This paper investigates a valuable setting called few-shot unsupervised domain adaptation (FS-UDA), which has not been sufficiently studied in the literature. In this setting, the source domain data are labelled, but with few-shot per category, while the target domain data are unlabelled. To address the FS-UDA setting, we develop a general UDA model to solve the following two key issues: the few-shot labeled data per category and the domain adaptation between support and query sets. Our model is general in that once trained it will be able to be applied to various FS-UDA tasks from the same source and target domains. Inspired by the recent local descriptor based few-shot learning (FSL), our general UDA model is fully built upon local descriptors (LDs) for image classification and domain adaptation. By proposing a novel concept called similarity patterns (SPs), our model not only effectively considers the spatial relationship of LDs that was ignored in previous FSL methods, but also makes the learned image similarity better serve the required domain alignment. Specifically, we propose a novel IMage-to-class sparse Similarity Encoding (IMSE) method. It learns SPs to extract the local discriminative information for classification and meanwhile aligns the covariance matrix of the SPs for domain adaptation. Also, domain adversarial training and multi-scale local feature matching are performed upon LDs. Extensive experiments conducted on a multi-domain benchmark dataset DomainNet demonstrates the state-of-the-art performance of our IMSE for the novel setting of FS-UDA. In addition, for FSL, our IMSE can also show better performance than most of recent FSL methods on miniImageNet.
In this paper, we study stochastic optimization of areas under precision-recall curves (AUPRC), which is widely used for combating imbalanced classification tasks. Although a few methods have been proposed for maximizing AUPRC, stochastic optimization of AUPRC with convergence guarantee remains an undeveloped territory. A recent work [42] has proposed a promising approach towards AUPRC based on maximizing a surrogate loss for the average precision, and proved an $O(1/\epsilon^5)$ complexity for finding an $\epsilon$-stationary solution of the non-convex objective. In this paper, we further improve the stochastic optimization of AURPC by (i) developing novel stochastic momentum methods with a better iteration complexity of $O(1/\epsilon^4)$ for finding an $\epsilon$-stationary solution; and (ii) designing a novel family of stochastic adaptive methods with the same iteration complexity of $O(1/\epsilon^4)$, which enjoy faster convergence in practice. To this end, we propose two innovative techniques that are critical for improving the convergence: (i) the biased estimators for tracking individual ranking scores are updated in a randomized coordinate-wise manner; and (ii) a momentum update is used on top of the stochastic gradient estimator for tracking the gradient of the objective. Extensive experiments on various data sets demonstrate the effectiveness of the proposed algorithms. Of independent interest, the proposed stochastic momentum and adaptive algorithms are also applicable to a class of two-level stochastic dependent compositional optimization problems.
3D object detection in point clouds is a challenging vision task that benefits various applications for understanding the 3D visual world. Lots of recent research focuses on how to exploit end-to-end trainable Hough voting for generating object proposals. However, the current voting strategy can only receive partial votes from the surfaces of potential objects together with severe outlier votes from the cluttered backgrounds, which hampers full utilization of the information from the input point clouds. Inspired by the back-tracing strategy in the conventional Hough voting methods, in this work, we introduce a new 3D object detection method, named as Back-tracing Representative Points Network (BRNet), which generatively back-traces the representative points from the vote centers and also revisits complementary seed points around these generated points, so as to better capture the fine local structural features surrounding the potential objects from the raw point clouds. Therefore, this bottom-up and then top-down strategy in our BRNet enforces mutual consistency between the predicted vote centers and the raw surface points and thus achieves more reliable and flexible object localization and class prediction results. Our BRNet is simple but effective, which significantly outperforms the state-of-the-art methods on two large-scale point cloud datasets, ScanNet V2 (+7.5% in terms of mAP@0.50) and SUN RGB-D (+4.7% in terms of mAP@0.50), while it is still lightweight and efficient. Code will be available at https://github.com/cheng052/BRNet.
Most online multi-object trackers perform object detection stand-alone in a neural net without any input from tracking. In this paper, we present a new online joint detection and tracking model, TraDeS (TRAck to DEtect and Segment), exploiting tracking clues to assist detection end-to-end. TraDeS infers object tracking offset by a cost volume, which is used to propagate previous object features for improving current object detection and segmentation. Effectiveness and superiority of TraDeS are shown on 4 datasets, including MOT (2D tracking), nuScenes (3D tracking), MOTS and Youtube-VIS (instance segmentation tracking). Project page: https://jialianwu.com/projects/TraDeS.html.
View synthesis aims to produce unseen views from a set of views captured by two or more cameras at different positions. This task is non-trivial since it is hard to conduct pixel-level matching among different views. To address this issue, most existing methods seek to exploit the geometric information to match pixels. However, when the distinct cameras have a large baseline (i.e., far away from each other), severe geometry distortion issues would occur and the geometric information may fail to provide useful guidance, resulting in very blurry synthesized images. To address the above issues, in this paper, we propose a novel deep generative model, called Self-Consistent Generative Network (SCGN), which synthesizes novel views from the given input views without explicitly exploiting the geometric information. The proposed SCGN model consists of two main components, i.e., a View Synthesis Network (VSN) and a View Decomposition Network (VDN), both employing an Encoder-Decoder structure. Here, the VDN seeks to reconstruct input views from the synthesized novel view to preserve the consistency of view synthesis. Thanks to VDN, SCGN is able to synthesize novel views without using any geometric rectification before encoding, making it easier for both training and applications. Finally, adversarial loss is introduced to improve the photo-realism of novel views. Both qualitative and quantitative comparisons against several state-of-the-art methods on two benchmark tasks demonstrated the superiority of our approach.
3D vehicle detection based on multi-modal fusion is an important task of many applications such as autonomous driving. Although significant progress has been made, we still observe two aspects that need to be further improvement: First, the specific gain that camera images can bring to 3D detection is seldom explored by previous works. Second, many fusion algorithms run slowly, which is essential for applications with high real-time requirements(autonomous driving). To this end, we propose an end-to-end trainable single-stage multi-modal feature adaptive network in this paper, which uses image information to effectively reduce false positive of 3D detection and has a fast detection speed. A multi-modal adaptive feature fusion module based on channel attention mechanism is proposed to enable the network to adaptively use the feature of each modal. Based on the above mechanism, two fusion technologies are proposed to adapt to different usage scenarios: PointAttentionFusion is suitable for filtering simple false positive and faster; DenseAttentionFusion is suitable for filtering more difficult false positive and has better overall performance. Experimental results on the KITTI dataset demonstrate significant improvement in filtering false positive over the approach using only point cloud data. Furthermore, the proposed method can provide competitive results and has the fastest speed compared to the published state-of-the-art multi-modal methods in the KITTI benchmark.
Most existing unsupervised domain adaptation methods mainly focused on aligning the marginal distributions of samples between the source and target domains. This setting does not sufficiently consider the class distribution information between the two domains, which could adversely affect the reduction of domain gap. To address this issue, we propose a novel approach called Conditional ADversarial Image Translation (CADIT) to explicitly align the class distributions given samples between the two domains. It integrates a discriminative structure-preserving loss and a joint adversarial generation loss. The former effectively prevents undesired label-flipping during the whole process of image translation, while the latter maintains the joint distribution alignment of images and labels. Furthermore, our approach enforces the classification consistence of target domain images before and after adaptation to aid the classifier training in both domains. Extensive experiments were conducted on multiple benchmark datasets including Digits, Faces, Scenes and Office31, showing that our approach achieved superior classification in the target domain when compared to the state-of-the-art methods. Also, both qualitative and quantitative results well supported our motivation that aligning the class distributions can indeed improve domain adaptation.
As one of the most important tasks in autonomous driving systems, ego-lane detection has been extensively studied and has achieved impressive results in many scenarios. However, ego-lane detection in the missing feature scenarios is still an unsolved problem. To address this problem, previous methods have been devoted to proposing more complicated feature extraction algorithms, but they are very time-consuming and cannot deal with extreme scenarios. Different from others, this paper exploits prior knowledge contained in digital maps, which has a strong capability to enhance the performance of detection algorithms. Specifically, we employ the road shape extracted from OpenStreetMap as lane model, which is highly consistent with the real lane shape and irrelevant to lane features. In this way, only a few lane features are needed to eliminate the position error between the road shape and the real lane, and a search-based optimization algorithm is proposed. Experiments show that the proposed method can be applied to various scenarios and can run in real-time at a frequency of 20 Hz. At the same time, we evaluated the proposed method on the public KITTI Lane dataset where it achieves state-of-the-art performance. Moreover, our code will be open source after publication.