PyTorchKR Papers

최신 논문

총 9,714편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2107.02980

VIN: Voxel-based Implicit Network for Joint 3D Object Detection and Segmentation for Lidars

A unified neural network structure is presented for joint 3D object detection and point cloud segmentation in this paper. We leverage rich supervision from both detection and segmentation labels rather than using just one of them. In addition, an extension based on single-stage object detectors is proposed based on the implicit function widely used in 3D scene and object understanding. The extension branch takes the final feature map from the object detection module as input, and produces an implicit function that generates semantic distribution for each point for its corresponding voxel center. We demonstrated the performance of our structure on nuScenes-lidarseg, a large-scale outdoor dataset. Our solution achieves competitive results against state-of-the-art methods in both 3D object detection and point cloud segmentation with little additional computation load compared with object detection solutions. The capability of efficient weakly supervision semantic segmentation of the proposed method is also validated by experiments.

arXiv:2107.02966

E-PixelHop: An Enhanced PixelHop Method for Object Classification

Based on PixelHop and PixelHop++, which are recently developed using the successive subspace learning (SSL) framework, we propose an enhanced solution for object classification, called E-PixelHop, in this work. E-PixelHop consists of the following steps. First, to decouple the color channels for a color image, we apply principle component analysis and project RGB three color channels onto two principle subspaces which are processed separately for classification. Second, to address the importance of multi-scale features, we conduct pixel-level classification at each hop with various receptive fields. Third, to further improve pixel-level classification accuracy, we develop a supervised label smoothing (SLS) scheme to ensure prediction consistency. Forth, pixel-level decisions from each hop and from each color subspace are fused together for image-level decision. Fifth, to resolve confusing classes for further performance boosting, we formulate E-PixelHop as a two-stage pipeline. In the first stage, multi-class classification is performed to get a soft decision for each class, where the top 2 classes with the highest probabilities are called confusing classes. Then,we conduct a binary classification in the second stage. The main contributions lie in Steps 1, 3 and 5.We use the classification of the CIFAR-10 dataset as an example to demonstrate the effectiveness of the above-mentioned key components of E-PixelHop.

arXiv:2107.02963공식 코드 · Papers with Code

Disentangle Your Dense Object Detector

Deep learning-based dense object detectors have achieved great success in the past few years and have been applied to numerous multimedia applications such as video understanding. However, the current training pipeline for dense detectors is compromised to lots of conjunctions that may not hold. In this paper, we investigate three such important conjunctions: 1) only samples assigned as positive in classification head are used to train the regression head; 2) classification and regression share the same input feature and computational fields defined by the parallel head architecture; and 3) samples distributed in different feature pyramid layers are treated equally when computing the loss. We first carry out a series of pilot experiments to show disentangling such conjunctions can lead to persistent performance improvement. Then, based on these findings, we propose Disentangled Dense Object Detector (DDOD), in which simple and effective disentanglement mechanisms are designed and integrated into the current state-of-the-art dense object detectors. Extensive experiments on MS COCO benchmark show that our approach can lead to 2.0 mAP, 2.4 mAP and 2.2 mAP absolute improvements on RetinaNet, FCOS, and ATSS baselines with negligible extra overhead. Notably, our best model reaches 55.0 mAP on the COCO test-dev set and 93.5 AP on the hard subset of WIDER FACE, achieving new state-of-the-art performance on these two competitive benchmarks. Code is available at https://github.com/zehuichen123/DDOD.

arXiv:2107.02790

iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesis

How would a static scene react to a local poke? What are the effects on other parts of an object if you could locally push it? There will be distinctive movement, despite evident variations caused by the stochastic nature of our world. These outcomes are governed by the characteristic kinematics of objects that dictate their overall motion caused by a local interaction. Conversely, the movement of an object provides crucial information about its underlying distinctive kinematics and the interdependencies between its parts. This two-way relation motivates learning a bijective mapping between object kinematics and plausible future image sequences. Therefore, we propose iPOKE -- invertible Prediction of Object Kinematics -- that, conditioned on an initial frame and a local poke, allows to sample object kinematics and establishes a one-to-one correspondence to the corresponding plausible videos, thereby providing a controlled stochastic video synthesis. In contrast to previous works, we do not generate arbitrary realistic videos, but provide efficient control of movements, while still capturing the stochastic nature of our environment and the diversity of plausible outcomes it entails. Moreover, our approach can transfer kinematics onto novel object instances and is not confined to particular object classes. Our project page is available at https://bit.ly/3dJN4Lf.

arXiv:2107.02493

Neighbor-Vote: Improving Monocular 3D Object Detection through Neighbor Distance Voting

As cameras are increasingly deployed in new application domains such as autonomous driving, performing 3D object detection on monocular images becomes an important task for visual scene understanding. Recent advances on monocular 3D object detection mainly rely on the ``pseudo-LiDAR'' generation, which performs monocular depth estimation and lifts the 2D pixels to pseudo 3D points. However, depth estimation from monocular images, due to its poor accuracy, leads to inevitable position shift of pseudo-LiDAR points within the object. Therefore, the predicted bounding boxes may suffer from inaccurate location and deformed shape. In this paper, we present a novel neighbor-voting method that incorporates neighbor predictions to ameliorate object detection from severely deformed pseudo-LiDAR point clouds. Specifically, each feature point around the object forms their own predictions, and then the ``consensus'' is achieved through voting. In this way, we can effectively combine the neighbors' predictions with local prediction and achieve more accurate 3D detection. To further enlarge the difference between the foreground region of interest (ROI) pseudo-LiDAR points and the background points, we also encode the ROI prediction scores of 2D foreground pixels into the corresponding pseudo-LiDAR points. We conduct extensive experiments on the KITTI benchmark to validate the merits of our proposed method. Our results on the bird's eye view detection outperform the state-of-the-art performance by a large margin, especially for the ``hard'' level detection.

arXiv:2107.02411

Adapting Vehicle Detector to Target Domain by Adversarial Prediction Alignment

While recent advancement of domain adaptation techniques is significant, most of methods only align a feature extractor and do not adapt a classifier to target domain, which would be a cause of performance degradation. We propose novel domain adaptation technique for object detection that aligns prediction output space. In addition to feature alignment, we aligned predictions of locations and class confidences of our vehicle detector for satellite images by adversarial training. The proposed method significantly improved AP score by over 5%, which shows effectivity of our method for object detection tasks in satellite images.

arXiv:2107.02396

Semi-TCL: Semi-Supervised Track Contrastive Representation Learning

Online tracking of multiple objects in videos requires strong capacity of modeling and matching object appearances. Previous methods for learning appearance embedding mostly rely on instance-level matching without considering the temporal continuity provided by videos. We design a new instance-to-track matching objective to learn appearance embedding that compares a candidate detection to the embedding of the tracks persisted in the tracker. It enables us to learn not only from videos labeled with complete tracks, but also unlabeled or partially labeled videos. We implement this learning objective in a unified form following the spirit of constrastive loss. Experiments on multiple object tracking datasets demonstrate that our method can effectively learning discriminative appearance embeddings in a semi-supervised fashion and outperform state of the art methods on representative benchmarks.

arXiv:2107.02069

SCOD: Active Object Detection for Embodied Agents using Sensory Commutativity of Action Sequences

We introduce SCOD (Sensory Commutativity Object Detection), an active method for movable and immovable object detection. SCOD exploits the commutative properties of action sequences, in the scenario of an embodied agent equipped with first-person sensors and a continuous motor space with multiple degrees of freedom. SCOD is based on playing an action sequence in two different orders from the same starting point and comparing the two final observations obtained after each sequence. Our experiments on 3D realistic robotic setups (iGibson) demonstrate the accuracy of SCOD and its generalization to unseen environments and objects. We also successfully apply SCOD on a real robot to further illustrate its generalization properties. With SCOD, we aim at providing a novel way of approaching the problem of object discovery in the context of a naive embodied agent. We provide code and a supplementary video.

arXiv:2107.02114

Semi-supervised Learning for Dense Object Detection in Retail Scenes

Retail scenes usually contain densely packed high number of objects in each image. Standard object detection techniques use fully supervised training methodology. This is highly costly as annotating a large dense retail object detection dataset involves an order of magnitude more effort compared to standard datasets. Hence, we propose semi-supervised learning to effectively use the large amount of unlabeled data available in the retail domain. We adapt a popular self supervised method called noisy student initially proposed for object classification to the task of dense object detection. We show that using unlabeled data with the noisy student training methodology, we can improve the state of the art on precise detection of objects in densely packed retail scenes. We also show that performance of the model increases as you increase the amount of unlabeled data.

arXiv:2107.02095

Are standard Object Segmentation models sufficient for Learning Affordance Segmentation?

Affordances are the possibilities of actions the environment offers to the individual. Ordinary objects (hammer, knife) usually have many affordances (grasping, pounding, cutting), and detecting these allow artificial agents to understand what are their possibilities in the environment, with obvious application in Robotics. Proposed benchmarks and state-of-the-art prediction models for supervised affordance segmentation are usually modifications of popular object segmentation models such as Mask R-CNN. We observe that theoretically, these popular object segmentation methods should be sufficient for detecting affordances masks. So we ask the question: is it necessary to tailor new architectures to the problem of learning affordances? We show that applying the out-of-the-box Mask R-CNN to the problem of affordances segmentation outperforms the current state-of-the-art. We conclude that the problem of supervised affordance segmentation is included in the problem of object segmentation and argue that better benchmarks for affordance learning should include action capacities.

arXiv:2107.02057

6D Object Pose Estimation using Keypoints and Part Affinity Fields

The task of 6D object pose estimation from RGB images is an important requirement for autonomous service robots to be able to interact with the real world. In this work, we present a two-step pipeline for estimating the 6 DoF translation and orientation of known objects. Keypoints and Part Affinity Fields (PAFs) are predicted from the input image adopting the OpenPose CNN architecture from human pose estimation. Object poses are then calculated from 2D-3D correspondences between detected and model keypoints via the PnP-RANSAC algorithm. The proposed approach is evaluated on the YCB-Video dataset and achieves accuracy on par with recent methods from the literature. Using PAFs to assemble detected keypoints into object instances proves advantageous over only using heatmaps. Models trained to predict keypoints of a single object class perform significantly better than models trained for several classes.

arXiv:2107.02036

A topological solution to object segmentation and tracking

The world is composed of objects, the ground, and the sky. Visual perception of objects requires solving two fundamental challenges: segmenting visual input into discrete units, and tracking identities of these units despite appearance changes due to object deformation, changing perspective, and dynamic occlusion. Current computer vision approaches to segmentation and tracking that approach human performance all require learning, raising the question: can objects be segmented and tracked without learning? Here, we show that the mathematical structure of light rays reflected from environment surfaces yields a natural representation of persistent surfaces, and this surface representation provides a solution to both the segmentation and tracking problems. We describe how to generate this surface representation from continuous visual input, and demonstrate that our approach can segment and invariantly track objects in cluttered synthetic video despite severe appearance changes, without requiring learning.

arXiv:2107.01889공식 코드 · Papers with Code

OPA: Object Placement Assessment Dataset

Image composition aims to generate realistic composite image by inserting an object from one image into another background image, where the placement (e.g., location, size, occlusion) of inserted object may be unreasonable, which would significantly degrade the quality of the composite image. Although some works attempted to learn object placement to create realistic composite images, they did not focus on assessing the plausibility of object placement. In this paper, we focus on object placement assessment task, which verifies whether a composite image is plausible in terms of the object placement. To accomplish this task, we construct the first Object Placement Assessment (OPA) dataset consisting of composite images and their rationality labels. We also propose a simple yet effective baseline for this task. Dataset is available at https://github.com/bcmi/Object-Placement-Assessment-Dataset-OPA.

arXiv:2107.01814

Web-Scale Generic Object Detection at Microsoft Bing

In this paper, we present Generic Object Detection (GenOD), one of the largest object detection systems deployed to a web-scale general visual search engine that can detect over 900 categories for all Microsoft Bing Visual Search queries in near real-time. It acts as a fundamental visual query understanding service that provides object-centric information and shows gains in multiple production scenarios, improving upon domain-specific models. We discuss the challenges of collecting data, training, deploying and updating such a large-scale object detection model with multiple dependencies. We discuss a data collection pipeline that reduces per-bounding box labeling cost by 81.5% and latency by 61.2% while improving on annotation quality. We show that GenOD can improve weighted average precision by over 20% compared to multiple domain-specific models. We also improve the model update agility by nearly 2 times with the proposed disjoint detector training compared to joint fine-tuning. Finally we demonstrate how GenOD benefits visual search applications by significantly improving object-level search relevance by 54.9% and user engagement by 59.9%.

arXiv:2107.01787

Multi-View Correlation Distillation for Incremental Object Detection

In real applications, new object classes often emerge after the detection model has been trained on a prepared dataset with fixed classes. Due to the storage burden and the privacy of old data, sometimes it is impractical to train the model from scratch with both old and new data. Fine-tuning the old model with only new data will lead to a well-known phenomenon of catastrophic forgetting, which severely degrades the performance of modern object detectors. In this paper, we propose a novel \textbf{M}ulti-\textbf{V}iew \textbf{C}orrelation \textbf{D}istillation (MVCD) based incremental object detection method, which explores the correlations in the feature space of the two-stage object detector (Faster R-CNN). To better transfer the knowledge learned from the old classes and maintain the ability to learn new classes, we design correlation distillation losses from channel-wise, point-wise and instance-wise views to regularize the learning of the incremental model. A new metric named Stability-Plasticity-mAP is proposed to better evaluate both the stability for old classes and the plasticity for new classes in incremental object detection. The extensive experiments conducted on VOC2007 and COCO demonstrate that MVCD can effectively learn to detect objects of new classes and mitigate the problem of catastrophic forgetting.

arXiv:2107.01469

Scene-aware Learning Network for Radar Object Detection

Object detection is essential to safe autonomous or assisted driving. Previous works usually utilize RGB images or LiDAR point clouds to identify and localize multiple objects in self-driving. However, cameras tend to fail in bad driving conditions, e.g. bad weather or weak lighting, while LiDAR scanners are too expensive to get widely deployed in commercial applications. Radar has been drawing more and more attention due to its robustness and low cost. In this paper, we propose a scene-aware radar learning framework for accurate and robust object detection. First, the learning framework contains branches conditioning on the scene category of the radar sequence; with each branch optimized for a specific type of scene. Second, three different 3D autoencoder-based architectures are proposed for radar object detection and ensemble learning is performed over the different architectures to further boost the final performance. Third, we propose novel scene-aware sequence mix augmentation (SceneMix) and scene-specific post-processing to generate more robust detection results. In the ROD2021 Challenge, we achieved a final result of average precision of 75.0% and an average recall of 81.0%. Moreover, in the parking lot scene, our framework ranks first with an average precision of 97.8% and an average recall of 98.6%, which demonstrates the effectiveness of our framework.

논문 ID: document/8967895

PPR-Net:Point-wise Pose Regression Network for Instance Segmentation and 6D Pose Estimation in Bin-picking Scenarios

Accurate object 6D pose estimation is a core task for robot bin-picking applications, especially when objects are randomly stacked with heavy occlusion. To address this problem, this paper proposes a simple but novel Point-wise Pose Regression Network (PPR-Net). For each point in the point cloud, the network regresses a 6D pose of the object instance that the point belongs to. We argue that the regressed poses of points from the same object instance should be located closely in pose space. Thus, these points can be clustered into different instances and their corresponding objects’ 6D poses can be estimated simultaneously. In our experiments, PPR-Net outperforms the state-of-the-art approach by 15% - 41% in average precision when evaluated on the benchmark Sileane ´ dataset. In addition, it also works well in real world robot bin-picking tasks.

arXiv:2107.01189

NTIRE 2021 Multi-modal Aerial View Object Classification Challenge

In this paper, we introduce the first Challenge on Multi-modal Aerial View Object Classification (MAVOC) in conjunction with the NTIRE 2021 workshop at CVPR. This challenge is composed of two different tracks using EO andSAR imagery. Both EO and SAR sensors possess different advantages and drawbacks. The purpose of this competition is to analyze how to use both sets of sensory information in complementary ways. We discuss the top methods submitted for this competition and evaluate their results on our blind test set. Our challenge results show significant improvement of more than 15% accuracy from our current baselines for each track of the competition

arXiv:2107.01181

Visual Relationship Forecasting in Videos

Real-world scenarios often require the anticipation of object interactions in unknown future, which would assist the decision-making process of both humans and agents. To meet this challenge, we present a new task named Visual Relationship Forecasting (VRF) in videos to explore the prediction of visual relationships in a reasoning manner. Specifically, given a subject-object pair with H existing frames, VRF aims to predict their future interactions for the next T frames without visual evidence. To evaluate the VRF task, we introduce two video datasets named VRF-AG and VRF-VidOR, with a series of spatio-temporally localized visual relation annotations in a video. These two datasets densely annotate 13 and 35 visual relationships in 1923 and 13447 video clips, respectively. In addition, we present a novel Graph Convolutional Transformer (GCT) framework, which captures both object-level and frame-level dependencies by spatio-temporal Graph Convolution Network and Transformer. Experimental results on both VRF-AG and VRF-VidOR datasets demonstrate that GCT outperforms the state-of-the-art sequence modelling methods on visual relationship forecasting.

arXiv:2107.00887

HO-3D_v3: Improving the Accuracy of Hand-Object Annotations of the HO-3D Dataset

HO-3D is a dataset providing image sequences of various hand-object interaction scenarios annotated with the 3D pose of the hand and the object and was originally introduced as HO-3D_v2. The annotations were obtained automatically using an optimization method, 'HOnnotate', introduced in the original paper. HO-3D_v3 provides more accurate annotations for both the hand and object poses thus resulting in better estimates of contact regions between the hand and the object. In this report, we elaborate on the improvements to the HOnnotate method and provide evaluations to compare the accuracy of HO-3D_v2 and HO-3D_v3. HO-3D_v3 results in 4mm higher accuracy compared to HO-3D_v2 for hand poses while exhibiting higher contact regions with the object surface.