检索结果-内蒙古大学图书馆

Widerperson: A diverse dataset for dense pedestrian detection in the wild

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Zhang, Shifeng Xie, Yiliang Wan, Jun Xia, Hansheng Li, Stan Z. Guo, Guodong Beijing China Macau University of Science and Technology China United States Nanjing China Institute of Deep Learning Baidu Research and National Engineering Laboratory for Deep Learning Technology and Application

Pedestrian detection has achieved significant progress with the availability of existing benchmark datasets. However, there is a gap in the diversity and density between real world requirements and current pedestrian detection benchmarks: 1) most of existing datasets are taken from a vehicle driving through the regular traffic scenario, usually leading to insufficient diversity;2) crowd scenarios with highly occluded pedestrians are still under represented, resulting in low density. To narrow this gap and facilitate future pedestrian detection research, we introduce a large and diverse dataset named WiderPerson for dense pedestrian detection in the wild. This dataset involves five types of annotations in a wide range of scenarios, no longer limited to the traffic scenario. There are a total of 13, 382 images with 399, 786 annotations, i.e., 29.87 annotations per image, which means this dataset contains dense pedestrians with various kinds of occlusions. Hence, pedestrians in the proposed dataset are extremely challenging due to large variations in the scenario and occlusion, which is suitable to evaluate pedestrian detectors in the wild. We introduce an improved Faster R-CNN and the vanilla RetinaNet to serve as baselines for the new pedestrian detection benchmark. Several experiments are conducted on previous datasets including Caltech-USA and CityPersons to analyze the generalization capabilities of the proposed dataset and we achieve state-of-the-art performances on these previous datasets without bells and whistles. Finally, we analyze common failure cases and find the classification ability of pedestrian detector needs to be improved to reduce false alarm and miss detection rates. The proposed dataset is available at http://***/users/sfzhang/WiderPerson. Copyright © 2019, The Authors. All rights reserved.

关键词： Large dataset

GINet: Graph interaction network for scene parsing

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Wu, Tianyi Lu, Yu Zhu, Yu Zhang, Chuang Wu, Ming Ma, Zhanyu Guo, Guodong Institute of Deep Learning Baidu Research Beijing China National Engineering Laboratory for Deep Learning Technology and Application Beijing China Beijing University of Posts and Telecommunications Beijing China

Recently, context reasoning using image regions beyond local convolution has shown great potential for scene parsing. In this work, we explore how to incorperate the linguistic knowledge to promote context reasoning over image regions by proposing a Graph Interaction unit (GI unit) and a Semantic Context Loss (SC-loss). The GI unit is capable of enhancing feature representations of convolution networks over high-level semantics and learning the semantic coherency adaptively to each sample. Specifically, the dataset-based linguistic knowledge is first incorporated in the GI unit to promote context reasoning over the visual graph, then the evolved representations of the visual graph are mapped to each local representation to enhance the discriminated capability for scene parsing. GI unit is further improved by the SC-loss to enhance the semantic representations over the exemplar-based semantic graph. We perform full ablation studies to demonstrate the effectiveness of each component in our approach. Particularly, the proposed GINet outperforms the state-of-the-art approaches on the popular benchmarks, including Pascal-Context and COCO Stuff. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolution

Dynamic Group Transformer: A General Vision Transformer Backbone with Dynamic Group Attention

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Liu, Kai Wu, Tianyi Liu, Cong Guo, Guodong Sun Yat-Sen University Guangzhou China Institute of Deep Learning Baidu Research Beijing China National Engineering Laboratory for Deep Learning Technology and Application Beijing China

Recently, Transformers have shown promising performance in various vision tasks. To reduce the quadratic computation complexity caused by each query attending to all keys/values, various methods have constrained the range of attention within local regions, where each query only attends to keys/values within a hand-crafted window. However, these hand-crafted window partition mechanisms are data-agnostic and ignore their input content, so it is likely that one query maybe attends to irrelevant keys/values. To address this issue, we propose a Dynamic Group Attention (DG-Attention), which dynamically divides all queries into multiple groups and selects the most relevant keys/values for each group. Our DG-Attention can flexibly model more relevant dependencies without any spatial constraint that is used in hand-crafted window based attention. Built on the DG-Attention, we develop a general vision transformer backbone named Dynamic Group Transformer (DGT). Extensive experiments show that our models can outperform the state-of-the-art methods on multiple common vision tasks, including image classification, semantic segmentation, object detection, and instance segmentation. Copyright © 2022, The Authors. All rights reserved.

关键词：

Every Pixel Counts: Unsupervised geometry learning with holistic 3d motion understanding

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Yang, Zhenheng Wang, Peng Wang, Yang Xu, Wei Nevatia, Ram University of Southern California Baidu Research National Engineering Laboratory for Deep Learning Technology and Applications

learning to estimate 3D geometry in a single image by watching unlabeled videos via deep convolutional network has made significant process recently. Current state-of-the-art (SOTA) methods, are based on the learning framework of rigid structure-from-motion, where only 3D camera ego motion is modeled for geometry estimation. However, moving objects also exist in many videos, e.g. moving cars in a street scene. In this paper, we tackle such motion by additionally incorporating per-pixel 3D object motion into the learning framework, which provides holistic 3D scene flow understanding and helps single image geometry estimation. Specifically, given two consecutive frames from a video, we adopt a motion network to predict their relative 3D camera pose and a segmentation mask distinguishing moving objects and rigid background. An optical flow network is used to estimate dense 2D per-pixel correspondence. A single image depth network predicts depth maps for both images. The four types of information, i.e. 2D flow, camera pose, segment mask and depth maps, are integrated into a differentiable holistic 3D motion parser (HMP), where per-pixel 3D motion for rigid background and moving objects are recovered. We design various losses w.r.t. the two types of 3D motions for training the depth and motion networks, yielding further error reduction for estimated geometry. Finally, in order to solve the 3D motion confusion from monocular videos, we combine stereo images into joint training. Experiments on KITTI 2015 dataset show that our estimated geometry, 3D motion and moving object masks, not only are constrained to be consistent, but also significantly outperforms other SOTA algorithms, demonstrating the benefits of our approach. Copyright © 2018, The Authors. All rights reserved.

关键词： Pixels

LEGO: learning edge with geometry all at once by watching videos

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Yang, Zhenheng Wang, Peng Wang, Yang Xu, Wei Nevatia, Ram University of Southern California Baidu Research National Engineering Laboratory for Deep Learning Technology and Applications

learning to estimate 3D geometry in a single image by watching unlabeled videos via deep convolutional network is attracting significant attention. In this paper, we introduce a "3D as-smooth-as-possible (3D-ASAP)" prior inside the pipeline, which enables joint estimation of edges and 3D scene, yielding results with significant improvement in accuracy for fine detailed structures. Specifically, we define the 3D-ASAP prior by requiring that any two points recovered in 3D from an image should lie on an existing planar surface if no other cues provided. We design an unsupervised framework that Learns Edges and Geometry (depth, normal) all at Once (LEGO). The predicted edges are embedded into depth and surface normal smoothness terms, where pixels without edges in-between are constrained to satisfy the prior. In our framework, the predicted depths, normals and edges are forced to be consistent all the time. We conduct experiments on KITTI to evaluate our estimated geometry and CityScapes to perform edge evaluation. We show that in all of the tasks, ***, normal and edge, our algorithm vastly outperforms other state-of-the-art (SOTA) algorithms, demonstrating the benefits of our approach. Copyright © 2018, The Authors. All rights reserved.

关键词： Geometry

Occlusion aware unsupervised learning of optical flow

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Wang, Yang Yang, Yi Yang, Zhenheng Zhao, Liang Wang, Peng Xu, Wei Baidu Research University of Southern California National Engineering Laboratory for Deep Learning Technology and Applications

It has been recently shown that a convolutional neural network can learn optical flow estimation with unsuper-vised learning. However, the performance of the unsuper-vised methods still has a relatively large gap compared to its supervised counterpart. Occlusion and large motion are some of the major factors that limit the current unsuper-vised learning of optical flow methods. In this work we introduce a new method which models occlusion explicitly and a new warping way that facilitates the learning of large motion. Our method shows promising results on Flying Chairs, MPI-Sintel and KITTI benchmark datasets. Espe-cially on KITTI dataset where abundant unlabeled samples exist, our unsupervised method outperforms its counterpart trained with supervised learning. Copyright © 2017, The Authors. All rights reserved.

关键词： Optical flows

FCFR-Net: Feature fusion based coarse-to-fine residual learning for depth completion

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Liu, Lina Song, Xibin Lyu, Xiaoyang Diao, Junwei Wang, Mengmeng Liu, Yong Zhang, Liangjun Institute of Cyber-Systems and Control Zhejiang University China Baidu Research China National Engineering Laboratory of Deep Learning Technology and Application China

Depth completion aims to recover a dense depth map from a sparse depth map with the corresponding color image as input. Recent approaches mainly formulate depth completion as a one-stage end-to-end learning task, which outputs dense depth maps directly. However, the feature extraction and supervision in one-stage frameworks are insufficient, limiting the performance of these approaches. To address this problem, we propose a novel end-to-end residual learning framework, which formulates the depth completion as a two-stage learning task, i.e., a sparse-to-coarse stage and a coarse-to-fine stage. First, a coarse dense depth map is obtained by a simple CNN framework. Then, a refined depth map is further obtained using a residual learning strategy in the coarse-to-fine stage with a coarse depth map and color image as input. Specially, in the coarse-to-fine stage, a channel shuffle extraction operation is utilized to extract more representative features from the color image and coarse depth map, and an energy based fusion operation is exploited to effectively fuse these features obtained by channel shuffle operation, thus leading to more accurate and refined depth maps. We achieve SoTA performance in RMSE on KITTI benchmark. Extensive experiments on other datasets future demonstrate the superiority of our approach over current state-of-the-art depth completion approaches. Copyright © 2020, The Authors. All rights reserved.

关键词： Benchmarking

Interactive language acquisition with one-shot visual concept learning through a conversational game

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Zhang, Haichao Yu, Haonan Xu, Wei Baidu Research - Institue of Deep Learning Sunnyvale United States National Engineering Laboratory for Deep Learning Technology and Applications Beijing China

Building intelligent agents that can communicate with and learn from humans in natural language is of great value. Supervised language learning is limited by the ability of capturing mainly the statistics of training data, and is hardly adaptive to new scenarios or flexible for acquiring new knowledge without inefficient retraining or catastrophic forgetting. We highlight the perspective that conversational interaction serves as a natural interface both for language learning and for novel knowledge acquisition and propose a joint imitation and reinforcement approach for grounded language learning through an interactive conversational game. The agent trained with this approach is able to actively acquire information by asking questions about novel objects and use the just-learned knowledge in subsequent conversations in a one-shot fashion. Results compared with other methods verified the effectiveness of the proposed approach. Copyright © 2018, The Authors. All rights reserved.

关键词： Intelligent agents

LAE : Long-Tailed Age Estimation 19th

学校读者我要写书评

暂无评论

LAE : Long-Tailed Age Estimation

19th International Conference on Computer Analysis of Images and Patterns, CAIP 2021

作者： Bao, Zenghao Tan, Zichang Zhu, Yu Wan, Jun Ma, Xibo Lei, Zhen Guo, Guodong CBSR&NLPR Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science and Innovation Chinese Academy of Sciences Beijing China Institute of Deep Learning Baidu Research Beijing China National Engineering Laboratory for Deep Learning Technology and Application Beijing China

ISBN: (纸本)9783030891305

Facial age estimation is an important yet very challenging problem in computer vision. To improve the performance of facial age estimation, we first formulate a simple standard baseline and build a much strong one by collecting the tricks in pre-training, data augmentation, model architecture, and so on. Compared with the standard baseline, the proposed one significantly decreases the estimation errors. Moreover, long-tailed recognition has been an important topic in facial age datasets, where the samples often lack on the elderly and children. To train a balanced age estimator, we propose a two-stage training method named Long-tailed Age Estimation (LAE), which decouples the learning procedure into representation learning and classification. The effectiveness of our approach has been demonstrated on the dataset provided by organizers of Guess The Age Contest 2021. © 2021, Springer Nature Switzerland AG.

关键词： deep learning