PyTorchKR Papers

최신 논문

총 9,712편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2211.01500

Learning to Grasp the Ungraspable with Emergent Extrinsic Dexterity

A simple gripper can solve more complex manipulation tasks if it can utilize the external environment such as pushing the object against the table or a vertical wall, known as "Extrinsic Dexterity." Previous work in extrinsic dexterity usually has careful assumptions about contacts which impose restrictions on robot design, robot motions, and the variations of the physical parameters. In this work, we develop a system based on reinforcement learning (RL) to address these limitations. We study the task of "Occluded Grasping" which aims to grasp the object in configurations that are initially occluded; the robot needs to move the object into a configuration from which these grasps can be achieved. We present a system with model-free RL that successfully achieves this task using a simple gripper with extrinsic dexterity. The policy learns emergent behaviors of pushing the object against the wall to rotate and then grasp it without additional reward terms on extrinsic dexterity. We discuss important components of the system including the design of the RL problem, multi-grasp training and selection, and policy generalization with automatic curriculum. Most importantly, the policy trained in simulation is zero-shot transferred to a physical robot. It demonstrates dynamic and contact-rich motions with a simple gripper that generalizes across objects with various size, density, surface friction, and shape with a 78% success rate. Videos can be found at https://sites.google.com/view/grasp-ungraspable/.

arXiv:2211.00849

Fine-grained Visual-Text Prompt-Driven Self-Training for Open-Vocabulary Object Detection

Inspired by the success of vision-language methods (VLMs) in zero-shot classification, recent works attempt to extend this line of work into object detection by leveraging the localization ability of pre-trained VLMs and generating pseudo labels for unseen classes in a self-training manner. However, since the current VLMs are usually pre-trained with aligning sentence embedding with global image embedding, the direct use of them lacks fine-grained alignment for object instances, which is the core of detection. In this paper, we propose a simple but effective fine-grained Visual-Text Prompt-driven self-training paradigm for Open-Vocabulary Detection (VTP-OVD) that introduces a fine-grained visual-text prompt adapting stage to enhance the current self-training paradigm with a more powerful fine-grained alignment. During the adapting stage, we enable VLM to obtain fine-grained alignment by using learnable text prompts to resolve an auxiliary dense pixel-wise prediction task. Furthermore, we propose a visual prompt module to provide the prior task information (i.e., the categories need to be predicted) for the vision branch to better adapt the pre-trained VLM to the downstream tasks. Experiments show that our method achieves the state-of-the-art performance for open-vocabulary object detection, e.g., 31.5% mAP on unseen classes of COCO.

arXiv:2211.01177

Neural Systematic Binder

The key to high-level cognition is believed to be the ability to systematically manipulate and compose knowledge pieces. While token-like structured knowledge representations are naturally provided in text, it is elusive how to obtain them for unstructured modalities such as scene images. In this paper, we propose a neural mechanism called Neural Systematic Binder or SysBinder for constructing a novel structured representation called Block-Slot Representation. In Block-Slot Representation, object-centric representations known as slots are constructed by composing a set of independent factor representations called blocks, to facilitate systematic generalization. SysBinder obtains this structure in an unsupervised way by alternatingly applying two different binding principles: spatial binding for spatial modularity across the full scene and factor binding for factor modularity within an object. SysBinder is a simple, deterministic, and general-purpose layer that can be applied as a drop-in module in any arbitrary neural network and on any modality. In experiments, we find that SysBinder provides significantly better factor disentanglement within the slots than the conventional object-centric methods, including, for the first time, in visually complex scene images such as CLEVR-Tex. Furthermore, we demonstrate factor-level systematicity in controlled scene generation by decoding unseen factor combinations.

arXiv:2211.01142

OPA-3D: Occlusion-Aware Pixel-Wise Aggregation for Monocular 3D Object Detection

Despite monocular 3D object detection having recently made a significant leap forward thanks to the use of pre-trained depth estimators for pseudo-LiDAR recovery, such two-stage methods typically suffer from overfitting and are incapable of explicitly encapsulating the geometric relation between depth and object bounding box. To overcome this limitation, we instead propose OPA-3D, a single-stage, end-to-end, Occlusion-Aware Pixel-Wise Aggregation network that to jointly estimate dense scene depth with depth-bounding box residuals and object bounding boxes, allowing a two-stream detection of 3D objects, leading to significantly more robust detections. Thereby, the geometry stream denoted as the Geometry Stream, combines visible depth and depth-bounding box residuals to recover the object bounding box via explicit occlusion-aware optimization. In addition, a bounding box based geometry projection scheme is employed in an effort to enhance distance perception. The second stream, named as the Context Stream, directly regresses 3D object location and size. This novel two-stream representation further enables us to enforce cross-stream consistency terms which aligns the outputs of both streams, improving the overall performance. Extensive experiments on the public benchmark demonstrate that OPA-3D outperforms state-of-the-art methods on the main Car category, whilst keeping a real-time inference speed. We plan to release all codes and trained models soon.

arXiv:2211.01080

Spatial Reasoning for Few-Shot Object Detection

Although modern object detectors rely heavily on a significant amount of training data, humans can easily detect novel objects using a few training examples. The mechanism of the human visual system is to interpret spatial relationships among various objects and this process enables us to exploit contextual information by considering the co-occurrence of objects. Thus, we propose a spatial reasoning framework that detects novel objects with only a few training examples in a context. We infer geometric relatedness between novel and base RoIs (Region-of-Interests) to enhance the feature representation of novel categories using an object detector well trained on base categories. We employ a graph convolutional network as the RoIs and their relatedness are defined as nodes and edges, respectively. Furthermore, we present spatial data augmentation to overcome the few-shot environment where all objects and bounding boxes in an image are resized randomly. Using the PASCAL VOC and MS COCO datasets, we demonstrate that the proposed method significantly outperforms the state-of-the-art methods and verify its efficacy through extensive ablation studies.

arXiv:2211.00960

Ambiguity-Aware Multi-Object Pose Optimization for Visually-Assisted Robot Manipulation

6D object pose estimation aims to infer the relative pose between the object and the camera using a single image or multiple images. Most works have focused on predicting the object pose without associated uncertainty under occlusion and structural ambiguity (symmetricity). However, these works demand prior information about shape attributes, and this condition is hardly satisfied in reality; even asymmetric objects may be symmetric under the viewpoint change. In addition, acquiring and fusing diverse sensor data is challenging when extending them to robotics applications. Tackling these limitations, we present an ambiguity-aware 6D object pose estimation network, PrimA6D++, as a generic uncertainty prediction method. The major challenges in pose estimation, such as occlusion and symmetry, can be handled in a generic manner based on the measured ambiguity of the prediction. Specifically, we devise a network to reconstruct the three rotation axis primitive images of a target object and predict the underlying uncertainty along each primitive axis. Leveraging the estimated uncertainty, we then optimize multi-object poses using visual measurements and camera poses by treating it as an object SLAM problem. The proposed method shows a significant performance improvement in T-LESS and YCB-Video datasets. We further demonstrate real-time scene recognition capability for visually-assisted robot manipulation. Our code and supplementary materials are available at https://github.com/rpmsnu/PrimA6D.

arXiv:2211.00826

TSAA: A Two-Stage Anchor Assignment Method towards Anchor Drift in Crowded Object Detection

Among current anchor-based detectors, a positive anchor box will be intuitively assigned to the object that overlaps it the most. The assigned label to each anchor will directly determine the optimization direction of the corresponding prediction box, including the direction of box regression and category prediction. In our practice of crowded object detection, however, the results show that a positive anchor does not always regress toward the object that overlaps it the most when multiple objects overlap. We name it anchor drift. The anchor drift reflects that the anchor-object matching relation, which is determined by the degree of overlap between anchors and objects, is not always optimal. Conflicts between the fixed matching relation and learned experience in the past training process may cause ambiguous predictions and thus raise the false-positive rate. In this paper, a simple but efficient adaptive two-stage anchor assignment (TSAA) method is proposed. It utilizes the final prediction boxes rather than the fixed anchors to calculate the overlap degree with objects to determine which object to regress for each anchor. The participation of the prediction box makes the anchor-object assignment mechanism adaptive. Extensive experiments are conducted on three classic detectors RetinaNet, Faster-RCNN and YOLOv3 on CrowdHuman and COCO to evaluate the effectiveness of TSAA. The results show that TSAA can significantly improve the detectors' performance without additional computational costs or network structure changes.

arXiv:2211.00733

State-of-the-art Models for Object Detection in Various Fields of Application

We present a list of datasets and their best models with the goal of advancing the state-of-the-art in object detection by placing the question of object recognition in the context of the two types of state-of-the-art methods: one-stage methods and two stage-methods. We provided an in-depth statistical analysis of the five top datasets in the light of recent developments in granulated Deep Learning models - COCO minival, COCO test, Pascal VOC 2007, ADE20K, and ImageNet. The datasets are handpicked after closely comparing them with the rest in terms of diversity, quality of data, minimal bias, labeling quality etc. More importantly, our work extends to provide the best combination of these datasets with the emerging models in the last two years. It lists the top models and their optimal use cases for each of the respective datasets. We have provided a comprehensive overview of a variety of both generic and specific object detection models, enlisting comparative results like inference time and average precision of box (AP) fixed at different Intersection Over Union (IoUs) and for different sized objects. The qualitative and quantitative analysis will allow experts to achieve new performance records using the best combination of datasets and models.

arXiv:2211.00562

Leveraging commonsense for object localisation in partial scenes

We propose an end-to-end solution to address the problem of object localisation in partial scenes, where we aim to estimate the position of an object in an unknown area given only a partial 3D scan of the scene. We propose a novel scene representation to facilitate the geometric reasoning, Directed Spatial Commonsense Graph (D-SCG), a spatial scene graph that is enriched with additional concept nodes from a commonsense knowledge base. Specifically, the nodes of D-SCG represent the scene objects and the edges are their relative positions. Each object node is then connected via different commonsense relationships to a set of concept nodes. With the proposed graph-based scene representation, we estimate the unknown position of the target object using a Graph Neural Network that implements a novel attentional message passing mechanism. The network first predicts the relative positions between the target object and each visible object by learning a rich representation of the objects via aggregating both the object nodes and the concept nodes in D-SCG. These relative positions then are merged to obtain the final position. We evaluate our method using Partial ScanNet, improving the state-of-the-art by 5.9% in terms of the localisation accuracy at a 8x faster training speed.

arXiv:2211.00110공식 코드 · Papers with Code

A new benchmark for group distribution shifts in hand grasp regression for object manipulation. Can meta-learning raise the bar?

Understanding hand-object pose with computer vision opens the door to new applications in mixed reality, assisted living or human-robot interaction. Most methods are trained and evaluated on balanced datasets. This is of limited use in real-world applications; how do these methods perform in the wild on unknown objects? We propose a novel benchmark for object group distribution shifts in hand and object pose regression. We then test the hypothesis that meta-learning a baseline pose regression neural network can adapt to these shifts and generalize better to unknown objects. Our results show measurable improvements over the baseline, depending on the amount of prior knowledge. For the task of joint hand-object pose regression, we observe optimization interference for the meta-learner. To address this issue and improve the method further, we provide a comprehensive analysis which should serve as a basis for future work on this benchmark.

arXiv:2211.00002공식 코드 · Papers with Code

A Self-Supervised Approach to Reconstruction in Sparse X-Ray Computed Tomography

Computed tomography has propelled scientific advances in fields from biology to materials science. This technology allows for the elucidation of 3-dimensional internal structure by the attenuation of x-rays through an object at different rotations relative to the beam. By imaging 2-dimensional projections, a 3-dimensional object can be reconstructed through a computational algorithm. Imaging at a greater number of rotation angles allows for improved reconstruction. However, taking more measurements increases the x-ray dose and may cause sample damage. Deep neural networks have been used to transform sparse 2-D projection measurements to a 3-D reconstruction by training on a dataset of known similar objects. However, obtaining high-quality object reconstructions for the training dataset requires high x-ray dose measurements that can destroy or alter the specimen before imaging is complete. This becomes a chicken-and-egg problem: high-quality reconstructions cannot be generated without deep learning, and the deep neural network cannot be learned without the reconstructions. This work develops and validates a self-supervised probabilistic deep learning technique, the physics-informed variational autoencoder, to solve this problem. A dataset consisting solely of sparse projection measurements from each object is used to jointly reconstruct all objects of the set. This approach has the potential to allow visualization of fragile samples with x-ray computed tomography. We release our code for reproducing our results at: https://github.com/vganapati/CT_PVAE .

arXiv:2210.17151

Tech Report: One-stage Lightweight Object Detectors

This work is for designing one-stage lightweight detectors which perform well in terms of mAP and latency. With baseline models each of which targets on GPU and CPU respectively, various operations are applied instead of the main operations in backbone networks of baseline models. In addition to experiments about backbone networks and operations, several feature pyramid network (FPN) architectures are investigated. Benchmarks and proposed detectors are analyzed in terms of the number of parameters, Gflops, GPU latency, CPU latency and mAP, on MS COCO dataset which is a benchmark dataset in object detection. This work propose similar or better network architectures considering the trade-off between accuracy and latency. For example, our proposed GPU-target backbone network outperforms that of YOLOX-tiny which is selected as the benchmark by 1.43x in speed and 0.5 mAP in accuracy on NVIDIA GeForce RTX 2080 Ti GPU.

arXiv:2210.17009

Point-Syn2Real: Semi-Supervised Synthetic-to-Real Cross-Domain Learning for Object Classification in 3D Point Clouds

Object classification using LiDAR 3D point cloud data is critical for modern applications such as autonomous driving. However, labeling point cloud data is labor-intensive as it requires human annotators to visualize and inspect the 3D data from different perspectives. In this paper, we propose a semi-supervised cross-domain learning approach that does not rely on manual annotations of point clouds and performs similar to fully-supervised approaches. We utilize available 3D object models to train classifiers that can generalize to real-world point clouds. We simulate the acquisition of point clouds by sampling 3D object models from multiple viewpoints and with arbitrary partial occlusions. We then augment the resulting set of point clouds through random rotations and adding Gaussian noise to better emulate the real-world scenarios. We then train point cloud encoding models, e.g., DGCNN, PointNet++, on the synthesized and augmented datasets and evaluate their cross-domain classification performance on corresponding real-world datasets. We also introduce Point-Syn2Real, a new benchmark dataset for cross-domain learning on point clouds. The results of our extensive experiments with this dataset demonstrate that the proposed cross-domain learning approach for point clouds outperforms the related baseline and state-of-the-art approaches in both indoor and outdoor settings in terms of cross-domain generalizability. The code and data will be available upon publishing.

arXiv:2210.16901공식 코드 · Papers with Code

Foreign Object Debris Detection for Airport Pavement Images based on Self-supervised Localization and Vision Transformer

Supervised object detection methods provide subpar performance when applied to Foreign Object Debris (FOD) detection because FOD could be arbitrary objects according to the Federal Aviation Administration (FAA) specification. Current supervised object detection algorithms require datasets that contain annotated examples of every to-be-detected object. While a large and expensive dataset could be developed to include common FOD examples, it is infeasible to collect all possible FOD examples in the dataset representation because of the open-ended nature of FOD. Limitations of the dataset could cause FOD detection systems driven by those supervised algorithms to miss certain FOD, which can become dangerous to airport operations. To this end, this paper presents a self-supervised FOD localization by learning to predict the runway images, which avoids the enumeration of FOD annotation examples. The localization method utilizes the Vision Transformer (ViT) to improve localization performance. The experiments show that the method successfully detects arbitrary FOD in real-world runway situations. The paper also provides an extension to the localization result to perform classification; a feature that can be useful to downstream tasks. To train the localization, this paper also presents a simple and realistic dataset creation framework that only collects clean runway images. The training and testing data for this method are collected at a local airport using unmanned aircraft systems (UAS). Additionally, the developed dataset is provided for public use and further studies.

arXiv:2210.16810공식 코드 · Papers with Code

SL3D: Self-supervised-Self-labeled 3D Recognition

Deep learning has attained remarkable success in many 3D visual recognition tasks, including shape classification, object detection, and semantic segmentation. However, many of these results rely on manually collecting densely annotated real-world 3D data, which is highly time-consuming and expensive to obtain, limiting the scalability of 3D recognition tasks. Thus, we study unsupervised 3D recognition and propose a Self-supervised-Self-Labeled 3D Recognition (SL3D) framework. SL3D simultaneously solves two coupled objectives, i.e., clustering and learning feature representation to generate pseudo-labeled data for unsupervised 3D recognition. SL3D is a generic framework and can be applied to solve different 3D recognition tasks, including classification, object detection, and semantic segmentation. Extensive experiments demonstrate its effectiveness. Code is available at https://github.com/fcendra/sl3d.

arXiv:2210.16574

Boosting Monocular 3D Object Detection with Object-Centric Auxiliary Depth Supervision

Recent advances in monocular 3D detection leverage a depth estimation network explicitly as an intermediate stage of the 3D detection network. Depth map approaches yield more accurate depth to objects than other methods thanks to the depth estimation network trained on a large-scale dataset. However, depth map approaches can be limited by the accuracy of the depth map, and sequentially using two separated networks for depth estimation and 3D detection significantly increases computation cost and inference time. In this work, we propose a method to boost the RGB image-based 3D detector by jointly training the detection network with a depth prediction loss analogous to the depth estimation task. In this way, our 3D detection network can be supervised by more depth supervision from raw LiDAR points, which does not require any human annotation cost, to estimate accurate depth without explicitly predicting the depth map. Our novel object-centric depth prediction loss focuses on depth around foreground objects, which is important for 3D object detection, to leverage pixel-wise depth supervision in an object-centric manner. Our depth regression model is further trained to predict the uncertainty of depth to represent the 3D confidence of objects. To effectively train the 3D detector with raw LiDAR points and to enable end-to-end training, we revisit the regression target of 3D objects and design a network architecture. Extensive experiments on KITTI and nuScenes benchmarks show that our method can significantly boost the monocular image-based 3D detector to outperform depth map approaches while maintaining the real-time inference speed.

arXiv:2210.16572공식 코드 · Papers with Code

SearchTrack: Multiple Object Tracking with Object-Customized Search and Motion-Aware Features

The paper presents a new method, SearchTrack, for multiple object tracking and segmentation (MOTS). To address the association problem between detected objects, SearchTrack proposes object-customized search and motion-aware features. By maintaining a Kalman filter for each object, we encode the predicted motion into the motion-aware feature, which includes both motion and appearance cues. For each object, a customized fully convolutional search engine is created by SearchTrack by learning a set of weights for dynamic convolutions specific to the object. Experiments demonstrate that our SearchTrack method outperforms competitive methods on both MOTS and MOT tasks, particularly in terms of association accuracy. Our method achieves 71.5 HOTA (car) and 57.6 HOTA (pedestrian) on the KITTI MOTS and 53.4 HOTA on MOT17. In terms of association accuracy, our method achieves state-of-the-art performance among 2D online methods on the KITTI MOTS. Our code is available at https://github.com/qa276390/SearchTrack.

arXiv:2210.16897

Time-rEversed diffusioN tEnsor Transformer: A new TENET of Few-Shot Object Detection

In this paper, we tackle the challenging problem of Few-shot Object Detection. Existing FSOD pipelines (i) use average-pooled representations that result in information loss; and/or (ii) discard position information that can help detect object instances. Consequently, such pipelines are sensitive to large intra-class appearance and geometric variations between support and query images. To address these drawbacks, we propose a Time-rEversed diffusioN tEnsor Transformer (TENET), which i) forms high-order tensor representations that capture multi-way feature occurrences that are highly discriminative, and ii) uses a transformer that dynamically extracts correlations between the query image and the entire support set, instead of a single average-pooled support embedding. We also propose a Transformer Relation Head (TRH), equipped with higher-order representations, which encodes correlations between query regions and the entire support set, while being sensitive to the positional variability of object instances. Our model achieves state-of-the-art results on PASCAL VOC, FSOD, and COCO.

arXiv:2210.16742

On-the-fly Object Detection using StyleGAN with CLIP Guidance

We present a fully automated framework for building object detectors on satellite imagery without requiring any human annotation or intervention. We achieve this by leveraging the combined power of modern generative models (e.g., StyleGAN) and recent advances in multi-modal learning (e.g., CLIP). While deep generative models effectively encode the key semantics pertinent to a data distribution, this information is not immediately accessible for downstream tasks, such as object detection. In this work, we exploit CLIP's ability to associate image features with text descriptions to identify neurons in the generator network, which are subsequently used to build detectors on-the-fly.

arXiv:2210.16173

Deep Learning Object Detection Approaches to Signal Identification

Traditionally source identification is solved using threshold based energy detection algorithms. These algorithms frequently sum up the activity in regions, and consider regions above a specific activity threshold to be sources. While these algorithms work for the majority of cases, they often fail to detect signals that occupy small frequency bands, fail to distinguish sources with overlapping frequency bands, and cannot detect any signals under a specified signal to noise ratio. Through the conversion of raw signal data to spectrogram, source identification can be framed as an object detection problem. By leveraging modern advancements in deep learning based object detection, we propose a system that manages to alleviate the failure cases encountered when using traditional source identification algorithms. Our contributions include framing source identification as an object detection problem, the publication of a spectrogram object detection dataset, and evaluation of the RetinaNet and YOLOv5 object detection models trained on the dataset. Our final models achieve Mean Average Precisions of up to 0.906. With such a high Mean Average Precision, these models are sufficiently robust for use in real world applications.