PyTorchKR Papers

최신 논문

총 9,712편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2208.11315

Comparison of Object Detection Algorithms for Street-level Objects

Object detection for street-level objects can be applied to various use cases, from car and traffic detection to the self-driving car system. Therefore, finding the best object detection algorithm is essential to apply it effectively. Many object detection algorithms have been released, and many have compared object detection algorithms, but few have compared the latest algorithms, such as YOLOv5, primarily which focus on street-level objects. This paper compares various one-stage detector algorithms; SSD MobileNetv2 FPN-lite 320x320, YOLOv3, YOLOv4, YOLOv5l, and YOLOv5s for street-level object detection within real-time images. The experiment utilizes a modified Udacity Self Driving Car Dataset with 3,169 images. Dataset is split into train, validation, and test; Then, it is preprocessed and augmented using rescaling, hue shifting, and noise. Each algorithm is then trained and evaluated. Based on the experiments, the algorithms have produced decent results according to the inference time and the values of their precision, recall, F1-Score, and Mean Average Precision (mAP). The results also shows that YOLOv5l outperforms the other algorithms in terms of accuracy with a mAP@.5 of 0.593, MobileNetv2 FPN-lite has the fastest inference time among the others with only 3.20ms inference time. It is also found that YOLOv5s is the most efficient, with it having a YOLOv5l accuracy and a speed almost as quick as the MobileNetv2 FPN-lite. This shows that various algorithm are suitable for street-level object detection and viable enough to be used in self-driving car.

arXiv:2208.11641

Detecting the unknown in Object Detection

Object detection methods have witnessed impressive improvements in the last years thanks to the design of novel neural network architectures and the availability of large scale datasets. However, current methods have a significant limitation: they are able to detect only the classes observed during training time, that are only a subset of all the classes that a detector may encounter in the real world. Furthermore, the presence of unknown classes is often not considered at training time, resulting in methods not even able to detect that an unknown object is present in the image. In this work, we address the problem of detecting unknown objects, known as open-set object detection. We propose a novel training strategy, called UNKAD, able to predict unknown objects without requiring any annotation of them, exploiting non annotated objects that are already present in the background of training images. In particular, exploiting the four-steps training strategy of Faster R-CNN, UNKAD first identifies and pseudo-labels unknown objects and then uses the pseudo-annotations to train an additional unknown class. While UNKAD can directly detect unknown objects, we further combine it with previous unknown detection techniques, showing that it improves their performance at no costs.

arXiv:2208.11533

ssFPN: Scale Sequence (S^2) Feature Based-Feature Pyramid Network for Object Detection

Feature Pyramid Network (FPN) has been an essential module for object detection models to consider various scales of an object. However, average precision (AP) on small objects is relatively lower than AP on medium and large objects. The reason is why the deeper layer of CNN causes information loss as feature extraction level. We propose a new scale sequence (S^2) feature extraction of FPN to strengthen feature information of small objects. We consider FPN structure as scale-space and extract scale sequence (S^2) feature by 3D convolution on the level axis of FPN. It is basically scale invariant feature and is built on high-resolution pyramid feature map for small objects. Furthermore, the proposed S^2 feature can be extended to most object detection models based on FPN. We demonstrate the proposed S2 feature can improve the performance of both one-stage and two-stage detectors on MS COCO dataset. Based on the proposed S2 feature, we achieve upto 1.3% and 1.1% of AP improvement for YOLOv4-P5 and YOLOv4-P6, respectively. For Faster RCNN and Mask R-CNN, we observe upto 2.0% and 1.6% of AP improvement with the suggested S^2 feature, respectively.

arXiv:2208.11356

Towards Efficient Use of Multi-Scale Features in Transformer-Based Object Detectors

Multi-scale features have been proven highly effective for object detection but often come with huge and even prohibitive extra computation costs, especially for the recent Transformer-based detectors. In this paper, we propose Iterative Multi-scale Feature Aggregation (IMFA) -- a generic paradigm that enables efficient use of multi-scale features in Transformer-based object detectors. The core idea is to exploit sparse multi-scale features from just a few crucial locations, and it is achieved with two novel designs. First, IMFA rearranges the Transformer encoder-decoder pipeline so that the encoded features can be iteratively updated based on the detection predictions. Second, IMFA sparsely samples scale-adaptive features for refined detection from just a few keypoint locations under the guidance of prior detection predictions. As a result, the sampled multi-scale features are sparse yet still highly beneficial for object detection. Extensive experiments show that the proposed IMFA boosts the performance of multiple Transformer-based object detectors significantly yet with only slight computational overhead.

arXiv:2208.11112공식 코드 · Papers with Code

DeepInteraction: 3D Object Detection via Modality Interaction

Existing top-performance 3D object detectors typically rely on the multi-modal fusion strategy. This design is however fundamentally restricted due to overlooking the modality-specific useful information and finally hampering the model performance. To address this limitation, in this work we introduce a novel modality interaction strategy where individual per-modality representations are learned and maintained throughout for enabling their unique characteristics to be exploited during object detection. To realize this proposed strategy, we design a DeepInteraction architecture characterized by a multi-modal representational interaction encoder and a multi-modal predictive interaction decoder. Experiments on the large-scale nuScenes dataset show that our proposed method surpasses all prior arts often by a large margin. Crucially, our method is ranked at the first position at the highly competitive nuScenes object detection leaderboard.

arXiv:2208.10976

Quality Matters: Embracing Quality Clues for Robust 3D Multi-Object Tracking

3D Multi-Object Tracking (MOT) has achieved tremendous achievement thanks to the rapid development of 3D object detection and 2D MOT. Recent advanced works generally employ a series of object attributes, e.g., position, size, velocity, and appearance, to provide the clues for the association in 3D MOT. However, these cues may not be reliable due to some visual noise, such as occlusion and blur, leading to tracking performance bottleneck. To reveal the dilemma, we conduct extensive empirical analysis to expose the key bottleneck of each clue and how they correlate with each other. The analysis results motivate us to efficiently absorb the merits among all cues, and adaptively produce an optimal tacking manner. Specifically, we present Location and Velocity Quality Learning, which efficiently guides the network to estimate the quality of predicted object attributes. Based on these quality estimations, we propose a quality-aware object association (QOA) strategy to leverage the quality score as an important reference factor for achieving robust association. Despite its simplicity, extensive experiments indicate that the proposed strategy significantly boosts tracking performance by 2.2% AMOTA and our method outperforms all existing state-of-the-art works on nuScenes by a large margin. Moreover, QTrack achieves 48.0% and 51.1% AMOTA tracking performance on the nuScenes validation and test sets, which significantly reduces the performance gap between pure camera and LiDAR based trackers.

arXiv:2208.10781

Object Detection in Aerial Images with Uncertainty-Aware Graph Network

In this work, we propose a novel uncertainty-aware object detection framework with a structured-graph, where nodes and edges are denoted by objects and their spatial-semantic similarities, respectively. Specifically, we aim to consider relationships among objects for effectively contextualizing them. To achieve this, we first detect objects and then measure their semantic and spatial distances to construct an object graph, which is then represented by a graph neural network (GNN) for refining visual CNN features for objects. However, refining CNN features and detection results of every object are inefficient and may not be necessary, as that include correct predictions with low uncertainties. Therefore, we propose to handle uncertain objects by not only transferring the representation from certain objects (sources) to uncertain objects (targets) over the directed graph, but also improving CNN features only on objects regarded as uncertain with their representational outputs from the GNN. Furthermore, we calculate a training loss by giving larger weights on uncertain objects, to concentrate on improving uncertain object predictions while maintaining high performances on certain objects. We refer to our model as Uncertainty-Aware Graph network for object DETection (UAGDet). We then experimentally validate ours on the challenging large-scale aerial image dataset, namely DOTA, that consists of lots of objects with small to large sizes in an image, on which ours improves the performance of the existing object detection network.

arXiv:2208.10773

Adversarial Vulnerability of Temporal Feature Networks for Object Detection

Taking into account information across the temporal domain helps to improve environment perception in autonomous driving. However, it has not been studied so far whether temporally fused neural networks are vulnerable to deliberately generated perturbations, i.e. adversarial attacks, or whether temporal history is an inherent defense against them. In this work, we study whether temporal feature networks for object detection are vulnerable to universal adversarial attacks. We evaluate attacks of two types: imperceptible noise for the whole image and locally-bound adversarial patch. In both cases, perturbations are generated in a white-box manner using PGD. Our experiments confirm, that attacking even a portion of a temporal input suffices to fool the network. We visually assess generated perturbations to gain insights into the functioning of attacks. To enhance the robustness, we apply adversarial training using 5-PGD. Our experiments on KITTI and nuScenes datasets demonstrate, that a model robustified via K-PGD is able to withstand the studied attacks while keeping the mAP-based performance comparable to that of an unattacked model.

arXiv:2208.10760

How good are deep models in understanding the generated images?

My goal in this paper is twofold: to study how well deep models can understand the images generated by DALL-E 2 and Midjourney, and to quantitatively evaluate these generative models. Two sets of generated images are collected for object recognition and visual question answering (VQA) tasks. On object recognition, the best model, out of 10 state-of-the-art object recognition models, achieves about 60\% and 80\% top-1 and top-5 accuracy, respectively. These numbers are much lower than the best accuracy on the ImageNet dataset (91\% and 99\%). On VQA, the OFA model scores 77.3\% on answering 241 binary questions across 50 images. This model scores 94.7\% on the binary VQA-v2 dataset. Humans are able to recognize the generated images and answer questions on them easily. We conclude that a) deep models struggle to understand the generated content, and may do better after fine-tuning, and b) there is a large distribution shift between the generated images and the real photographs. The distribution shift appears to be category-dependent. Data is available at: https://drive.google.com/file/d/1n2nCiaXtYJRRF2R73-LNE3zggeU_HeH0/view?usp=sharing.

arXiv:2208.10056

Minkowski Tracker: A Sparse Spatio-Temporal R-CNN for Joint Object Detection and Tracking

Recent research in multi-task learning reveals the benefit of solving related problems in a single neural network. 3D object detection and multi-object tracking (MOT) are two heavily intertwined problems predicting and associating an object instance location across time. However, most previous works in 3D MOT treat the detector as a preceding separated pipeline, disjointly taking the output of the detector as an input to the tracker. In this work, we present Minkowski Tracker, a sparse spatio-temporal R-CNN that jointly solves object detection and tracking. Inspired by region-based CNN (R-CNN), we propose to solve tracking as a second stage of the object detector R-CNN that predicts assignment probability to tracks. First, Minkowski Tracker takes 4D point clouds as input to generate a spatio-temporal Bird's-eye-view (BEV) feature map through a 4D sparse convolutional encoder network. Then, our proposed TrackAlign aggregates the track region-of-interest (ROI) features from the BEV features. Finally, Minkowski Tracker updates the track and its confidence score based on the detection-to-track match probability predicted from the ROI features. We show in large-scale experiments that the overall performance gain of our method is due to four factors: 1. The temporal reasoning of the 4D encoder improves the detection performance 2. The multi-task learning of object detection and MOT jointly enhances each other 3. The detection-to-track match score learns implicit motion model to enhance track assignment 4. The detection-to-track match score improves the quality of the track confidence score. As a result, Minkowski Tracker achieved the state-of-the-art performance on Nuscenes dataset tracking task without hand-designed motion models.

arXiv:2208.10035공식 코드 · Papers with Code

A Simple Baseline for Multi-Camera 3D Object Detection

3D object detection with surrounding cameras has been a promising direction for autonomous driving. In this paper, we present SimMOD, a Simple baseline for Multi-camera Object Detection, to solve the problem. To incorporate multi-view information as well as build upon previous efforts on monocular 3D object detection, the framework is built on sample-wise object proposals and designed to work in a two-stage manner. First, we extract multi-scale features and generate the perspective object proposals on each monocular image. Second, the multi-view proposals are aggregated and then iteratively refined with multi-view and multi-scale visual features in the DETR3D-style. The refined proposals are end-to-end decoded into the detection results. To further boost the performance, we incorporate the auxiliary branches alongside the proposal generation to enhance the feature learning. Also, we design the methods of target filtering and teacher forcing to promote the consistency of two-stage training. We conduct extensive experiments on the 3D object detection benchmark of nuScenes to demonstrate the effectiveness of SimMOD and achieve new state-of-the-art performance. Code will be available at https://github.com/zhangyp15/SimMOD.

arXiv:2208.10002

TransNet: Category-Level Transparent Object Pose Estimation

Transparent objects present multiple distinct challenges to visual perception systems. First, their lack of distinguishing visual features makes transparent objects harder to detect and localize than opaque objects. Even humans find certain transparent surfaces with little specular reflection or refraction, e.g. glass doors, difficult to perceive. A second challenge is that common depth sensors typically used for opaque object perception cannot obtain accurate depth measurements on transparent objects due to their unique reflective properties. Stemming from these challenges, we observe that transparent object instances within the same category (e.g. cups) look more similar to each other than to ordinary opaque objects of that same category. Given this observation, the present paper sets out to explore the possibility of category-level transparent object pose estimation rather than instance-level pose estimation. We propose TransNet, a two-stage pipeline that learns to estimate category-level transparent object pose using localized depth completion and surface normal estimation. TransNet is evaluated in terms of pose estimation accuracy on a recent, large-scale transparent object dataset and compared to a state-of-the-art category-level pose estimation approach. Results from this comparison demonstrate that TransNet achieves improved pose estimation accuracy on transparent objects and key findings from the included ablation studies suggest future directions for performance improvements.

arXiv:2208.09870공식 코드 · Papers with Code

Objects Can Move: 3D Change Detection by Geometric Transformation Constistency

AR/VR applications and robots need to know when the scene has changed. An example is when objects are moved, added, or removed from the scene. We propose a 3D object discovery method that is based only on scene changes. Our method does not need to encode any assumptions about what is an object, but rather discovers objects by exploiting their coherent move. Changes are initially detected as differences in the depth maps and segmented as objects if they undergo rigid motions. A graph cut optimization propagates the changing labels to geometrically consistent regions. Experiments show that our method achieves state-of-the-art performance on the 3RScan dataset against competitive baselines. The source code of our method can be found at https://github.com/katadam/ObjectsCanMove.

arXiv:2208.09829

CenDerNet: Center and Curvature Representations for Render-and-Compare 6D Pose Estimation

We introduce CenDerNet, a framework for 6D pose estimation from multi-view images based on center and curvature representations. Finding precise poses for reflective, textureless objects is a key challenge for industrial robotics. Our approach consists of three stages: First, a fully convolutional neural network predicts center and curvature heatmaps for each view; Second, center heatmaps are used to detect object instances and find their 3D centers; Third, 6D object poses are estimated using 3D centers and curvature heatmaps. By jointly optimizing poses across views using a render-and-compare approach, our method naturally handles occlusions and object symmetries. We show that CenDerNet outperforms previous methods on two industry-relevant datasets: DIMO and T-LESS.

arXiv:2208.09686공식 코드 · Papers with Code

YOLOV: Making Still Image Object Detectors Great at Video Object Detection

Video object detection (VID) is challenging because of the high variation of object appearance as well as the diverse deterioration in some frames. On the positive side, the detection in a certain frame of a video, compared with that in a still image, can draw support from other frames. Hence, how to aggregate features across different frames is pivotal to VID problem. Most of existing aggregation algorithms are customized for two-stage detectors. However, these detectors are usually computationally expensive due to their two-stage nature. This work proposes a simple yet effective strategy to address the above concerns, which costs marginal overheads with significant gains in accuracy. Concretely, different from traditional two-stage pipeline, we select important regions after the one-stage detection to avoid processing massive low-quality candidates. Besides, we evaluate the relationship between a target frame and reference frames to guide the aggregation. We conduct extensive experiments and ablation studies to verify the efficacy of our design, and reveal its superiority over other state-of-the-art VID approaches in both effectiveness and efficiency. Our YOLOX-based model can achieve promising performance (\emph{e.g.}, 87.5\% AP50 at over 30 FPS on the ImageNet VID dataset on a single 2080Ti GPU), making it attractive for large-scale or real-time applications. The implementation is simple, we have made the demo codes and models available at \url{https://github.com/YuHengsss/YOLOV}.

arXiv:2208.09668

Generalised Co-Salient Object Detection

We propose a new setting that relaxes an assumption in the conventional Co-Salient Object Detection (CoSOD) setting by allowing the presence of "noisy images" which do not show the shared co-salient object. We call this new setting Generalised Co-Salient Object Detection (GCoSOD). We propose a novel random sampling based Generalised CoSOD Training (GCT) strategy to distill the awareness of inter-image absence of co-salient objects into CoSOD models. It employs a Diverse Sampling Self-Supervised Learning (DS3L) that, in addition to the provided supervised co-salient label, introduces additional self-supervised labels for noisy images (being null, that no co-salient object is present). Further, the random sampling process inherent in GCT enables the generation of a high-quality uncertainty map highlighting potential false-positive predictions at instance level. To evaluate the performance of CoSOD models under the GCoSOD setting, we propose two new testing datasets, namely CoCA-Common and CoCA-Zero, where a common salient object is partially present in the former and completely absent in the latter. Extensive experiments demonstrate that our proposed method significantly improves the performance of CoSOD models in terms of the performance under the GCoSOD setting as well as the model calibration degrees.

논문 ID: document/9852199

LMOT: Efficient Light-Weight Detection and Tracking in Crowds

Multi-object tracking is a vital component in various robotics and computer vision applications. However, existing multi-object tracking techniques trade off computation runtime for tracking accuracy leading to challenges in deploying such pipelines in real-time applications. This paper introduces a novel real-time model, LMOT, i.e., Light-weight Multi-Object Tracker, that performs joint pedestrian detection and tracking. LMOT introduces a simplified DLA-34 encoder network to extract detection features for the current image that are computationally efficient. Furthermore, we generate efficient tracking features using a linear transformer for the prior image frame and its corresponding detection heatmap. After that, LMOT fuses both detection and tracking feature maps in a multi-layer scheme and performs a two-stage online data association relying on the Kalman filter to generate tracklets. We evaluated our model on the challenging real-world MOT16/17/20 datasets, showing LMOT significantly outperforms the state-of-the-art trackers concerning runtime while maintaining high robustness. LMOT is approximately ten times faster than state-of-the-art trackers while being only 3.8% behind in performance accuracy on average leading to a much computationally lighter model.

arXiv:2208.09480

Neural Light Field Estimation for Street Scenes with Differentiable Virtual Object Insertion

We consider the challenging problem of outdoor lighting estimation for the goal of photorealistic virtual object insertion into photographs. Existing works on outdoor lighting estimation typically simplify the scene lighting into an environment map which cannot capture the spatially-varying lighting effects in outdoor scenes. In this work, we propose a neural approach that estimates the 5D HDR light field from a single image, and a differentiable object insertion formulation that enables end-to-end training with image-based losses that encourage realism. Specifically, we design a hybrid lighting representation tailored to outdoor scenes, which contains an HDR sky dome that handles the extreme intensity of the sun, and a volumetric lighting representation that models the spatially-varying appearance of the surrounding scene. With the estimated lighting, our shadow-aware object insertion is fully differentiable, which enables adversarial training over the composited image to provide additional supervisory signal to the lighting prediction. We experimentally demonstrate that our hybrid lighting representation is more performant than existing outdoor lighting estimation methods. We further show the benefits of our AR object insertion in an autonomous driving application, where we obtain performance gains for a 3D object detector when trained on our augmented data.

arXiv:2208.09463공식 코드 · Papers with Code

Temporal View Synthesis of Dynamic Scenes through 3D Object Motion Estimation with Multi-Plane Images

The challenge of graphically rendering high frame-rate videos on low compute devices can be addressed through periodic prediction of future frames to enhance the user experience in virtual reality applications. This is studied through the problem of temporal view synthesis (TVS), where the goal is to predict the next frames of a video given the previous frames and the head poses of the previous and the next frames. In this work, we consider the TVS of dynamic scenes in which both the user and objects are moving. We design a framework that decouples the motion into user and object motion to effectively use the available user motion while predicting the next frames. We predict the motion of objects by isolating and estimating the 3D object motion in the past frames and then extrapolating it. We employ multi-plane images (MPI) as a 3D representation of the scenes and model the object motion as the 3D displacement between the corresponding points in the MPI representation. In order to handle the sparsity in MPIs while estimating the motion, we incorporate partial convolutions and masked correlation layers to estimate corresponding points. The predicted object motion is then integrated with the given user or camera motion to generate the next frame. Using a disocclusion infilling module, we synthesize the regions uncovered due to the camera and object motion. We develop a new synthetic dataset for TVS of dynamic scenes consisting of 800 videos at full HD resolution. We show through experiments on our dataset and the MPI Sintel dataset that our model outperforms all the competing methods in the literature.

arXiv:2208.09446공식 코드 · Papers with Code

MonoSIM: Simulating Learning Behaviors of Heterogeneous Point Cloud Object Detectors for Monocular 3D Object Detection

Monocular 3D object detection is a fundamental but very important task to many applications including autonomous driving, robotic grasping and augmented reality. Existing leading methods tend to estimate the depth of the input image first, and detect the 3D object based on point cloud. This routine suffers from the inherent gap between depth estimation and object detection. Besides, the prediction error accumulation would also affect the performance. In this paper, a novel method named MonoSIM is proposed. The insight behind introducing MonoSIM is that we propose to simulate the feature learning behaviors of a point cloud based detector for monocular detector during the training period. Hence, during inference period, the learned features and prediction would be similar to the point cloud based detector as possible. To achieve it, we propose one scene-level simulation module, one RoI-level simulation module and one response-level simulation module, which are progressively used for the detector's full feature learning and prediction pipeline. We apply our method to the famous M3D-RPN detector and CaDDN detector, conducting extensive experiments on KITTI and Waymo Open datasets. Results show that our method consistently improves the performance of different monocular detectors for a large margin without changing their network architectures. Our codes will be publicly available at https://github.com/sunh18/MonoSIM}{https://github.com/sunh18/MonoSIM.