PyTorchKR Papers

최신 논문

총 9,714편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2201.12828

Comprehensive Saliency Fusion for Object Co-segmentation

Object co-segmentation has drawn significant attention in recent years, thanks to its clarity on the expected foreground, the shared object in a group of images. Saliency fusion has been one of the promising ways to carry it out. However, prior works either fuse saliency maps of the same image or saliency maps of different images to extract the expected foregrounds. Also, they rely on hand-crafted saliency extraction and correspondence processes in most cases. This paper revisits the problem and proposes fusing saliency maps of both the same image and different images. It also leverages advances in deep learning for the saliency extraction and correspondence processes. Hence, we call it comprehensive saliency fusion. Our experiments reveal that our approach achieves much-improved object co-segmentation results compared to prior works on important benchmark datasets such as iCoseg, MSRC, and Internet Images.

arXiv:2201.12723

A Frustratingly Simple Approach for End-to-End Image Captioning

Image Captioning is a fundamental task to join vision and language, concerning about cross-modal understanding and text generation. Recent years witness the emerging attention on image captioning. Most of existing works follow a traditional two-stage training paradigm. Before training the captioning models, an extra object detector is utilized to recognize the objects in the image at first. However, they require sizeable datasets with fine-grained object annotation for training the object detector, which is a daunting task. In addition, the errors of the object detectors are easy to propagate to the following captioning models, degenerating models' performance. To alleviate such defects, we propose a frustratingly simple but highly effective end-to-end image captioning framework, Visual Conditioned GPT (VC-GPT), by connecting the pre-trained visual encoder (CLIP-ViT) and language decoder (GPT2). Different from the vanilla connection method that directly inserts the cross-attention modules into GPT2, we come up with a self-ensemble cross-modal fusion mechanism that comprehensively considers both the single- and cross-modal knowledge. As a result, we do not need extra object detectors for model training. Experimental results conducted on three popular image captioning benchmarks (MSCOCO, Flickr30k and NoCaps) demonstrate that our VC-GPT achieves either the best or the second-best performance across all evaluation metrics over extensive baseline systems.

arXiv:2201.12716공식 코드 · Papers with Code

You Only Demonstrate Once: Category-Level Manipulation from Single Visual Demonstration

Promising results have been achieved recently in category-level manipulation that generalizes across object instances. Nevertheless, it often requires expensive real-world data collection and manual specification of semantic keypoints for each object category and task. Additionally, coarse keypoint predictions and ignoring intermediate action sequences hinder adoption in complex manipulation tasks beyond pick-and-place. This work proposes a novel, category-level manipulation framework that leverages an object-centric, category-level representation and model-free 6 DoF motion tracking. The canonical object representation is learned solely in simulation and then used to parse a category-level, task trajectory from a single demonstration video. The demonstration is reprojected to a target trajectory tailored to a novel object via the canonical representation. During execution, the manipulation horizon is decomposed into longrange, collision-free motion and last-inch manipulation. For the latter part, a category-level behavior cloning (CatBC) method leverages motion tracking to perform closed-loop control. CatBC follows the target trajectory, projected from the demonstration and anchored to a dynamically selected category-level coordinate frame. The frame is automatically selected along the manipulation horizon by a local attention mechanism. This framework allows to teach different manipulation strategies by solely providing a single demonstration, without complicated manual programming. Extensive experiments demonstrate its efficacy in a range of challenging industrial tasks in highprecision assembly, which involve learning complex, long-horizon policies. The process exhibits robustness against uncertainty due to dynamics as well as generalization across object instances and scene configurations. The supplementary video is available at https://www.youtube.com/watch?v=WAr8ZY3mYyw

arXiv:2201.12558공식 코드 · Papers with Code

The KFIoU Loss for Rotated Object Detection

Differing from the well-developed horizontal object detection area whereby the computing-friendly IoU based loss is readily adopted and well fits with the detection metrics. In contrast, rotation detectors often involve a more complicated loss based on SkewIoU which is unfriendly to gradient-based training. In this paper, we propose an effective approximate SkewIoU loss based on Gaussian modeling and Gaussian product, which mainly consists of two items. The first term is a scale-insensitive center point loss, which is used to quickly narrow the distance between the center points of the two bounding boxes. In the distance-independent second term, the product of the Gaussian distributions is adopted to inherently mimic the mechanism of SkewIoU by its definition, and show its alignment with the SkewIoU loss at trend-level within a certain distance (i.e. within 9 pixels). This is in contrast to recent Gaussian modeling based rotation detectors e.g. GWD loss and KLD loss that involve a human-specified distribution distance metric which require additional hyperparameter tuning that vary across datasets and detectors. The resulting new loss called KFIoU loss is easier to implement and works better compared with exact SkewIoU loss, thanks to its full differentiability and ability to handle the non-overlapping cases. We further extend our technique to the 3-D case which also suffers from the same issues as 2-D. Extensive results on various public datasets (2-D/3-D, aerial/text/face images) with different base detectors show the effectiveness of our approach.

arXiv:2201.13178공식 코드 · Papers with Code

Few-Shot Backdoor Attacks on Visual Object Tracking

Visual object tracking (VOT) has been widely adopted in mission-critical applications, such as autonomous driving and intelligent surveillance systems. In current practice, third-party resources such as datasets, backbone networks, and training platforms are frequently used to train high-performance VOT models. Whilst these resources bring certain convenience, they also introduce new security threats into VOT models. In this paper, we reveal such a threat where an adversary can easily implant hidden backdoors into VOT models by tempering with the training process. Specifically, we propose a simple yet effective few-shot backdoor attack (FSBA) that optimizes two losses alternately: 1) a \emph{feature loss} defined in the hidden feature space, and 2) the standard \emph{tracking loss}. We show that, once the backdoor is embedded into the target model by our FSBA, it can trick the model to lose track of specific objects even when the \emph{trigger} only appears in one or a few frames. We examine our attack in both digital and physical-world settings and show that it can significantly degrade the performance of state-of-the-art VOT trackers. We also show that our attack is resistant to potential defenses, highlighting the vulnerability of VOT models to potential backdoor attacks.

arXiv:2201.12047

Exploring Object-Aware Attention Guided Frame Association for RGB-D SLAM

Deep learning models as an emerging topic have shown great progress in various fields. Especially, visualization tools such as class activation mapping methods provided visual explanation on the reasoning of convolutional neural networks (CNNs). By using the gradients of the network layers, it is possible to demonstrate where the networks pay attention during a specific image recognition task. Moreover, these gradients can be integrated with CNN features for localizing more generalized task dependent attentive (salient) objects in scenes. Despite this progress, there is not much explicit usage of this gradient (network attention) information to integrate with CNN representations for object semantics. This can be very useful for visual tasks such as simultaneous localization and mapping (SLAM) where CNN representations of spatially attentive object locations may lead to improved performance. Therefore, in this work, we propose the use of task specific network attention for RGB-D indoor SLAM. To do so, we integrate layer-wise object attention information (layer gradients) with CNN layer representations to improve frame association performance in an RGB-D indoor SLAM method. Experiments show promising results with improved performance over the baseline.

arXiv:2201.11871

Infrastructure-Based Object Detection and Tracking for Cooperative Driving Automation: A Survey

Object detection plays a fundamental role in enabling Cooperative Driving Automation (CDA), which is regarded as the revolutionary solution to addressing safety, mobility, and sustainability issues of contemporary transportation systems. Although current computer vision technologies could provide satisfactory object detection results in occlusion-free scenarios, the perception performance of onboard sensors could be inevitably limited by the range and occlusion. Owing to flexible position and pose for sensor installation, infrastructure-based detection and tracking systems can enhance the perception capability for connected vehicles and thus quickly become one of the most popular research topics. In this paper, we review the research progress for infrastructure-based object detection and tracking systems. Architectures of roadside perception systems based on different types of sensors are reviewed to show a high-level description of the workflows for infrastructure-based perception systems. Roadside sensors and different perception methodologies are reviewed and analyzed with detailed literature to provide a low-level explanation for specific methods followed by Datasets and Simulators to draw an overall landscape of infrastructure-based object detection and tracking methods. Discussions are conducted to point out current opportunities, open problems, and anticipated future trends.

arXiv:2201.12184공식 코드 · Papers with Code

A tomographic workflow to enable deep learning for X-ray based foreign object detection

Detection of unwanted (`foreign') objects within products is a common procedure in many branches of industry for maintaining production quality. X-ray imaging is a fast, non-invasive and widely applicable method for foreign object detection. Deep learning has recently emerged as a powerful approach for recognizing patterns in radiographs (i.e., X-ray images), enabling automated X-ray based foreign object detection. However, these methods require a large number of training examples and manual annotation of these examples is a subjective and laborious task. In this work, we propose a Computed Tomography (CT) based method for producing training data for supervised learning of foreign object detection, with minimal labour requirements. In our approach, a few representative objects are CT scanned and reconstructed in 3D. The radiographs that have been acquired as part of the CT-scan data serve as input for the machine learning method. High-quality ground truth locations of the foreign objects are obtained through accurate 3D reconstructions and segmentations. Using these segmented volumes, corresponding 2D segmentations are obtained by creating virtual projections. We outline the benefits of objectively and reproducibly generating training data in this way compared to conventional radiograph annotation. In addition, we show how the accuracy depends on the number of objects used for the CT reconstructions. The results show that in this workflow generally only a relatively small number of representative objects (i.e., fewer than 10) are needed to achieve adequate detection performance in an industrial setting. Moreover, for real experimental data we show that the workflow leads to higher foreign object detection accuracies than with standard radiograph annotation.

arXiv:2201.11547

ASOC: Adaptive Self-aware Object Co-localization

The primary goal of this paper is to localize objects in a group of semantically similar images jointly, also known as the object co-localization problem. Most related existing works are essentially weakly-supervised, relying prominently on the neighboring images' weak-supervision. Although weak supervision is beneficial, it is not entirely reliable, for the results are quite sensitive to the neighboring images considered. In this paper, we combine it with a self-awareness phenomenon to mitigate this issue. By self-awareness here, we refer to the solution derived from the image itself in the form of saliency cue, which can also be unreliable if applied alone. Nevertheless, combining these two paradigms together can lead to a better co-localization ability. Specifically, we introduce a dynamic mediator that adaptively strikes a proper balance between the two static solutions to provide an optimal solution. Therefore, we call this method \textit{ASOC}: Adaptive Self-aware Object Co-localization. We perform exhaustive experiments on several benchmark datasets and validate that weak-supervision supplemented with self-awareness has superior performance outperforming several compared competing methods.

arXiv:2201.11460공식 코드 · Papers with Code

RelTR: Relation Transformer for Scene Graph Generation

Different objects in the same scene are more or less related to each other, but only a limited number of these relationships are noteworthy. Inspired by DETR, which excels in object detection, we view scene graph generation as a set prediction problem and propose an end-to-end scene graph generation model RelTR which has an encoder-decoder architecture. The encoder reasons about the visual feature context while the decoder infers a fixed-size set of triplets subject-predicate-object using different types of attention mechanisms with coupled subject and object queries. We design a set prediction loss performing the matching between the ground truth and predicted triplets for the end-to-end training. In contrast to most existing scene graph generation methods, RelTR is a one-stage method that predicts a set of relationships directly only using visual appearance without combining entities and labeling all possible predicates. Extensive experiments on the Visual Genome and Open Images V6 datasets demonstrate the superior performance and fast inference of our model.

arXiv:2201.10830공식 코드 · Papers with Code

MonoDistill: Learning Spatial Features for Monocular 3D Object Detection

3D object detection is a fundamental and challenging task for 3D scene understanding, and the monocular-based methods can serve as an economical alternative to the stereo-based or LiDAR-based methods. However, accurately detecting objects in the 3D space from a single image is extremely difficult due to the lack of spatial cues. To mitigate this issue, we propose a simple and effective scheme to introduce the spatial information from LiDAR signals to the monocular 3D detectors, without introducing any extra cost in the inference phase. In particular, we first project the LiDAR signals into the image plane and align them with the RGB images. After that, we use the resulting data to train a 3D detector (LiDAR Net) with the same architecture as the baseline model. Finally, this LiDAR Net can serve as the teacher to transfer the learned knowledge to the baseline model. Experimental results show that the proposed method can significantly boost the performance of the baseline model and ranks the $1^{st}$ place among all monocular-based methods on the KITTI benchmark. Besides, extensive ablation studies are conducted, which further prove the effectiveness of each part of our designs and illustrate what the baseline model has learned from the LiDAR Net. Our code will be released at \url{https://github.com/monster-ghost/MonoDistill}.

arXiv:2201.10734공식 코드 · Papers with Code

CrossRectify: Leveraging Disagreement for Semi-supervised Object Detection

Semi-supervised object detection has recently achieved substantial progress. As a mainstream solution, the self-labeling-based methods train the detector on both labeled data and unlabeled data with pseudo labels predicted by the detector itself, but their performances are always limited. Through experimental analysis, we reveal the underlying reason is that the detector is misguided by the incorrect pseudo labels predicted by itself (dubbed self-errors). These self-errors can hurt performance even worse than random-errors, and can be neither discerned nor rectified during the self-labeling process. In this paper, we propose an effective detection framework named CrossRectify, to obtain accurate pseudo labels by simultaneously training two detectors with different initial parameters. Specifically, the proposed approach leverages the disagreements between detectors to discern the self-errors and refines the pseudo label quality by the proposed cross-rectifying mechanism. Extensive experiments show that CrossRectify achieves outperforming performances over various detector structures on 2D and 3D detection benchmarks.

arXiv:2201.10162

Semantically Video Coding: Instill Static-Dynamic Clues into Structured Bitstream for AI Tasks

Traditional media coding schemes typically encode image/video into a semantic-unknown binary stream, which fails to directly support downstream intelligent tasks at the bitstream level. Semantically Structured Image Coding (SSIC) framework makes the first attempt to enable decoding-free or partial-decoding image intelligent task analysis via a Semantically Structured Bitstream (SSB). However, the SSIC only considers image coding and its generated SSB only contains the static object information. In this paper, we extend the idea of semantically structured coding from video coding perspective and propose an advanced Semantically Structured Video Coding (SSVC) framework to support heterogeneous intelligent applications. Video signals contain more rich dynamic motion information and exist more redundancy due to the similarity between adjacent frames. Thus, we present a reformulation of semantically structured bitstream (SSB) in SSVC which contains both static object characteristics and dynamic motion clues. Specifically, we introduce optical flow to encode continuous motion information and reduce cross-frame redundancy via a predictive coding architecture, then the optical flow and residual information are reorganized into SSB, which enables the proposed SSVC could better adaptively support video-based downstream intelligent applications. Extensive experiments demonstrate that the proposed SSVC framework could directly support multiple intelligent tasks just depending on a partially decoded bitstream. This avoids the full bitstream decompression and thus significantly saves bitrate/bandwidth consumption for intelligent analytics. We verify this point on the tasks of image object detection, pose estimation, video action recognition, video object segmentation, etc.

arXiv:2201.09574

Multi-Scale Iterative Refinement Network for RGB-D Salient Object Detection

The extensive research leveraging RGB-D information has been exploited in salient object detection. However, salient visual cues appear in various scales and resolutions of RGB images due to semantic gaps at different feature levels. Meanwhile, similar salient patterns are available in cross-modal depth images as well as multi-scale versions. Cross-modal fusion and multi-scale refinement are still an open problem in RGB-D salient object detection task. In this paper, we begin by introducing top-down and bottom-up iterative refinement architecture to leverage multi-scale features, and then devise attention based fusion module (ABF) to address on cross-modal correlation. We conduct extensive experiments on seven public datasets. The experimental results show the effectiveness of our devised method

arXiv:2201.09208

Design of Sensor Fusion Driver Assistance System for Active Pedestrian Safety

In this paper, we present a parallel architecture for a sensor fusion detection system that combines a camera and 1D light detection and ranging (lidar) sensor for object detection. The system contains two object detection methods, one based on an optical flow, and the other using lidar. The two sensors can effectively complement the defects of the other. The accurate longitudinal accuracy of the object's location and its lateral movement information can be achieved simultaneously. Using a spatio-temporal alignment and a policy of sensor fusion, we completed the development of a fusion detection system with high reliability at distances of up to 20 m. Test results show that the proposed system achieves a high level of accuracy for pedestrian or object detection in front of a vehicle, and has high robustness to special environments.

arXiv:2201.09207

Visual Object Tracking on Multi-modal RGB-D Videos: A Review

The development of visual object tracking has continued for decades. Recent years, as the wide accessibility of the low-cost RGBD sensors, the task of visual object tracking on RGB-D videos has drawn much attention. Compared to conventional RGB-only tracking, the RGB-D videos can provide more information that facilitates objecting tracking in some complicated scenarios. The goal of this review is to summarize the relative knowledge of the research filed of RGB-D tracking. To be specific, we will generalize the related RGB-D tracking benchmarking datasets as well as the corresponding performance measurements. Besides, the existing RGB-D tracking methods are summarized in the paper. Moreover, we discuss the possible future direction in the field of RGB-D tracking.

arXiv:2201.09354

Survey and Systematization of 3D Object Detection Models and Methods

Strong demand for autonomous vehicles and the wide availability of 3D sensors are continuously fueling the proposal of novel methods for 3D object detection. In this paper, we provide a comprehensive survey of recent developments from 2012-2021 in 3D object detection covering the full pipeline from input data, over data representation and feature extraction to the actual detection modules. We introduce fundamental concepts, focus on a broad range of different approaches that have emerged over the past decade, and propose a systematization that provides a practical framework for comparing these approaches with the goal of guiding future development, evaluation and application activities. Specifically, our survey and systematization of 3D object detection models and methods can help researchers and practitioners to get a quick overview of the field by decomposing 3DOD solutions into more manageable pieces.

arXiv:2201.08812

DeepMix: Mobility-aware, Lightweight, and Hybrid 3D Object Detection for Headsets

Mobile headsets should be capable of understanding 3D physical environments to offer a truly immersive experience for augmented/mixed reality (AR/MR). However, their small form-factor and limited computation resources make it extremely challenging to execute in real-time 3D vision algorithms, which are known to be more compute-intensive than their 2D counterparts. In this paper, we propose DeepMix, a mobility-aware, lightweight, and hybrid 3D object detection framework for improving the user experience of AR/MR on mobile headsets. Motivated by our analysis and evaluation of state-of-the-art 3D object detection models, DeepMix intelligently combines edge-assisted 2D object detection and novel, on-device 3D bounding box estimations that leverage depth data captured by headsets. This leads to low end-to-end latency and significantly boosts detection accuracy in mobile scenarios. A unique feature of DeepMix is that it fully exploits the mobility of headsets to fine-tune detection results and boost detection accuracy. To the best of our knowledge, DeepMix is the first 3D object detection that achieves 30 FPS (an end-to-end latency much lower than the 100 ms stringent requirement of interactive AR/MR). We implement a prototype of DeepMix on Microsoft HoloLens and evaluate its performance via both extensive controlled experiments and a user study with 30+ participants. DeepMix not only improves detection accuracy by 9.1--37.3% but also reduces end-to-end latency by 2.68--9.15x, compared to the baseline that uses existing 3D object detection models.

arXiv:2201.08763

Object Detection in Aerial Images: What Improves the Accuracy?

Object detection is a challenging and popular computer vision problem. The problem is even more challenging in aerial images due to significant variation in scale and viewpoint in a diverse set of object categories. Recently, deep learning-based object detection approaches have been actively explored for the problem of object detection in aerial images. In this work, we investigate the impact of Faster R-CNN for aerial object detection and explore numerous strategies to improve its performance for aerial images. We conduct extensive experiments on the challenging iSAID dataset. The resulting adapted Faster R-CNN obtains a significant mAP gain of 4.96% over its vanilla baseline counterpart on the iSAID validation set, demonstrating the impact of different strategies investigated in this work.

arXiv:2201.08683

A Comprehensive Study of Vision Transformers on Dense Prediction Tasks

Convolutional Neural Networks (CNNs), architectures consisting of convolutional layers, have been the standard choice in vision tasks. Recent studies have shown that Vision Transformers (VTs), architectures based on self-attention modules, achieve comparable performance in challenging tasks such as object detection and semantic segmentation. However, the image processing mechanism of VTs is different from that of conventional CNNs. This poses several questions about their generalizability, robustness, reliability, and texture bias when used to extract features for complex tasks. To address these questions, we study and compare VT and CNN architectures as feature extractors in object detection and semantic segmentation. Our extensive empirical results show that the features generated by VTs are more robust to distribution shifts, natural corruptions, and adversarial attacks in both tasks, whereas CNNs perform better at higher image resolutions in object detection. Furthermore, our results demonstrate that VTs in dense prediction tasks produce more reliable and less texture-biased predictions.