Discriminatively localizing sounding objects in cocktail-party, i.e., mixed sound scenes, is commonplace for humans, but still challenging for machines. In this paper, we propose a two-stage learning framework to perform self-supervised class-aware sounding object localization. First, we propose to learn robust object representations by aggregating the candidate sound localization results in the single source scenes. Then, class-aware object localization maps are generated in the cocktail-party scenarios by referring the pre-learned object knowledge, and the sounding objects are accordingly selected by matching audio and visual object category distributions, where the audiovisual consistency is viewed as the self-supervised signal. Experimental results in both realistic and synthesized cocktail-party videos demonstrate that our model is superior in filtering out silent objects and pointing out the location of sounding objects of different classes. Code is available at https://github.com/DTaoo/Discriminative-Sounding-Objects-Localization.
We show how to insert an object from one image to another and get realistic results in the hard case, where the shading of the inserted object clashes with the shading of the scene. Rendering objects using an illumination model of the scene doesn't work, because doing so requires a geometric and material model of the object, which is hard to recover from a single image. In this paper, we introduce a method that corrects shading inconsistencies of the inserted object without requiring a geometric and physical model or an environment map. Our method uses a deep image prior (DIP), trained to produce reshaded renderings of inserted objects via consistent image decomposition inferential losses. The resulting image from DIP aims to have (a) an albedo similar to the cut-and-paste albedo, (b) a similar shading field to that of the target scene, and (c) a shading that is consistent with the cut-and-paste surface normals. The result is a simple procedure that produces convincing shading of the inserted object. We show the efficacy of our method both qualitatively and quantitatively for several objects with complex surface properties and also on a dataset of spherical lampshades for quantitative evaluation. Our method significantly outperforms an Image Harmonization (IH) baseline for all these objects. They also outperform the cut-and-paste and IH baselines in a user study with over 100 users.
Zero-shot detection (ZSD) is crucial to large-scale object detection with the aim of simultaneously localizing and recognizing unseen objects. There remain several challenges for ZSD, including reducing the ambiguity between background and unseen objects as well as improving the alignment between visual and semantic concept. In this work, we propose a novel framework named Background Learnable Cascade (BLC) to improve ZSD performance. The major contributions for BLC are as follows: (i) we propose a multi-stage cascade structure named Cascade Semantic R-CNN to progressively refine the alignment between visual and semantic of ZSD; (ii) we develop the semantic information flow structure and directly add it between each stage in Cascade Semantic RCNN to further improve the semantic feature learning; (iii) we propose the background learnable region proposal network (BLRPN) to learn an appropriate word vector for background class and use this learned vector in Cascade Semantic R CNN, this design makes \Background Learnable" and reduces the confusion between background and unseen classes. Our extensive experiments show BLC obtains significantly performance improvements for MS-COCO over state-of-the-art methods.
When generating technical instructions, it is often convenient to describe complex objects in the world at different levels of abstraction. A novice user might need an object explained piece by piece, while for an expert, talking about the complex object (e.g. a wall or railing) directly may be more succinct and efficient. We show how to generate building instructions at different levels of abstraction in Minecraft. We introduce the use of hierarchical planning to this end, a method from AI planning which can capture the structure of complex objects neatly. A crowdsourcing evaluation shows that the choice of abstraction level matters to users, and that an abstraction strategy which balances low-level and high-level object descriptions compares favorably to ones which don't.
We introduce dense relational captioning, a novel image captioning task which aims to generate multiple captions with respect to relational information between objects in a visual scene. Relational captioning provides explicit descriptions for each relationship between object combinations. This framework is advantageous in both diversity and amount of information, leading to a comprehensive image understanding based on relationships, e.g., relational proposal generation. For relational understanding between objects, the part-of-speech (POS; i.e., subject-object-predicate categories) can be a valuable prior information to guide the causal sequence of words in a caption. We enforce our framework to learn not only to generate captions but also to understand the POS of each word. To this end, we propose the multi-task triple-stream network (MTTSNet) which consists of three recurrent units responsible for each POS which is trained by jointly predicting the correct captions and POS for each word. In addition, we found that the performance of MTTSNet can be improved by modulating the object embeddings with an explicit relational module. We demonstrate that our proposed model can generate more diverse and richer captions, via extensive experimental analysis on large scale datasets and several metrics. Then, we present applications of our framework to holistic image captioning, scene graph generation, and retrieval tasks.
The growing urban complexity demands an efficient algorithm to acquire and process various sensor information from autonomous vehicles. In this paper, we introduce an algorithm to utilize object detection results from the image to adaptively sample and acquire radar data using Compressed Sensing (CS). This novel algorithm is motivated by the hypothesis that with a limited sampling budget, allocating more sampling budget to areas with the object as opposed to a uniform sampling ultimately improves relevant object detection performance. We improve detection performance by dynamically allocating a lower sampling rate to objects such as buses than pedestrians leading to better reconstruction than baseline across areas with objects of interest. We automate the sampling rate allocation using linear programming and show significant time savings while reducing the radar block size by a factor of 2. We also analyze a Binary Permuted Diagonal measurement matrix for radar acquisition which is hardware-efficient and show its performance is similar to Gaussian and Binary Permuted Block Diagonal matrix. Our experiments on the Oxford radar dataset show an effective reconstruction of objects of interest with 10% sampling rate. Finally, we develop a transformer-based 2D object detection network using the NuScenes radar and image data.
We propose a method to learn image representations from uncurated videos. We combine a supervised loss from off-the-shelf object detectors and self-supervised losses which naturally arise from the video-shot-frame-object hierarchy present in each video. We report competitive results on 19 transfer learning tasks of the Visual Task Adaptation Benchmark (VTAB), and on 8 out-of-distribution-generalization tasks, and discuss the benefits and shortcomings of the proposed approach. In particular, it improves over the baseline on all 18/19 few-shot learning tasks and 8/8 out-of-distribution generalization tasks. Finally, we perform several ablation studies and analyze the impact of the pretrained object detector on the performance across this suite of tasks.
Image contour based vision measurement is widely applied in robot manipulation and industrial automation. It is appealing to realize object-agnostic vision system, which can be conveniently reused for various types of objects. We propose the contour primitive of interest extraction network (CPieNet) based on the one-shot learning framework. First, CPieNet is featured by that its contour primitive of interest (CPI) output, a designated regular contour part lying on a specified object, provides the essential geometric information for vision measurement. Second, CPieNet has the one-shot learning ability, utilizing a support sample to assist the perception of the novel object. To realize lower-cost training, we generate support-query sample pairs from unpaired online public images, which cover a wide range of object categories. To obtain single-pixel wide contour for precise measurement, the Gabor-filters based non-maximum suppression is designed to thin the raw contour. For the novel CPI extraction task, we built the Object Contour Primitives dataset using online public images, and the Robotic Object Contour Measurement dataset using a camera mounted on a robot. The effectiveness of the proposed methods is validated by a series of experiments.
In this work, we present an uncertainty-based method for sensor fusion with camera and radar data. The outputs of two neural networks, one processing camera and the other one radar data, are combined in an uncertainty aware manner. To this end, we gather the outputs and corresponding meta information for both networks. For each predicted object, the gathered information is post-processed by a gradient boosting method to produce a joint prediction of both networks. In our experiments we combine the YOLOv3 object detection network with a customized $1D$ radar segmentation network and evaluate our method on the nuScenes dataset. In particular we focus on night scenes, where the capability of object detection networks based on camera data is potentially handicapped. Our experiments show, that this approach of uncertainty aware fusion, which is also of very modular nature, significantly gains performance compared to single sensor baselines and is in range of specifically tailored deep learning based fusion approaches.
Object recognition in unseen indoor environments remains a challenging problem for visual perception of mobile robots. In this letter, we propose the use of topologically persistent features, which rely on the objects' shape information, to address this challenge. In particular, we extract two kinds of features, namely, sparse persistence image (PI) and amplitude, by applying persistent homology to multi-directional height function-based filtrations of the cubical complexes representing the object segmentation maps. The features are then used to train a fully connected network for recognition. For performance evaluation, in addition to a widely used shape dataset and a benchmark indoor scenes dataset, we collect a new dataset, comprising scene images from two different environments, namely, a living room and a mock warehouse. The scenes are captured using varying camera poses under different illumination conditions and include up to five different objects from a given set of fourteen objects. On the benchmark indoor scenes dataset, sparse PI features show better recognition performance in unseen environments than the features learned using the widely used ResNetV2-56 and EfficientNet-B4 models. Further, they provide slightly higher recall and accuracy values than Faster R-CNN, an end-to-end object detection method, and its state-of-the-art variant, Domain Adaptive Faster R-CNN. The performance of our methods also remains relatively unchanged from the training environment (living room) to the unseen environment (mock warehouse) in the new dataset. In contrast, the performance of the object detection methods drops substantially. We also implement the proposed method on a real-world robot to demonstrate its usefulness.
The training of deep-learning-based 3D object detectors requires large datasets with 3D bounding box labels for supervision that have to be generated by hand-labeling. We propose a network architecture and training procedure for learning monocular 3D object detection without 3D bounding box labels. By representing the objects as triangular meshes and employing differentiable shape rendering, we define loss functions based on depth maps, segmentation masks, and ego- and object-motion, which are generated by pre-trained, off-the-shelf networks. We evaluate the proposed algorithm on the real-world KITTI dataset and achieve promising performance in comparison to state-of-the-art methods requiring 3D bounding box labels for training and superior performance to conventional baseline methods.
While unsupervised domain translation (UDT) has seen a lot of success recently, we argue that mediating its translation via categorical semantic features could broaden its applicability. In particular, we demonstrate that categorical semantics improves the translation between perceptually different domains sharing multiple object categories. We propose a method to learn, in an unsupervised manner, categorical semantic features (such as object labels) that are invariant of the source and target domains. We show that conditioning the style encoder of unsupervised domain translation methods on the learned categorical semantics leads to a translation preserving the digits on MNIST$\leftrightarrow$SVHN and to a more realistic stylization on Sketches$\to$Reals.
Recently, progress has been made in the supervised training of Convolutional Object Detectors (e.g. Faster R-CNN) for threat recognition in carry-on luggage using X-ray images. This is part of the Transportation Security Administration's (TSA's) mission to protect air travelers in the United States. While more training data with threats may reliably improve performance for this class of deep algorithm, it is expensive to stage in realistic contexts. By contrast, data from the real world can be collected quickly with minimal cost. In this paper, we present a semi-supervised approach for threat recognition which we call Background Adaptive Faster R-CNN. This approach is a training method for two-stage object detectors which uses Domain Adaptation methods from the field of deep learning. The data sources described earlier make two "domains": a hand-collected data domain of images with threats, and a real-world domain of images assumed without threats. Two domain discriminators, one for discriminating object proposals and one for image features, are adversarially trained to prevent encoding domain-specific information. Without this penalty a Convolutional Neural Network (CNN) can learn to identify domains based on superficial characteristics, and minimize a supervised loss function without improving its ability to recognize objects. For the hand-collected data, only object proposals and image features from backgrounds are used. The losses for these domain-adaptive discriminators are added to the Faster R-CNN losses of images from both domains. This can reduce threat detection false alarm rates by matching the statistics of extracted features from hand-collected backgrounds to real world data. Performance improvements are demonstrated on two independently-collected datasets of labeled threats.
Given the outstanding progress that convolutional neural networks (CNNs) have made on natural image classification and object recognition problems, it is shown that deep learning methods can achieve very good recognition performance on many texture datasets. However, while CNNs for natural image classification/object recognition tasks have been revealed to be highly vulnerable to various types of adversarial attack methods, the robustness of deep learning methods for texture recognition is yet to be examined. In our paper, we show that there exist small image-agnostic/univesal perturbations that can fool the deep learning models with more than 80\% of testing fooling rates on all tested texture datasets. The computed perturbations using various attack methods on the tested datasets are generally quasi-imperceptible, containing structured patterns with low, middle and high frequency components.
Document images often have intricate layout structures, with numerous content regions (e.g. texts, figures, tables) densely arranged on each page. This makes the manual annotation of layout datasets expensive and inefficient. These characteristics also challenge existing active learning methods, as image-level scoring and selection suffer from the overexposure of common objects.Inspired by recent progresses in semi-supervised learning and self-training, we propose an Object-Level Active Learning framework for efficient document layout Annotation, OLALA. In this framework, only regions with the most ambiguous object predictions within an image are selected for annotators to label, optimizing the use of the annotation budget. For unselected predictions, the semi-automatic correction algorithm is proposed to identify certain errors based on prior knowledge of layout structures and rectifies them with minor supervision. Additionally, we carefully design a perturbation-based object scoring function for document images. It governs the object selection process via evaluating prediction ambiguities, and considers both the positions and categories of predicted layout objects. Extensive experiments show that OLALA can significantly boost model performance and improve annotation efficiency, given the same labeling budget. Code for this paper can be accessed via https://github.com/lolipopshock/detectron2_al.
Humans explain inter-object relationships with semantic labels that demonstrate a high-level understanding required to perform complex Vision-Language tasks such as Visual Question Answering (VQA). However, existing VQA models represent relationships as a combination of object-level visual features which constrain a model to express interactions between objects in a single domain, while the model is trying to solve a multi-modal task. In this paper, we propose a general purpose semantic relationship parser which generates a semantic feature vector for each subject-predicate-object triplet in an image, and a Mutual and Self Attention (MSA) mechanism that learns to identify relationship triplets that are important to answer the given question. To motivate the significance of semantic relationships, we show an oracle setting with ground-truth relationship triplets, where our model achieves a ~25% accuracy gain over the closest state-of-the-art model on the challenging GQA dataset. Further, with our semantic parser, we show that our model outperforms other comparable approaches on VQA and GQA datasets.
The remarkable recent advances in object-centric generative world models raise a few questions. First, while many of the recent achievements are indispensable for making a general and versatile world model, it is quite unclear how these ingredients can be integrated into a unified framework. Second, despite using generative objectives, abilities for object detection and tracking are mainly investigated, leaving the crucial ability of temporal imagination largely under question. Third, a few key abilities for more faithful temporal imagination such as multimodal uncertainty and situation-awareness are missing. In this paper, we introduce Generative Structured World Models (G-SWM). The G-SWM achieves the versatile world modeling not only by unifying the key properties of previous models in a principled framework but also by achieving two crucial new abilities, multimodal uncertainty and situation-awareness. Our thorough investigation on the temporal generation ability in comparison to the previous models demonstrates that G-SWM achieves the versatility with the best or comparable performance for all experiment settings including a few complex settings that have not been tested before.
Techniques to discover Petri nets from event data assume precisely one case identifier per event. These case identifiers are used to correlate events, and the resulting discovered Petri net aims to describe the life-cycle of individual cases. In reality, there is not one possible case notion, but multiple intertwined case notions. For example, events may refer to mixtures of orders, items, packages, customers, and products. A package may refer to multiple items, multiple products, one order, and one customer. Therefore, we need to assume that each event refers to a collection of objects, each having a type (instead of a single case identifier). Such object-centric event logs are closer to data in real-life information systems. From an object-centric event log, we want to discover an object-centric Petri net with places that correspond to object types and transitions that may consume and produce collections of objects of different types. Object-centric Petri nets visualize the complex relationships among objects from different types. This paper discusses a novel process discovery approach implemented in PM4Py. As will be demonstrated, it is indeed feasible to discover holistic process models that can be used to drill-down into specific viewpoints if needed.
In the context of future manufacturing lines, removing fixtures will be a fundamental step to increase the flexibility of autonomous systems in assembly and logistic operations. Vision-based 3D pose estimation is a necessity to accurately handle objects that might not be placed at fixed positions during the robot task execution. Industrial tasks bring multiple challenges for the robust pose estimation of objects such as difficult object properties, tight cycle times and constraints on camera views. In particular, when interacting with objects, we have to work with close-range partial views of objects that pose a new challenge for typical view-based pose estimation methods. In this paper, we present a 3D pose estimation method based on a gradient-ascend particle filter that integrates new observations on-the-fly to improve the pose estimate. Thereby, we can apply this method online during task execution to save valuable cycle time. In contrast to other view-based pose estimation methods, we model potential views in full 6- dimensional space that allows us to cope with close-range partial objects views. We demonstrate the approach on a real assembly task, in which the algorithm usually converges to the correct pose within 10-15 iterations with an average accuracy of less than 8mm.
Human-object interaction (HOI) detection requires a large amount of annotated data. Current algorithms suffer from insufficient training samples and category imbalance within datasets. To increase data efficiency, in this paper, we propose an efficient and effective data augmentation method called DecAug for HOI detection. Based on our proposed object state similarity metric, object patterns across different HOIs are shared to augment local object appearance features without changing their state. Further, we shift spatial correlation between humans and objects to other feasible configurations with the aid of a pose-guided Gaussian Mixture Model while preserving their interactions. Experiments show that our method brings up to 3.3 mAP and 1.6 mAP improvements on V-COCO and HICODET dataset for two advanced models. Specifically, interactions with fewer samples enjoy more notable improvement. Our method can be easily integrated into various HOI detection models with negligible extra computational consumption. Our code will be made publicly available.