Monocular 3D object detection is drawing increasing attention from the community as it enables cars to perceive the world in 3D with a single camera. However, monocular 3D detection currently struggles with extremely lower detection rates compared to LiDAR-based methods, limiting its applications. The poor accuracy is mainly caused by the absence of accurate depth cues due to the ill-posed nature of monocular imagery. LiDAR point clouds, which provide accurate depth measurement, can offer beneficial information for the training of monocular methods. Prior works only use LiDAR point clouds to train a depth estimator. This implicit way does not fully utilize LiDAR point clouds, consequently leading to suboptimal performances. To effectively take advantage of LiDAR point clouds, in this paper we propose a general, simple yet effective framework for monocular methods. Specifically, we use LiDAR point clouds to directly guide the training of monocular 3D detectors, allowing them to learn desired objectives meanwhile eliminating the extra annotation cost. Thanks to the general design, our method can be plugged into any monocular 3D detection method, significantly boosting the performance. In conclusion, we take the first place on KITTI monocular 3D detection benchmark and increase the BEV/3D AP from 11.88/8.65 to 22.06/16.80 on the hard setting for the prior state-of-the-art method. The code will be made publicly available soon.
Image-only and pseudo-LiDAR representations are commonly used for monocular 3D object detection. However, methods based on them have shortcomings of either not well capturing the spatial relationships in neighbored image pixels or being hard to handle the noisy nature of the monocular pseudo-LiDAR point cloud. To overcome these issues, in this paper we propose a novel object-centric voxel representation tailored for monocular 3D object detection. Specifically, voxels are built on each object proposal, and their sizes are adaptively determined by the 3D spatial distribution of the points, allowing the noisy point cloud to be organized effectively within a voxel grid. This representation is proved to be able to locate the object in 3D space accurately. Furthermore, prior works would like to estimate the orientation via deep features extracted from an entire image or a noisy point cloud. By contrast, we argue that the local RoI information from the object image patch alone with a proper resizing scheme is a better input as it provides complete semantic clues meanwhile excludes irrelevant interferences. Besides, we decompose the confidence mechanism in monocular 3D object detection by considering the relationship between 3D objects and the associated 2D boxes. Evaluated on KITTI, our method outperforms state-of-the-art methods by a large margin. The code will be made publicly available soon.
Bounding box regression is an important component in object detection. Recent work has shown the promising performance by optimizing the Intersection over Union (IoU) as loss. However, IoU-based loss has the gradient vanish problem in the case of low overlapping bounding boxes, and the model could easily ignore these simple cases. In this paper, we propose Side Overlap (SO) loss by maximizing the side overlap of two bounding boxes, which puts more penalty for low overlapping bounding box cases. Besides, to speed up the convergence, the Corner Distance (CD) is added into the objective function. Combining the Side Overlap and Corner Distance, we get a new regression objective function, Side and Corner Align Loss (SCALoss). The SCALoss is well-correlated with IoU loss, which also benefits the evaluation metric but produces more penalty for low-overlapping cases. It can serve as a comprehensive similarity measure, leading the better localization performance and faster convergence speed. Experiments on COCO and PASCAL VOC benchmarks show that SCALoss can bring consistent improvement and outperform $\ell_n$ loss and IoU based loss with popular object detectors such as YOLOV3, SSD, Reppoints, Faster-RCNN.
3D object detection algorithms for autonomous driving reason about 3D obstacles either from 3D birds-eye view or perspective view or both. Recent works attempt to improve the detection performance via mining and fusing from multiple egocentric views. Although the egocentric perspective view alleviates some weaknesses of the birds-eye view, the sectored grid partition becomes so coarse in the distance that the targets and surrounding context mix together, which makes the features less discriminative. In this paper, we generalize the research on 3D multi-view learning and propose a novel multi-view-based 3D detection method, named X-view, to overcome the drawbacks of the multi-view methods. Specifically, X-view breaks through the traditional limitation about the perspective view whose original point must be consistent with the 3D Cartesian coordinate. X-view is designed as a general paradigm that can be applied on almost any 3D detectors based on LiDAR with only little increment of running time, no matter it is voxel/grid-based or raw-point-based. We conduct experiments on KITTI and NuScenes datasets to demonstrate the robustness and effectiveness of our proposed X-view. The results show that X-view obtains consistent improvements when combined with four mainstream state-of-the-art 3D methods: SECOND, PointRCNN, Part-A^2, and PV-RCNN.
Object detectors based on sparse object proposals have recently been proven to be successful in the 2D domain, which makes it possible to establish a fully end-to-end detector without time-consuming post-processing. This development is also attractive for 3D object detectors. However, considering the remarkably larger search space in the 3D domain, whether it is feasible to adopt the sparse method in the 3D object detection setting is still an open question. In this paper, we propose SparsePoint, the first sparse method for 3D object detection. Our SparsePoint adopts a number of learnable proposals to encode most likely potential positions of 3D objects and a foreground embedding to encode shared semantic features of all objects. Besides, with the attention module to provide object-level interaction for redundant proposal removal and Hungarian algorithm to supply one-one label assignment, our method can produce sparse and accurate predictions. SparsePoint sets a new state-of-the-art on four public datasets, including ScanNetV2, SUN RGB-D, S3DIS, and Matterport3D. Our code will be publicly available soon.
Few-shot learning (FSL) aims to classify images under low-data regimes, where the conventional pooled global representation is likely to lose useful local characteristics. Recent work has achieved promising performances by using deep descriptors. They generally take all deep descriptors from neural networks into consideration while ignoring that some of them are useless in classification due to their limited receptive field, e.g., task-irrelevant descriptors could be misleading and multiple aggregative descriptors from background clutter could even overwhelm the object's presence. In this paper, we argue that a Mutual Nearest Neighbor (MNN) relation should be established to explicitly select the query descriptors that are most relevant to each task and discard less relevant ones from aggregative clutters in FSL. Specifically, we propose Discriminative Mutual Nearest Neighbor Neural Network (DMN4) for FSL. Extensive experiments demonstrate that our method not only qualitatively selects task-relevant descriptors but also quantitatively outperforms the existing state-of-the-arts by a large margin of 1.8~4.9% on fine-grained CUB, a considerable margin of 1.4~2.2% on both supervised and semi-supervised miniImagenet, and ~1.4% on challenging tieredimagenet.
As an instance-level recognition problem, re-identification (re-ID) requires models to capture diverse features. However, with continuous training, re-ID models pay more and more attention to the salient areas. As a result, the model may only focus on few small regions with salient representations and ignore other important information. This phenomenon leads to inferior performance, especially when models are evaluated on small inter-identity variation data. In this paper, we propose a novel network, Erasing-Salient Net (ES-Net), to learn comprehensive features by erasing the salient areas in an image. ES-Net proposes a novel method to locate the salient areas by the confidence of objects and erases them efficiently in a training batch. Meanwhile, to mitigate the over-erasing problem, this paper uses a trainable pooling layer P-pooling that generalizes global max and global average pooling. Experiments are conducted on two specific re-identification tasks (i.e., Person re-ID, Vehicle re-ID). Our ES-Net outperforms state-of-the-art methods on three Person re-ID benchmarks and two Vehicle re-ID benchmarks. Specifically, mAP / Rank-1 rate: 88.6% / 95.7% on Market1501, 78.8% / 89.2% on DuckMTMC-reID, 57.3% / 80.9% on MSMT17, 81.9% / 97.0% on Veri-776, respectively. Rank-1 / Rank-5 rate: 83.6% / 96.9% on VehicleID (Small), 79.9% / 93.5% on VehicleID (Medium), 76.9% / 90.7% on VehicleID (Large), respectively. Moreover, the visualized salient areas show human-interpretable visual explanations for the ranking results.
Non-autoregressive generation (NAG) has recently attracted great attention due to its fast inference speed. However, the generation quality of existing NAG models still lags behind their autoregressive counterparts. In this work, we show that BERT can be employed as the backbone of a NAG model to greatly improve performance. Additionally, we devise mechanisms to alleviate the two common problems of vanilla NAG models: the inflexibility of prefixed output length and the conditional independence of individual token predictions. Lastly, to further increase the speed advantage of the proposed model, we propose a new decoding strategy, ratio-first, for applications where the output lengths can be approximately estimated beforehand. For a comprehensive evaluation, we test the proposed model on three text generation tasks, including text summarization, sentence compression and machine translation. Experimental results show that our model significantly outperforms existing non-autoregressive baselines and achieves competitive performance with many strong autoregressive models. In addition, we also conduct extensive analysis experiments to reveal the effect of each proposed component.
In recent years, supervised person re-identification (re-ID) models have received increasing studies. However, these models trained on the source domain always suffer dramatic performance drop when tested on an unseen domain. Existing methods are primary to use pseudo labels to alleviate this problem. One of the most successful approaches predicts neighbors of each unlabeled image and then uses them to train the model. Although the predicted neighbors are credible, they always miss some hard positive samples, which may hinder the model from discovering important discriminative information of the unlabeled domain. In this paper, to complement these low recall neighbor pseudo labels, we propose a joint learning framework to learn better feature embeddings via high precision neighbor pseudo labels and high recall group pseudo labels. The group pseudo labels are generated by transitively merging neighbors of different samples into a group to achieve higher recall. However, the merging operation may cause subgroups in the group due to imperfect neighbor predictions. To utilize these group pseudo labels properly, we propose using a similarity-aggregating loss to mitigate the influence of these subgroups by pulling the input sample towards the most similar embeddings. Extensive experiments on three large-scale datasets demonstrate that our method can achieve state-of-the-art performance under the unsupervised domain adaptation re-ID setting.