation of correspondences between them, which leads to degraded accuracy in cross-resolution challenges. In this paper, we consider the cross-resolution homography estimation as a multimodal problem, and propose a local transformer network embedded within a multiscale structure to explicitly learn correspondences between the multimodal inputs, namely, input images with different resolutions. The proposed local transformer adopts a local attention map specifically for each position in the feature. By combining the local transformer with the multiscale structure, the network is able to capture long-short range correspondences efficiently and accurately. Experiments on both the MS-COCO dataset and real-captured cross-resolution dataset show that the proposed network outperforms existing state-of-the-art feature-based and deep-learning-based homography estimation methods, and is able to accurately align images under 10x resolution gap.
We propose a novel video frame interpolation algorithm based on asymmetric bilateral motion estimation (ABME), which synthesizes an intermediate frame between two input frames. First, we predict symmetric bilateral motion fields to interpolate an anchor frame. Second, we estimate asymmetric bilateral motions fields from the anchor frame to the input frames. Third, we use the asymmetric fields to warp the input frames backward and reconstruct the intermediate frame. Last, to refine the intermediate frame, we develop a new synthesis network that generates a set of dynamic filters and a residual frame using local and global information. Experimental results show that the proposed algorithm achieves excellent performance on various datasets. The source codes and pretrained models are available at https://github.com/JunHeum/ABME.
With the development of computational power and techniques for data collection, deep learning demonstrates a superior performance over most existing algorithms on visual benchmark data sets. Many efforts have been devoted to studying the mechanism of deep learning. One important observation is that deep learning can learn the discriminative patterns from raw materials directly in a task-dependent manner. Therefore, the representations obtained by deep learning outperform hand-crafted features significantly. However, for some real-world applications, it is too expensive to collect the task-specific labels, such as visual search in online shopping. Compared to the limited availability of these task-specific labels, their coarse-class labels are much more affordable, but representations learned from them can be suboptimal for the target task. To mitigate this challenge, we propose an algorithm to learn the fine-grained patterns for the target task, when only its coarse-class labels are available. More importantly, we provide a theoretical guarantee for this. Extensive experiments on real-world data sets demonstrate that the proposed method can significantly improve the performance of learned representations on the target task, when only coarse-class information is available for training.
We derive computed tomography (CT) of a time-varying volumetric scattering object, using a small number of moving cameras. We focus on passive tomography of dynamic clouds, as clouds have a major effect on the Earth's climate. State of the art scattering CT assumes a static object. Existing 4D CT methods rely on a linear image formation model and often on significant priors. In this paper, the angular and temporal sampling rates needed for a proper recovery are discussed. Spatiotemporal CT is achieved using gradient-based optimization, which accounts for the correlation time of the dynamic object content. We demonstrate this in physics-based simulations and on experimental real-world data.
Document unwarping attempts to undo the physical deformation of the paper and recover a 'flatbed' scanned document-image for downstream tasks such as OCR. Current state-of-the-art relies on global unwarping of the document which is not robust to local deformation changes. Moreover, a global unwarping often produces spurious warping artifacts in less warped regions to compensate for severe warps present in other parts of the document. In this paper, we propose the first end-to-end trainable piece-wise unwarping method that predicts local deformation fields and stitches them together with global information to obtain an improved unwarping. The proposed piece-wise formulation results in 4% improvement in terms of multi-scale structural similarity (MS-SSIM) and shows better performance in terms of OCR metrics, character error rate (CER) and word error rate (WER) compared to the state-of-the-art.
Animals have evolved highly functional visual systems to understand motion, assisting perception even under complex environments. In this paper, we work towards developing a computer vision system able to segment objects by exploiting motion cues, i.e. motion segmentation. To achieve this, we introduce a simple variant of the Transformer to segment optical flow frames into primary objects and the background, which can be trained in a self-supervised manner, i.e. without using any manual annotations. Despite using only optical flow, and no appearance information, as input, our approach achieves superior results compared to previous state-of-the-art self-supervised methods on public benchmarks (DAVIS2016, SegTrackv2, FBMS59), while being an order of magnitude faster. On a challenging camouflage dataset (MoCA), we significantly outperform other self-supervised approaches, and are competitive with the top supervised approach, highlighting the importance of motion cues and the potential bias towards appearance in existing video segmentation models.
Federated Learning for Non-IID Data via Unified Feature Learning and Optimization Objective Alignment
PDF ↗Federated Learning (FL) aims to establish a shared model across decentralized clients under the privacy-preserving constraint. Despite certain success, it is still challenging for FL to deal with non-IID (non-independent and identical distribution) client data, which is a general scenario in real-world FL tasks. It has been demonstrated that the performance of FL will be reduced greatly under the non-IID scenario, since the discrepant data distributions will induce optimization inconsistency and feature divergence issues. Besides, naively minimizing an aggregate loss function in this scenario may have negative impacts on some clients and thus deteriorate their personal model performance. To address these issues, we propose a Unified Feature learning and Optimization objectives alignment method (FedUFO) for non-IID FL. In particular, an adversary module is proposed to reduce the divergence on feature representation among different clients, and two consensus losses are proposed to reduce the inconsistency on optimization objectives from two perspectives. Extensive experiments demonstrate that our FedUFO can outperform the state-of-the-art approaches, including the competitive one data-sharing method. Besides, FedUFO can enable more reasonable and balanced model performance among different clients.
Accurate camera pose estimation or global camera re-localization is a core component in Structure-from-Motion (SfM) and SLAM systems. Given pair-wise relative camera poses, pose-graph optimization (PGO) involves solving for an optimized set of globally-consistent absolute camera poses. In this work, we propose a novel PGO scheme fueled by graph neural networks (GNN), namely PoGO-Net, to conduct the absolute camera pose regression leveraging multiple rotation averaging (MRA). Specifically, PoGO-Net takes a noisy view-graph as the input, where the nodes and edges are designed to encode the geometric constraints and local graph consistency. Besides, we address the outlier edge removal by exploiting an implicit edge-dropping scheme where the noisy or corrupted edges are effectively filtered out with parameterized networks. Furthermore, we introduce a joint loss function embedding MRA formulation such that the robust inference is capable of achieving real-time performances even for large-scale scenes. Our proposed network is trained end-to-end on public benchmarks, outperforming state-of-the-art approaches in extensive experiments that demonstrate the efficiency and robustness of our proposed network.