PyTorchKR Papers

최신 논문

총 9,714편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2011.10875

Transparent Object Tracking Benchmark

Visual tracking has achieved considerable progress in recent years. However, current research in the field mainly focuses on tracking of opaque objects, while little attention is paid to transparent object tracking. In this paper, we make the first attempt in exploring this problem by proposing a Transparent Object Tracking Benchmark (TOTB). Specifically, TOTB consists of 225 videos (86K frames) from 15 diverse transparent object categories. Each sequence is manually labeled with axis-aligned bounding boxes. To the best of our knowledge, TOTB is the first benchmark dedicated to transparent object tracking. In order to understand how existing trackers perform and to provide comparison for future research on TOTB, we extensively evaluate 25 state-of-the-art tracking algorithms. The evaluation results exhibit that more efforts are needed to improve transparent object tracking. Besides, we observe some nontrivial findings from the evaluation that are discrepant with some common beliefs in opaque object tracking. For example, we find that deeper features are not always good for improvements. Moreover, to encourage future research, we introduce a novel tracker, named TransATOM, which leverages transparency features for tracking and surpasses all 25 evaluated approaches by a large margin. By releasing TOTB, we expect to facilitate future research and application of transparent object tracking in both the academia and industry. The TOTB and evaluation results as well as TransATOM are available at https://hengfan2010.github.io/projects/TOTB.

arXiv:2011.10678공식 코드 · Papers with Code

Open-Vocabulary Object Detection Using Captions

Despite the remarkable accuracy of deep neural networks in object detection, they are costly to train and scale due to supervision requirements. Particularly, learning more object categories typically requires proportionally more bounding box annotations. Weakly supervised and zero-shot learning techniques have been explored to scale object detectors to more categories with less supervision, but they have not been as successful and widely adopted as supervised models. In this paper, we put forth a novel formulation of the object detection problem, namely open-vocabulary object detection, which is more general, more practical, and more effective than weakly supervised and zero-shot approaches. We propose a new method to train object detectors using bounding box annotations for a limited set of object categories, as well as image-caption pairs that cover a larger variety of objects at a significantly lower cost. We show that the proposed method can detect and localize objects for which no bounding box annotation is provided during training, at a significantly higher accuracy than zero-shot approaches. Meanwhile, objects with bounding box annotation can be detected almost as accurately as supervised methods, which is significantly better than weakly supervised baselines. Accordingly, we establish a new state of the art for scalable object detection.

arXiv:2011.10671공식 코드 · Papers with Code

A Review and Comparative Study on Probabilistic Object Detection in Autonomous Driving

Capturing uncertainty in object detection is indispensable for safe autonomous driving. In recent years, deep learning has become the de-facto approach for object detection, and many probabilistic object detectors have been proposed. However, there is no summary on uncertainty estimation in deep object detection, and existing methods are not only built with different network architectures and uncertainty estimation methods, but also evaluated on different datasets with a wide range of evaluation metrics. As a result, a comparison among methods remains challenging, as does the selection of a model that best suits a particular application. This paper aims to alleviate this problem by providing a review and comparative study on existing probabilistic object detection methods for autonomous driving applications. First, we provide an overview of generic uncertainty estimation in deep learning, and then systematically survey existing methods and evaluation metrics for probabilistic object detection. Next, we present a strict comparative study for probabilistic object detection based on an image detector and three public autonomous driving datasets. Finally, we present a discussion of the remaining challenges and future works. Code has been made available at https://github.com/asharakeh/pod_compare.git

arXiv:2011.10471

Online Descriptor Enhancement via Self-Labelling Triplets for Visual Data Association

Object-level data association is central to robotic applications such as tracking-by-detection and object-level simultaneous localization and mapping. While current learned visual data association methods outperform hand-crafted algorithms, many rely on large collections of domain-specific training examples that can be difficult to obtain without prior knowledge. Additionally, such methods often remain fixed during inference-time and do not harness observed information to better their performance. We propose a self-supervised method for incrementally refining visual descriptors to improve performance in the task of object-level visual data association. Our method optimizes deep descriptor generators online, by continuously training a widely available image classification network pre-trained with domain-independent data. We show that earlier layers in the network outperform later-stage layers for the data association task while also allowing for a 94% reduction in the number of parameters, enabling the online optimization. We show that self-labelling challenging triplets--choosing positive examples separated by large temporal distances and negative examples close in the descriptor space--improves the quality of the learned descriptors for the multi-object tracking task. Finally, we demonstrate that our approach surpasses other visual data-association methods applied to a tracking-by-detection task, and show that it provides better performance-gains when compared to other methods that attempt to adapt to observed information.

arXiv:2011.10278공식 코드 · Papers with Code

Joint Representation of Temporal Image Sequences and Object Motion for Video Object Detection

In this paper, we propose a new video object detector (VoD) method referred to as temporal feature aggregation and motion-aware VoD (TM-VoD), which produces a joint representation of temporal image sequences and object motion. The proposed TM-VoD aggregates visual feature maps extracted by convolutional neural networks applying the temporal attention gating and spatial feature alignment. This temporal feature aggregation is performed in two stages in a hierarchical fashion. In the first stage, the visual feature maps are fused at a pixel level via gated attention model. In the second stage, the proposed method aggregates the features after aligning the object features using temporal box offset calibration and weights them according to the cosine similarity measure. The proposed TM-VoD also finds the representation of the motion of objects in two successive steps. The pixel-level motion features are first computed based on the incremental changes between the adjacent visual feature maps. Then, box-level motion features are obtained from both the region of interest (RoI)-aligned pixel-level motion features and the sequential changes of the box coordinates. Finally, all these features are concatenated to produce a joint representation of the objects for VoD. The experiments conducted on the ImageNet VID dataset demonstrate that the proposed method outperforms existing VoD methods and achieves a performance comparable to that of state-of-the-art VoDs.

arXiv:2011.10287

Learning Object-Centric Video Models by Contrasting Sets

Contrastive, self-supervised learning of object representations recently emerged as an attractive alternative to reconstruction-based training. Prior approaches focus on contrasting individual object representations (slots) against one another. However, a fundamental problem with this approach is that the overall contrastive loss is the same for (i) representing a different object in each slot, as it is for (ii) (re-)representing the same object in all slots. Thus, this objective does not inherently push towards the emergence of object-centric representations in the slots. We address this problem by introducing a global, set-based contrastive loss: instead of contrasting individual slot representations against one another, we aggregate the representations and contrast the joined sets against one another. Additionally, we introduce attention-based encoders to this contrastive setup which simplifies training and provides interpretable object masks. Our results on two synthetic video datasets suggest that this approach compares favorably against previous contrastive methods in terms of reconstruction, future prediction and object separation performance.

arXiv:2011.10258

Cascade Attentive Dropout for Weakly Supervised Object Detection

Weakly supervised object detection (WSOD) aims to classify and locate objects with only image-level supervision. Many WSOD approaches adopt multiple instance learning as the initial model, which is prone to converge to the most discriminative object regions while ignoring the whole object, and therefore reduce the model detection performance. In this paper, a novel cascade attentive dropout strategy is proposed to alleviate the part domination problem, together with an improved global context module. We purposely discard attentive elements in both channel and space dimensions, and capture the inter-pixel and inter-channel dependencies to induce the model to better understand the global context. Extensive experiments have been conducted on the challenging PASCAL VOC 2007 benchmarks, which achieve 49.8% mAP and 66.0% CorLoc, outperforming state-of-the-arts.

arXiv:2011.10142

Cooperating RPN's Improve Few-Shot Object Detection

Learning to detect an object in an image from very few training examples - few-shot object detection - is challenging, because the classifier that sees proposal boxes has very little training data. A particularly challenging training regime occurs when there are one or two training examples. In this case, if the region proposal network (RPN) misses even one high intersection-over-union (IOU) training box, the classifier's model of how object appearance varies can be severely impacted. We use multiple distinct yet cooperating RPN's. Our RPN's are trained to be different, but not too different; doing so yields significant performance improvements over state of the art for COCO and PASCAL VOC in the very few-shot setting. This effect appears to be independent of the choice of classifier or dataset.

arXiv:2011.09315공식 코드 · Papers with Code

End-to-End Object Detection with Adaptive Clustering Transformer

End-to-end Object Detection with Transformer (DETR)proposes to perform object detection with Transformer and achieve comparable performance with two-stage object detection like Faster-RCNN. However, DETR needs huge computational resources for training and inference due to the high-resolution spatial input. In this paper, a novel variant of transformer named Adaptive Clustering Transformer(ACT) has been proposed to reduce the computation cost for high-resolution input. ACT cluster the query features adaptively using Locality Sensitive Hashing (LSH) and ap-proximate the query-key interaction using the prototype-key interaction. ACT can reduce the quadratic O(N2) complexity inside self-attention into O(NK) where K is the number of prototypes in each layer. ACT can be a drop-in module replacing the original self-attention module without any training. ACT achieves a good balance between accuracy and computation cost (FLOPs). The code is available as supplementary for the ease of experiment replication and verification. Code is released at \url{https://github.com/gaopengcuhk/SMCA-DETR/}

arXiv:2011.09157

Dense Contrastive Learning for Self-Supervised Visual Pre-Training

To date, most existing self-supervised learning methods are designed and optimized for image classification. These pre-trained models can be sub-optimal for dense prediction tasks due to the discrepancy between image-level prediction and pixel-level prediction. To fill this gap, we aim to design an effective, dense self-supervised learning method that directly works at the level of pixels (or local features) by taking into account the correspondence between local features. We present dense contrastive learning, which implements self-supervised learning by optimizing a pairwise contrastive (dis)similarity loss at the pixel level between two views of input images. Compared to the baseline method MoCo-v2, our method introduces negligible computation overhead (only <1% slower), but demonstrates consistently superior performance when transferring to downstream dense prediction tasks including object detection, semantic segmentation and instance segmentation; and outperforms the state-of-the-art methods by a large margin. Specifically, over the strong MoCo-v2 baseline, our method achieves significant improvements of 2.0% AP on PASCAL VOC object detection, 1.1% AP on COCO object detection, 0.9% AP on COCO instance segmentation, 3.0% mIoU on PASCAL VOC semantic segmentation and 1.8% mIoU on Cityscapes semantic segmentation. Code is available at: https://git.io/AdelaiDet

arXiv:2011.09427

Fast Motion Understanding with Spatiotemporal Neural Networks and Dynamic Vision Sensors

This paper presents a Dynamic Vision Sensor (DVS) based system for reasoning about high speed motion. As a representative scenario, we consider the case of a robot at rest reacting to a small, fast approaching object at speeds higher than 15m/s. Since conventional image sensors at typical frame rates observe such an object for only a few frames, estimating the underlying motion presents a considerable challenge for standard computer vision systems and algorithms. In this paper we present a method motivated by how animals such as insects solve this problem with their relatively simple vision systems. Our solution takes the event stream from a DVS and first encodes the temporal events with a set of causal exponential filters across multiple time scales. We couple these filters with a Convolutional Neural Network (CNN) to efficiently extract relevant spatiotemporal features. The combined network learns to output both the expected time to collision of the object, as well as the predicted collision point on a discretized polar grid. These critical estimates are computed with minimal delay by the network in order to react appropriately to the incoming object. We highlight the results of our system to a toy dart moving at 23.4m/s with a 24.73{\deg} error in ${\theta}$, 18.4mm average discretized radius prediction error, and 25.03% median time to collision prediction error.

arXiv:2011.08726

Modality-Buffet for Real-Time Object Detection

Real-time object detection in videos using lightweight hardware is a crucial component of many robotic tasks. Detectors using different modalities and with varying computational complexities offer different trade-offs. One option is to have a very lightweight model that can predict from all modalities at once for each frame. However, in some situations (e.g., in static scenes) it might be better to have a more complex but more accurate model and to extrapolate from previous predictions for the frames coming in at processing time. We formulate this task as a sequential decision making problem and use reinforcement learning (RL) to generate a policy that decides from the RGB input which detector out of a portfolio of different object detectors to take for the next prediction. The objective of the RL agent is to maximize the accuracy of the predictions per image. We evaluate the approach on the Waymo Open Dataset and show that it exceeds the performance of each single detector.

arXiv:2011.08534

A Divide et Impera Approach for 3D Shape Reconstruction from Multiple Views

Estimating the 3D shape of an object from a single or multiple images has gained popularity thanks to the recent breakthroughs powered by deep learning. Most approaches regress the full object shape in a canonical pose, possibly extrapolating the occluded parts based on the learned priors. However, their viewpoint invariant technique often discards the unique structures visible from the input images. In contrast, this paper proposes to rely on viewpoint variant reconstructions by merging the visible information from the given views. Our approach is divided into three steps. Starting from the sparse views of the object, we first align them into a common coordinate system by estimating the relative pose between all the pairs. Then, inspired by the traditional voxel carving, we generate an occupancy grid of the object taken from the silhouette on the images and their relative poses. Finally, we refine the initial reconstruction to build a clean 3D model which preserves the details from each viewpoint. To validate the proposed method, we perform a comprehensive evaluation on the ShapeNet reference benchmark in terms of relative pose estimation and 3D shape reconstruction.

arXiv:2011.08529공식 코드 · Papers with Code

Slender Object Detection: Diagnoses and Improvements

In this paper, we are concerned with the detection of a particular type of objects with extreme aspect ratios, namely \textbf{slender objects}. In real-world scenarios, slender objects are actually very common and crucial to the objective of a detection system. However, this type of objects has been largely overlooked by previous object detection algorithms. Upon our investigation, for a classical object detection method, a drastic drop of $18.9\%$ mAP on COCO is observed, if solely evaluated on slender objects. Therefore, we systematically study the problem of slender object detection in this work. Accordingly, an analytical framework with carefully designed benchmark and evaluation protocols is established, in which different algorithms and modules can be inspected and compared. \New Our study reveals that effective slender object detection can be achieved ~\textbf{with none of} (1) anchor-based localization; (2) specially designed box representations. Instead, \textbf{the critical aspect of improving slender object detection is feature adaptation}. It identifies and extends the insights of existing methods that are previously underexploited. Furthermore, we propose a feature adaption strategy that achieves clear and consistent improvements over current representative object detection methods.

arXiv:2011.07205

Bi-Dimensional Feature Alignment for Cross-Domain Object Detection

Recently the problem of cross-domain object detection has started drawing attention in the computer vision community. In this paper, we propose a novel unsupervised cross-domain detection model that exploits the annotated data in a source domain to train an object detector for a different target domain. The proposed model mitigates the cross-domain representation divergence for object detection by performing cross-domain feature alignment in two dimensions, the depth dimension and the spatial dimension. In the depth dimension of channel layers, it uses inter-channel information to bridge the domain divergence with respect to image style alignment. In the dimension of spatial layers, it deploys spatial attention modules to enhance detection relevant regions and suppress irrelevant regions with respect to cross-domain feature alignment. Experiments are conducted on a number of benchmark cross-domain detection datasets. The empirical results show the proposed method outperforms the state-of-the-art comparison methods.

arXiv:2011.07513공식 코드 · Papers with Code

AmphibianDetector: adaptive computation for moving objects detection

Convolutional neural networks (CNN) allow achieving the highest accuracy for the task of object detection in images. Major challenges in further development of object detectors are false-positive detections and high demand of processing power. In this paper, we propose an approach to object detection which makes it possible to reduce the number of false-positive detections by processing only moving objects and reduce the required processing power for algorithm inference. The proposed approach is a modification of CNN already trained for object detection task. This method can be used to improve the accuracy of an existing system by applying minor changes to the algorithm. The efficiency of the proposed approach was demonstrated on the open dataset "CDNet2014 pedestrian". The implementation of the method proposed in the article is available on the GitHub: https://github.com/david-svitov/AmphibianDetector

arXiv:2011.07357공식 코드 · Papers with Code

Solving Physics Puzzles by Reasoning about Paths

We propose a new deep learning model for goal-driven tasks that require intuitive physical reasoning and intervention in the scene to achieve a desired end goal. Its modular structure is motivated by hypothesizing a sequence of intuitive steps that humans apply when trying to solve such a task. The model first predicts the path the target object would follow without intervention and the path the target object should follow in order to solve the task. Next, it predicts the desired path of the action object and generates the placement of the action object. All components of the model are trained jointly in a supervised way; each component receives its own learning signal but learning signals are also backpropagated through the entire architecture. To evaluate the model we use PHYRE - a benchmark test for goal-driven physical reasoning in 2D mechanics puzzles.

arXiv:2011.08061

FRDet: Balanced and Lightweight Object Detector based on Fire-Residual Modules for Embedded Processor of Autonomous Driving

For deployment on an embedded processor for autonomous driving, the object detection network should satisfy all of the accuracy, real-time inference, and light model size requirements. Conventional deep CNN-based detectors aim for high accuracy, making their model size heavy for an embedded system with limited memory space. In contrast, lightweight object detectors are greatly compressed but at a significant sacrifice of accuracy. Therefore, we propose FRDet, a lightweight one-stage object detector that is balanced to satisfy all the constraints of accuracy, model size, and real-time processing on an embedded GPU processor for autonomous driving applications. Our network aims to maximize the compression of the model while achieving or surpassing YOLOv3 level of accuracy. This paper proposes the Fire-Residual (FR) module to design a lightweight network with low accuracy loss by adapting fire modules with residual skip connections. In addition, the Gaussian uncertainty modeling of the bounding box is applied to further enhance the localization accuracy. Experiments on the KITTI dataset showed that FRDet reduced the memory size by 50.8% but achieved higher accuracy by 1.12% mAP compared to YOLOv3. Moreover, the real-time detection speed reached 31.3 FPS on an embedded GPU board(NVIDIA Xavier). The proposed network achieved higher compression with comparable accuracy compared to other deep CNN object detectors while showing improved accuracy than the lightweight detector baselines. Therefore, the proposed FRDet is a well-balanced and efficient object detector for practical application in autonomous driving that can satisfies all the criteria of accuracy, real-time inference, and light model size.

arXiv:2011.08014

Hierarchical Complementary Learning for Weakly Supervised Object Localization

Weakly supervised object localization (WSOL) is a challenging problem which aims to localize objects with only image-level labels. Due to the lack of ground truth bounding boxes, class labels are mainly employed to train the model. This model generates a class activation map (CAM) which activates the most discriminate features. However, the main drawback of CAM is the ability to detect just a part of the object. To solve this problem, some researchers have removed parts from the detected object \cite{b1, b2, b4}, or the image \cite{b3}. The aim of removing parts from image or detected parts of the object is to force the model to detect the other features. However, these methods require one or many hyper-parameters to erase the appropriate pixels on the image, which could involve a loss of information. In contrast, this paper proposes a Hierarchical Complementary Learning Network method (HCLNet) that helps the CNN to perform better classification and localization of objects on the images. HCLNet uses a complementary map to force the network to detect the other parts of the object. Unlike previous works, this method does not need any extras hyper-parameters to generate different CAMs, as well as does not introduce a big loss of information. In order to fuse these different maps, two different fusion strategies known as the addition strategy and the l1-norm strategy have been used. These strategies allowed to detect the whole object while excluding the background. Extensive experiments show that HCLNet obtains better performance than state-of-the-art methods.

arXiv:2011.07756

Zero Cost Improvements for General Object Detection Network

Modern object detection networks pursuit higher precision on general object detection datasets, at the same time the computation burden is also increasing along with the improvement of precision. Nevertheless, the inference time and precision are both critical to object detection system which needs to be real-time. It is necessary to research precision improvement without extra computation cost. In this work, two modules are proposed to improve detection precision with zero cost, which are focus on FPN and detection head improvement for general object detection networks. We employ the scale attention mechanism to efficiently fuse multi-level feature maps with less parameters, which is called SA-FPN module. Considering the correlation of classification head and regression head, we use sequential head to take the place of widely-used parallel head, which is called Seq-HEAD module. To evaluate the effectiveness, we apply the two modules to some modern state-of-art object detection networks, including anchor-based and anchor-free. Experiment results on coco dataset show that the networks with the two modules can surpass original networks by 1.1 AP and 0.8 AP with zero cost for anchor-based and anchor-free networks, respectively. Code will be available at https://git.io/JTFGl.