Few-shot semantic segmentation (FSS) is an important task for novel (unseen) object segmentation under the data-scarcity scenario. However, most FSS methods rely on unidirectional feature aggregation, e.g., from support prototypes to get the query prediction, and from high-resolution features to guide the low-resolution ones. This usually fails to fully capture the cross-resolution feature relationships and thus leads to inaccurate estimates of the query objects. To resolve the above dilemma, we propose a cyclic memory network (CMN) to directly learn to read abundant support information from all resolution features in a cyclic manner. Specifically, we first generate N pairs (key and value) of multi-resolution query features guided by the support feature and its mask. Next, we circularly take one pair of these features as the query to be segmented, and the rest N-1 pairs are written into an external memory accordingly, i.e., this leave-one-out process is conducted for N times. In each cycle, the query feature is updated by collaboratively matching its key and value with the memory, which can elegantly cover all the spatial locations from different resolutions. Furthermore, we incorporate the query feature re-adding and the query feature recursive updating mechanisms into the memory reading operation. CMN, equipped with these merits, can thus capture cross-resolution relationships and better handle the object appearance and scale variations in FSS. Experiments on PASCAL-5i and COCO-20i well validate the effectiveness of our model for FSS.
论文检索
输入标题、作者或关键词，从 5,999 篇学术成果中精准定位
In this paper, we present DeepSIM, a generative model for conditional image manipulation based on a single image. We find that extensive augmentation is key for enabling single image training, and incorporate the use of thin-plate-spline (TPS) as an effective augmentation. Our network learns to map between a primitive representation of the image to the image itself. The choice of a primitive representation has an impact on the ease and expressiveness of the manipulations and can be automatic (e.g. edges), manual (e.g. segmentation) or hybrid such as edges on top of segmentations. At manipulation time, our generator allows for making complex image changes by modifying the primitive input representation and mapping it through the network. Our method is shown to achieve remarkable performance on image manipulation tasks.
GLoRIA: A Multimodal Global-Local Representation Learning Framework for Label-Efficient Medical Image Recognition
PDF ↗In recent years, the growing number of medical imaging studies is placing an ever-increasing burden on radiologists. Deep learning provides a promising solution for automatic medical image analysis and clinical decision support. However, large-scale manually labeled datasets required for training deep neural networks are difficult and expensive to obtain for medical images. The purpose of this work is to develop label-efficient multimodal medical imaging representations by leveraging radiology reports. Specifically, we propose an attention-based framework (GLoRIA) for learning global and local representations by contrasting image sub-regions and words in the paired report. In addition, we propose methods to leverage the learned representations for various downstream medical image recognition tasks with limited labels. Our results demonstrate high-performance and label-efficiency for image-text retrieval, classification (finetuning and zeros-shot settings), and segmentation on different datasets.
RGB-D semantic segmentation has attracted increasing attention over the past few years. Existing methods mostly employ homogeneous convolution operators to consume the RGB and depth features, ignoring their intrinsic differences. In fact, the RGB values capture the photometric appearance properties in the projected image space, while the depth feature encodes both the shape of a local geometry as well as the base (whereabout) of it in a larger context. Compared with the base, the shape probably is more inherent and has a stronger connection to the semantics, and thus is more critical for segmentation accuracy. Inspired by this observation, we introduce Shape-aware Convolutional layer (ShapeConv) for processing the depth feature, where the depth feature is firstly decomposed into a shape-component and a base-component, next two learnable weights are introduced to cooperate with them independently, and finally a convolution is applied on the re-weighted combination of these two components. ShapeConv is model-agnostic and can be easily integrated into most CNNs to replace vanilla convolutional layers for semantic segmentation. Extensive experiments on three challenging indoor RGB-D semantic segmentation benchmarks, i.e., NYU-Dv2(-13,-40), SUN RGB-D, and SID, demonstrate the effectiveness of our ShapeConv when employing it over five popular architectures. Moreover, the performance of CNNs with ShapeConv is boosted without introducing any computation and memory increase in the inference phase. The reason is that the learnt weights for balancing the importance between the shape and base components in ShapeConv become constants in the inference phase, and thus can be fused into the following convolution, resulting in a network that is identical to one with vanilla convolutional layers.
In recent years, many dexterous robotic hands have been designed to assist or replace human hands in executing various tasks. But how to teach them to perform dexterous operations like human hands is still a challenging task. In this paper, we propose a grasp synthesis framework to make robots grasp and manipulate objects like human beings. We first build a dataset by accurately segmenting the functional areas of the object and annotating semantic touch code for each functional area to guide the dexterous hand to complete the functional grasp and post-grasp manipulation. This dataset contains 18 categories of 129 objects selected from four datasets, and 15 people participated in data annotation. Then we carefully design four loss functions to constrain the network, which successfully generates the functional grasp of dexterous hand under the guidance of semantic touch code. The thorough experiments in synthetic data show our model can robustly generate functional grasp, even for objects that the model has not see before.
TMCOSS: Thresholded Multi-Criteria Online Subset Selection for Data-Efficient Autonomous Driving
PDF ↗Training vision-based Autonomous driving models is a challenging problem with enormous practical implications. One of the main challenges is the requirement of storage and processing of vast volumes of (possibly redundant) driving video data. In this paper, we study the problem of data-efficient training of autonomous driving systems. We argue that in the context of an edge-device deployment, multi-criteria online video frame subset selection is an appropriate technique for developing such frameworks. We study existing convex optimization based solutions and show that they are unable to provide solution with high weightage to loss of selected video frames. We design a novel multi-criteria online subset selection algorithm, TMCOSS, which uses a thresholded concave function of selection variables. Extensive experiments using driving simulator CARLA show that we are able to drop 80% of the frames, while succeeding to complete 100% of the episodes. We also show that TMCOSS improves performance on the crucial affordance 'Relative Angle' during turns, on inclusion of bucket-specific relative angle loss (BL), leading to selection of more frames in those parts. TMCOSS also achieves an 80% reduction in number of training video frames, on real-world videos from the standard BDD and Cityscapes datasets, for the tasks of drivable area segmentation, and semantic segmentation.
Gradient-based algorithms are crucial to modern computer-vision and graphics applications, enabling learning-based optimization and inverse problems. For example, photorealistic differentiable rendering pipelines for color images have been proven highly valuable to applications aiming to map 2D and 3D domains. However, to the best of our knowledge, no effort has been made so far towards extending these gradient-based methods to the generation of depth (2.5D) images, as simulating structured-light depth sensors implies solving complex light transport and stereo-matching problems. In this paper, we introduce a novel end-to-end differentiable simulation pipeline for the generation of realistic 2.5D scans, built on physics-based 3D rendering and custom block-matching algorithms. Each module can be differentiated w.r.t sensor and scene parameters; e.g., to automatically tune the simulation for new devices over some provided scans or to leverage the pipeline as a 3D-to-2.5D transformer within larger computer-vision applications. Applied to the training of deep-learning methods for various depth-based recognition tasks (classification, pose estimation, semantic segmentation), our simulation greatly improves the performance of the resulting models on real scans, thereby demonstrating the fidelity and value of its synthetic depth data compared to previous static simulations and learning-based domain adaptation schemes.
An important issue facing vision-based intelligent systems today is the lack of accessibility-aware development. A main reason for this issue is the absence of any large-scale, standardized vision benchmarks that incorporate relevant tasks and scenarios related to people with disabilities. This lack of representation hinders even preliminary analysis with respect to underlying pose, appearance, and occlusion characteristics of diverse pedestrians. What is the impact of significant occlusion from a wheelchair on instance segmentation quality? How can interaction with mobility aids, e.g., a long and narrow walking cane, be recognized robustly? To begin addressing such questions, we introduce X-World, an accessibility-centered development environment for vision-based autonomous systems. We tackle inherent data scarcity by leveraging a simulation environment to spawn dynamic agents with various mobility aids. The simulation supports generation of ample amounts of finely annotated, multi-modal data in a safe, cheap, and privacy-preserving manner. Our analysis highlights novel challenges introduced by our benchmark and tasks, as well as numerous opportunities for future developments. We further broaden our analysis using a complementary real-world evaluation benchmark of in-situ navigation by pedestrians with disabilities. Our contributions provide an initial step towards widespread deployment of vision-based agents that can perceive and model the interaction needs of diverse people with disabilities.
In this work, we tackle the problem of category-level online pose tracking for objects from point cloud sequences. For the first time, we propose a unified framework that can handle 9DoF object pose tracking for novel rigid object instances as well as per-part pose tracking for articulated objects from known categories. Here the 9DoF pose, comprising 6D pose and 3D size, is equivalent to a 3D amodal bounding box representation with free 6D pose. Given the depth point cloud at the current frame and the estimated pose from the last frame, our novel end-to-end pipeline learns to accurately update the pose. Our pipeline is composed of three modules: 1) a pose canonicalization module that normalizes the pose of the input depth point cloud; 2) RotationNet, a module that directly regresses small interframe delta rotations; and 3) CoordinateNet, a module that predicts the normalized coordinates and segmentation, enabling analytical computation of the 3D size and translation. Leveraging the small pose regime in the pose-canonicalized point clouds, our method integrates the best of both worlds by combining dense coordinate prediction and direct rotation regression, thus yielding an end-to-end differentiable pipeline optimized for 9DoF pose accuracy (without using non-differentiable RANSAC). Our extensive experiments demonstrate that our method achieves new state-of-the-art performance on category-level rigid object pose and articulated object pose benchmarks at the fastest FPS 12.
Data augmentation is vital for deep learning neural networks. By providing massive training samples, it helps to improve the generalization ability of the model. Weakly supervised semantic segmentation (WSSS) is a challenging problem that has been deeply studied in recent years, conventional data augmentation approaches for WSSS usually employ geometrical transformations, random cropping, and color jittering. However, merely increasing the same contextual semantic data does not bring much gain to the networks to distinguish the objects, e.g., the correct image-level classification of "aeroplane" may be not only due to the recognition of the object itself but also its co-occurrence context like "sky", which will cause the model to focus less on the object features. To this end, we present a Context Decoupling Augmentation (CDA) method, to change the inherent context in which the objects appear and thus drive the network to remove the dependence between object instances and contextual information. To validate the effectiveness of the proposed method, extensive experiments on PASCAL VOC 2012 dataset with several alternative network architectures demonstrate that CDA can boost various popular WSSS methods to the new state-of-the-art by a large margin.
In this work, we devote to address the challenging problem of scene parsing. Previous methods, though capture context to exploit global clues, handle scene parsing as a pixel-independent task. However, it is well known that pixels in an image are highly correlated with each other, especially those from the same semantic region, while treating pixels independently fails to take advantage of such correlations. In this work, we treat each respective region in an image as a whole, and capture the structure topology as well as the affinity among different regions. To this end, we first divide the entire feature maps to different regions and extract respective global features from them. Next, we construct a directed graph whose nodes are regional features, and the edge connecting every two nodes is the affinity between the regional features they represent. After that, we transfer the affinity-aware nodes in the directed graph back to corresponding regions of the image, which helps to model the region dependencies and mitigate unrealistic results. In addition, to further boost the correlation among pixels, we propose a region-level loss that evaluates all pixels in a region as a whole and motivates the network to learn the exclusive regional feature per class. With the proposed approach, we achieves new state-of-the-art segmentation results on PASCAL-Context, ADE20K, and COCO-Stuff consistently.
In this paper, we propose an anchor-free single-stage LiDAR-based 3D object detector -- RangeDet. The most notable difference with previous works is that our method is purely based on the range view representation. Compared with the commonly used voxelized or Bird's Eye View (BEV) representations, the range view representation is more compact and without quantization error. Although there are works adopting it for semantic segmentation, its performance in object detection is largely behind voxelized or BEV counterparts. We first analyze the existing range-view-based methods and find two issues overlooked by previous works: 1) the scale variation between nearby and far away objects; 2) the inconsistency between the 2D range image coordinates used in feature extraction and the 3D Cartesian coordinates used in output. Then we deliberately design three components to address these issues in our RangeDet. We test our RangeDet in the large-scale Waymo Open Dataset (WOD). Our best model achieves 72.9/75.9/65.8 3D AP on vehicle/pedestrian/cyclist. These results outperform other range-view-based methods by a large margin, and are overall comparable with the state-of-the-art multi-view-based methods. Codes will be released at https://github.com/TuSimple/RangeDet.
In recent years, sparse voxel-based methods have become the state-of-the-arts for 3D semantic segmentation of indoor scenes, thanks to the powerful 3D CNNs. Nevertheless, being oblivious to the underlying geometry, voxel-based methods suffer from ambiguous features on spatially close objects and struggle with handling complex and irregular geometries due to the lack of geodesic information. In view of this, we present Voxel-Mesh Network (VMNet), a novel 3D deep architecture that operates on the voxel and mesh representations leveraging both the Euclidean and geodesic information. Intuitively, the Euclidean information extracted from voxels can offer contextual cues representing interactions between nearby objects, while the geodesic information extracted from meshes can help separate objects that are spatially close but have disconnected surfaces. To incorporate such information from the two domains, we design an intra-domain attentive module for effective feature aggregation and an inter-domain attentive module for adaptive feature fusion. Experimental results validate the effectiveness of VMNet: specifically, on the challenging ScanNet dataset for large-scale segmentation of indoor scenes, it outperforms the state-of-the-art SparseConvNet and MinkowskiNet (74.6% vs 72.5% and 73.6% in mIoU) with a simpler network structure (17M vs 30M and 38M parameters). Code release: https://github.com/hzykent/VMNet
In this work, we address the task of unsupervised domain adaptation (UDA) for semantic segmentation in presence of multiple target domains: the objective is to train a single model that can handle all these domains at test time. Such a multi-target adaptation is crucial for a variety of scenarios that real-world autonomous systems must handle. It is a challenging set-up since one faces not only the domain gap between the labeled source set and the unlabeled target set, but also the distribution shifts existing within the latter among the different target domains. To this end, we introduce two adversarial frameworks: (i) multi-discriminator, which explicitly aligns each target domain to its counterparts, and (ii) multi-target knowledge transfer, which learns a target-agnostic model thanks to a multi-teacher/single-student distillation mechanism. The evaluation is done on four newly proposed multi-target benchmarks for UDA in semantic segmentation. In all tested scenarios, our approaches consistently outperform baselines, setting competitive standards for the novel task.
Recently, various works that attempted to introduce rotation invariance to point cloud analysis have devised point-pair features, such as angles and distances. In these methods, however, the point-pair is only comprised of the center point and its adjacent points in a vicinity, which may bring information loss to the local feature representation. In this paper, we instead connect each point densely with all other points in a local neighborhood to compose the point-pairs. Specifically, we present a simple but effective local feature representation, called sorted Gram matrix(SGM), which is not only invariant to arbitrary rotations, but also models the pair-wise relationship of all the points in a neighborhood. In more detail, we utilize vector inner product to model distance- and angle-information between two points, and in a local patch it naturally forms a Gram matrix. In order to guarantee permutation invariance, we sort the correlation value in Gram matrix for each point, therefore this geometric feature names sorted Gram matrix. Furthermore, we mathematically prove that the Gram matrix is rotation-invariant and sufficient to model the inherent structure of a point cloud patch. We then use SGM as features in convolution, which can be readily integrated as a drop-in module into any point-based networks. Finally, we evaluated the proposed method on two widely used datasets, and it outperforms previous state-of-the-arts on both shape classification and part segmentation tasks by a large margin.
Lane detection plays a key role in autonomous driving. While car cameras always take streaming videos on the way, current lane detection works mainly focus on individual images (frames) by ignoring dynamics along the video. In this work, we collect a new video instance lane detection (VIL-100) dataset, which contains 100 videos with in total 10,000 frames, acquired from different real traffic scenarios. All the frames in each video are manually annotated to a high-quality instance-level lane annotation, and a set of frame-level and video-level metrics are included for quantitative performance evaluation. Moreover, we propose a new baseline model, named multi-level memory aggregation network (MMA-Net), for video instance lane detection. In our approach, the representation of current frame is enhanced by attentively aggregating both local and global memory features from other frames. Experiments on the new collected dataset show that the proposed MMA-Net outperforms state-of-the-art lane detection methods and video object segmentation methods. We release our dataset and code at https://github.com/yujun0-0/MMA-Net.
Video instance segmentation (VIS) aims to segment and associate all instances of predefined classes for each frame in videos. Prior methods usually obtain segmentation for a frame or clip first, and merge the incomplete results by tracking or matching. These methods may cause error accumulation in the merging step. Contrarily, we propose a new paradigm -- Propose-Reduce, to generate complete sequences for input videos by a single step. We further build a sequence propagation head on the existing image-level instance segmentation network for long-term propagation. To ensure robustness and high recall of our proposed framework, multiple sequences are proposed where redundant sequences of the same instance are reduced. We achieve state-of-the-art performance on two representative benchmark datasets -- we obtain 47.6% in terms of AP on YouTube-VIS validation set and 70.4% for J&F on DAVIS-UVOS validation set.
Sparse-to-Dense Feature Matching: Intra and Inter Domain Cross-Modal Learning in Domain Adaptation for 3D Semantic Segmentation
PDF ↗Domain adaptation is critical for success when confronting with the lack of annotations in a new domain. As the huge time consumption of labeling process on 3D point cloud, domain adaptation for 3D semantic segmentation is of great expectation. With the rise of multi-modal datasets, large amount of 2D images are accessible besides 3D point clouds. In light of this, we propose to further leverage 2D data for 3D domain adaptation by intra and inter domain cross modal learning. As for intra-domain cross modal learning, most existing works sample the dense 2D pixel-wise features into the same size with sparse 3D point-wise features, resulting in the abandon of numerous useful 2D features. To address this problem, we propose Dynamic sparse-to-dense Cross Modal Learning (DsCML) to increase the sufficiency of multi-modality information interaction for domain adaptation. For inter-domain cross modal learning, we further advance Cross Modal Adversarial Learning (CMAL) on 2D and 3D data which contains different semantic content aiming to promote high-level modal complementarity. We evaluate our model under various multi-modality domain adaptation settings including day-to-night, country-to-country and dataset-to-dataset, brings large improvements over both uni-modal and multi-modal domain adaptation methods on all settings.
Unlocking the Potential of Ordinary Classifier: Class-Specific Adversarial Erasing Framework for Weakly Supervised Semantic Segmentation
PDF ↗Weakly supervised semantic segmentation (WSSS) using image-level classification labels usually utilizes the Class Activation Maps (CAMs) to localize objects of interest in images. While pointing out that CAMs only highlight the most discriminative regions of the classes of interest, adversarial erasing (AE) methods have been proposed to further explore the less discriminative regions. In this paper, we review the potential of the pre-trained classifier which is trained on the raw images. We experimentally verify that the ordinary classifier already has the capability to activate the less discriminative regions if the most discriminative regions are erased to some extent. Based on that, we propose a class-specific AE-based framework that fully exploits the potential of an ordinary classifier. Our framework (1) adopts the ordinary classifier to notify the regions to be erased and (2) generates a class-specific mask for erasing by randomly sampling a single specific class to be erased (target class) among the existing classes on the image for obtaining more precise CAMs. Specifically, with the guidance of the ordinary classifier, the proposed CAMs Generation Network (CGNet) is enforced to generate a CAM of the target class while constraining the CAM not to intrude the object regions of the other classes. Along with the pseudo-labels refined from our CAMs, we achieve the state-of-the-art WSSS performance on both PASCAL VOC 2012 and MS-COCO dataset only with image-level supervision. The code is available at https://github.com/KAIST-vilab/OC-CSE.
Real-time video inference on edge devices like mobile phones and drones is challenging due to the high computation cost of Deep Neural Networks. We present Adaptive Model Streaming (AMS), a new approach to improving the performance of efficient lightweight models for video inference on edge devices. AMS uses a remote server to continually train and adapt a small model running on the edge device, boosting its performance on the live video using online knowledge distillation from a large, state-of-the-art model. We discuss the challenges of over-the-network model adaptation for video inference and present several techniques to reduce communication the cost of this approach: avoiding excessive overfitting, updating a small fraction of important model parameters, and adaptive sampling of training frames at edge devices. On the task of video semantic segmentation, our experimental results show 0.4--17.8 percent mean Intersection-over-Union improvement compared to a pre-trained model across several video datasets. Our prototype can perform video segmentation at 30 frames-per-second with 40 milliseconds camera-to-label latency on a Samsung Galaxy S10+ mobile phone, using less than 300 Kbps uplink and downlink bandwidth on the device.