Knowledge amalgamation (KA) is a novel deep model reusing task aiming to transfer knowledge from several well-trained teachers to a multi-talented and compact student. Currently, most of these approaches are tailored for convolutional neural networks (CNNs). However, there is a tendency that transformers, with a completely different architecture, are starting to challenge the domination of CNNs in many computer vision tasks. Nevertheless, directly applying the previous KA methods to transformers leads to severe performance degradation. In this work, we explore a more effective KA scheme for transformer-based object detection models. Specifically, considering the architecture characteristics of transformers, we propose to dissolve the KA into two aspects: sequence-level amalgamation (SA) and task-level amalgamation (TA). In particular, a hint is generated within the sequence-level amalgamation by concatenating teacher sequences instead of redundantly aggregating them to a fixed-size one as previous KA works. Besides, the student learns heterogeneous detection tasks through soft targets with efficiency in the task-level amalgamation. Extensive experiments on PASCAL VOC and COCO have unfolded that the sequence-level amalgamation significantly boosts the performance of students, while the previous methods impair the students. Moreover, the transformer-based students excel in learning amalgamated knowledge, as they have mastered heterogeneous detection tasks rapidly and achieved superior or at least comparable performance to those of the teachers in their specializations.
Visual quality inspection in high performance manufacturing can benefit from automation, due to cost savings and improved rigor. Deep learning techniques are the current state of the art for generic computer vision tasks like classification and object detection. Manufacturing data can pose a challenge for deep learning because data is highly repetitive and there are few images of defects or deviations to learn from. Deep learning models trained with such data can be fragile and sensitive to context, and can under-detect new defects not found in the training data. In this work, we explore training defect detection models to learn specific defects out of context, so that they are more likely to be detected in new situations. We demonstrate how models trained on diverse images containing a common defect type can pick defects out in new circumstances. Such generic models could be more robust to new defects not found data collected for training, and can reduce data collection impediments to implementing visual inspection on production lines. Additionally, we demonstrate that object detection models trained to predict a label and bounding box outperform classifiers that predict a label only on held out test data typical of manufacturing inspection tasks. Finally, we studied the factors that affect generalization in order to train models that work under a wider range of conditions.
Recent self-supervised learning (SSL) methods have demonstrated impressive results in learning visual representations from unlabeled remote sensing images. However, most remote sensing images predominantly consist of scenographic scenes containing multiple ground objects without explicit foreground targets, which limits the performance of existing SSL methods that focus on foreground targets. This raises the question: Is there a method that can automatically aggregate similar objects within scenographic remote sensing images, thereby enabling models to differentiate knowledge embedded in various geospatial patterns for improved feature representation? In this work, we present the Pattern Integration and Enhancement Vision Transformer (PIEViT), a novel self-supervised learning framework designed specifically for remote sensing imagery. PIEViT utilizes a teacher-student architecture to address both image-level and patch-level tasks. It employs the Geospatial Pattern Cohesion (GPC) module to explore the natural clustering of patches, enhancing the differentiation of individual features. The Feature Integration Projection (FIP) module further refines masked token reconstruction using geospatially clustered patches. We validated PIEViT across multiple downstream tasks, including object detection, semantic segmentation, and change detection. Experiments demonstrated that PIEViT enhances the representation of internal patch features, providing significant improvements over existing self-supervised baselines. It achieves excellent results in object detection, land cover classification, and change detection, underscoring its robustness, generalization, and transferability for remote sensing image interpretation tasks.
Despite the numerous developments in object tracking, further development of current tracking algorithms is limited by small and mostly saturated datasets. As a matter of fact, data-hungry trackers based on deep-learning currently rely on object detection datasets due to the scarcity of dedicated large-scale tracking datasets. In this work, we present TrackingNet, the first large-scale dataset and benchmark for object tracking in the wild. We provide more than 30K videos with more than 14 million dense bounding box annotations. Our dataset covers a wide selection of object classes in broad and diverse context. By releasing such a large-scale dataset, we expect deep trackers to further improve and generalize. In addition, we introduce a new benchmark composed of 500 novel videos, modeled with a distribution similar to our training dataset. By sequestering the annotation of the test set and providing an online evaluation server, we provide a fair benchmark for future development of object trackers. Deep trackers fine-tuned on a fraction of our dataset improve their performance by up to 1.6% on OTB100 and up to 1.7% on TrackingNet Test. We provide an extensive benchmark on TrackingNet by evaluating more than 20 trackers. Our results suggest that object tracking in the wild is far from being solved.
In this paper, we propose M$^2$BEV, a unified framework that jointly performs 3D object detection and map segmentation in the Birds Eye View~(BEV) space with multi-camera image inputs. Unlike the majority of previous works which separately process detection and segmentation, M$^2$BEV infers both tasks with a unified model and improves efficiency. M$^2$BEV efficiently transforms multi-view 2D image features into the 3D BEV feature in ego-car coordinates. Such BEV representation is important as it enables different tasks to share a single encoder. Our framework further contains four important designs that benefit both accuracy and efficiency: (1) An efficient BEV encoder design that reduces the spatial dimension of a voxel feature map. (2) A dynamic box assignment strategy that uses learning-to-match to assign ground-truth 3D boxes with anchors. (3) A BEV centerness re-weighting that reinforces with larger weights for more distant predictions, and (4) Large-scale 2D detection pre-training and auxiliary supervision. We show that these designs significantly benefit the ill-posed camera-based 3D perception tasks where depth information is missing. M$^2$BEV is memory efficient, allowing significantly higher resolution images as input, with faster inference speed. Experiments on nuScenes show that M$^2$BEV achieves state-of-the-art results in both 3D object detection and BEV segmentation, with the best single model achieving 42.5 mAP and 57.0 mIoU in these two tasks, respectively.
The proposed method uses live image footage which, based on calculations of pixel motion, decides whether or not an object is in the blind-spot. If found, the driver is notified by a sensory light or noise built into the vehicle's CPU. The new technology incorporates optical vectors and flow fields rather than expensive radar-waves, creating cheaper detection systems that retain the needed accuracy while adapting to the current processor speeds.
This paper presents a method for analysis of the vote space created from the local features extraction process in a multi-detection system. The method is opposed to the classic clustering approach and gives a high level of control over the clusters composition for further verification steps. Proposed method comprises of the graphical vote space presentation, the proposition generation, the two-pass iterative vote aggregation and the cascade filters for verification of the propositions. Cascade filters contain all of the minor algorithms needed for effective object detection verification. The new approach does not have the drawbacks of the classic clustering approaches and gives a substantial control over process of detection. Method exhibits an exceptionally high detection rate in conjunction with a low false detection chance in comparison to alternative methods.
We present an integrated framework for using Convolutional Networks for classification, localization and detection. We show how a multiscale and sliding window approach can be efficiently implemented within a ConvNet. We also introduce a novel deep learning approach to localization by learning to predict object boundaries. Bounding boxes are then accumulated rather than suppressed in order to increase detection confidence. We show that different tasks can be learned simultaneously using a single shared network. This integrated framework is the winner of the localization task of the ImageNet Large Scale Visual Recognition Challenge 2013 (ILSVRC2013) and obtained very competitive results for the detection and classifications tasks. In post-competition work, we establish a new state of the art for the detection task. Finally, we release a feature extractor from our best model called OverFeat.
체화 인공지능(Embodied AI)은 제로샷(zero-shot) 물체 목표 내비게이션(ObjectNav)을 가능하게 하기 위해 사전학습(pre-training)된 비전-언어 모델(VLM)로 구축한 질의 가능한 시맨틱 지도에 점점 더 의존하고 있습니다. 그러나 기존 접근 방식은 일반적으로 텍스트 전용 쿼리에 의존하므로 세분화된 객체 카테고리로 갈수록 의미적 구체성이 높아짐에 따라 신뢰도가 떨어집니다. 본 논문에서는 질의 가능한 지도에서의 그라운딩(grounding)을 개선하기 위해 웹에서 수집한 이미지로 텍스트 객체 쿼리를 강화하는 제로샷 플러그 앤 플레이 프레임워크인 IMPRINT를 소개합니다. 검색된 이미지는 비전-언어 모델을 사용하여 인코딩되고, 시맨틱 지도와 매칭되어 유사도 지도를 생성하며, 종합되어 문맥 인식 위치 추정을 제공합니다. 특히 이는 기본 내비게이션 정책의 추가 학습(training)이나 수정을 전혀 요구하지 않습니다. 롱테일(long-tail) 행동을 명시적으로 평가하기 위해 Habitat Synthetic Scenes를 기반으로 구축되고 의미론적으로 구체적인 하위 카테고리를 특징으로 하는 새로운 ObjectNav 벤치마크인 HSSD-rare를 제시합니다. OVON과 HSSD-rare 전반에서 이미지 조건부 쿼리는 객체 그라운딩을 일관되게 개선하고 엔드투엔드(end-to-end) 내비게이션 성능 향상을 가져옵니다. 추가 분석을 통해 위치 추정 성능 향상을 내비게이션 성능으로 전환하는 것은 다운스트림 탐지 품질에 결정적으로 의존함을 확인하였으며, 이는 롱테일 체화 내비게이션의 주요 시스템 병목 현상을 강조합니다.
Human-robot interaction for assistive technologies relies on the prediction of affordances, which are the potential actions a robot can perform on objects. Predicting object affordances from visual perception is formulated differently for tasks such as grasping detection, affordance classification, affordance segmentation, and hand-object interaction synthesis. In this work, we highlight the reproducibility issue in these redefinitions, making comparative benchmarks unfair and unreliable. To address this problem, we propose a unified formulation for visual affordance prediction, provide a comprehensive and systematic review of previous works highlighting strengths and limitations of methods and datasets, and analyse what challenges reproducibility. To favour transparency, we introduce the Affordance Sheet, a document to detail the proposed solution, the datasets, and the validation. As the physical properties of an object influence the interaction with the robot, we present a generic framework that links visual affordance prediction to the physical world. Using the weight of an object as an example for this framework, we discuss how estimating object mass can affect the affordance prediction. Our approach bridges the gap between affordance perception and robot actuation, and accounts for the complete information about objects of interest and how the robot interacts with them to accomplish its task.
Single-Domain Generalized Object Detection~(S-DGOD) aims to train an object detector on a single source domain while generalizing well to diverse unseen target domains, making it suitable for multimedia applications that involve various domain shifts, such as intelligent video surveillance and VR/AR technologies. With the success of large-scale Vision-Language Models, recent S-DGOD approaches exploit pre-trained vision-language knowledge to guide invariant feature learning across visual domains. However, the utilized knowledge remains at a coarse-grained level~(e.g., the textual description of adverse weather paired with the image) and serves as an implicit regularization for guidance, struggling to learn accurate region- and object-level features in varying domains. In this work, we propose a new cross-modal feature learning method, which can capture generalized and discriminative regional features for S-DGOD tasks. The core of our method is the mechanism of Cross-modal and Region-aware Feature Interaction, which simultaneously learns both inter-modal and intra-modal regional invariance through dynamic interactions between fine-grained textual and visual features. Moreover, we design a simple but effective strategy called Cross-domain Proposal Refining and Mixing, which aligns the position of region proposals across multiple domains and diversifies them, enhancing the localization ability of detectors in unseen scenarios. Our method achieves new state-of-the-art results on S-DGOD benchmark datasets, with improvements of +8.8\%~mPC on Cityscapes-C and +7.9\%~mPC on DWD over baselines, demonstrating its efficacy.
We propose a weakly supervised method using two algorithms to predict object bounding boxes given only an image classification dataset. First algorithm is a simple Fully Convolutional Network (FCN) trained to classify object instances. We use the property of FCN to return a mask for images larger than training images to get a primary output segmentation mask during test time by passing an image pyramid to it. We enhance the FCN output mask into final output bounding boxes by a Convolutional Encoder-Decoder (ConvAE) viz. the second algorithm. ConvAE is trained to localize objects on an artificially generated dataset of output segmentation masks. We demonstrate the effectiveness of this method in localizing objects in grocery shelves where annotating data for object detection is hard due to variety of objects. This method can be extended to any problem domain where collecting images of objects is easy and annotating their coordinates is hard.
Detecting carried objects is one of the requirements for developing systems to reason about activities involving people and objects. We present an approach to detect carried objects from a single video frame with a novel method that incorporates features from multiple scales. Initially, a foreground mask in a video frame is segmented into multi-scale superpixels. Then the human-like regions in the segmented area are identified by matching a set of extracted features from superpixels against learned features in a codebook. A carried object probability map is generated using the complement of the matching probabilities of superpixels to human-like regions and background information. A group of superpixels with high carried object probability and strong edge support is then merged to obtain the shape of the carried object. We applied our method to two challenging datasets, and results show that our method is competitive with or better than the state-of-the-art.
Understanding comprehensive assembly knowledge from videos is critical for futuristic ultra-intelligent industry. To enable technological breakthrough, we present HA-ViD - the first human assembly video dataset that features representative industrial assembly scenarios, natural procedural knowledge acquisition process, and consistent human-robot shared annotations. Specifically, HA-ViD captures diverse collaboration patterns of real-world assembly, natural human behaviors and learning progression during assembly, and granulate action annotations to subject, action verb, manipulated object, target object, and tool. We provide 3222 multi-view, multi-modality videos (each video contains one assembly task), 1.5M frames, 96K temporal labels and 2M spatial labels. We benchmark four foundational video understanding tasks: action recognition, action segmentation, object detection and multi-object tracking. Importantly, we analyze their performance for comprehending knowledge in assembly progress, process efficiency, task collaboration, skill parameters and human intention. Details of HA-ViD is available at: https://iai-hrc.github.io/ha-vid.
Uses of underwater videos to assess diversity and abundance of fish are being rapidly adopted by marine biologists. Manual processing of videos for quantification by human analysts is time and labour intensive. Automatic processing of videos can be employed to achieve the objectives in a cost and time-efficient way. The aim is to build an accurate and reliable fish detection and recognition system, which is important for an autonomous robotic platform. However, there are many challenges involved in this task (e.g. complex background, deformation, low resolution and light propagation). Recent advancement in the deep neural network has led to the development of object detection and recognition in real time scenarios. An end-to-end deep learning-based architecture is introduced which outperformed the state of the art methods and first of its kind on fish assessment task. A Region Proposal Network (RPN) introduced by an object detector termed as Faster R-CNN was combined with three classification networks for detection and recognition of fish species obtained from Remote Underwater Video Stations (RUVS). An accuracy of 82.4% (mAP) obtained from the experiments are much higher than previously proposed methods.
Underwater image enhancement is such an important low-level vision task with many applications that numerous algorithms have been proposed in recent years. These algorithms developed upon various assumptions demonstrate successes from various aspects using different data sets and different metrics. In this work, we setup an undersea image capturing system, and construct a large-scale Real-world Underwater Image Enhancement (RUIE) data set divided into three subsets. The three subsets target at three challenging aspects for enhancement, i.e., image visibility quality, color casts, and higher-level detection/classification, respectively. We conduct extensive and systematic experiments on RUIE to evaluate the effectiveness and limitations of various algorithms to enhance visibility and correct color casts on images with hierarchical categories of degradation. Moreover, underwater image enhancement in practice usually serves as a preprocessing step for mid-level and high-level vision tasks. We thus exploit the object detection performance on enhanced images as a brand new task-specific evaluation criterion. The findings from these evaluations not only confirm what is commonly believed, but also suggest promising solutions and new directions for visibility enhancement, color correction, and object detection on real-world underwater images.
Cell phone coverage and high-speed service gaps persist in rural areas in sub-Saharan Africa, impacting public access to mobile-based financial, educational, and humanitarian services. Improving maps of telecommunications infrastructure can help inform strategies to eliminate gaps in mobile coverage. Deep neural networks, paired with remote sensing images, can be used for object detection of cell towers and eliminate the need for inefficient and burdensome manual mapping to find objects over large geographic regions. In this study, we demonstrate a partially automated workflow to train an object detection model to locate cell towers using OpenStreetMap (OSM) features and high-resolution Maxar imagery. For model fine-tuning and evaluation, we curated a diverse dataset of over 6,000 unique images of cell towers in 26 countries in eastern, southern, and central Africa using automatically generated annotations from OSM points. Our model achieves an average precision at 50% Intersection over Union (IoU) (AP@50) of 81.2 with good performance across different geographies and out-of-sample testing. Accurate localization of cell towers can yield more accurate cell coverage maps, in turn enabling improved delivery of digital services for decision-support applications.
Safety and reliability are crucial for the public acceptance of autonomous driving. To ensure accurate and reliable environmental perception, intelligent vehicles must exhibit accuracy and robustness in various environments. Millimeter-wave radar, known for its high penetration capability, can operate effectively in adverse weather conditions such as rain, snow, and fog. Traditional 3D millimeter-wave radars can only provide range, Doppler, and azimuth information for objects. Although the recent emergence of 4D millimeter-wave radars has added elevation resolution, the radar point clouds remain sparse due to Constant False Alarm Rate (CFAR) operations. In contrast, cameras offer rich semantic details but are sensitive to lighting and weather conditions. Hence, this paper leverages these two highly complementary and cost-effective sensors, 4D millimeter-wave radar and camera. By integrating 4D radar spectra with depth-aware camera images and employing attention mechanisms, we fuse texture-rich images with depth-rich radar data in the Bird's Eye View (BEV) perspective, enhancing 3D object detection. Additionally, we propose using GAN-based networks to generate depth images from radar spectra in the absence of depth sensors, further improving detection accuracy.
Rendering synthetic data (e.g., 3D CAD-rendered images) to generate annotations for learning deep models in vision tasks has attracted increasing attention in recent years. However, simply applying the models learnt on synthetic images may lead to high generalization error on real images due to domain shift. To address this issue, recent progress in cross-domain recognition has featured the Mean Teacher, which directly simulates unsupervised domain adaptation as semi-supervised learning. The domain gap is thus naturally bridged with consistency regularization in a teacher-student scheme. In this work, we advance this Mean Teacher paradigm to be applicable for cross-domain detection. Specifically, we present Mean Teacher with Object Relations (MTOR) that novelly remolds Mean Teacher under the backbone of Faster R-CNN by integrating the object relations into the measure of consistency cost between teacher and student modules. Technically, MTOR firstly learns relational graphs that capture similarities between pairs of regions for teacher and student respectively. The whole architecture is then optimized with three consistency regularizations: 1) region-level consistency to align the region-level predictions between teacher and student, 2) inter-graph consistency for matching the graph structures between teacher and student, and 3) intra-graph consistency to enhance the similarity between regions of same class within the graph of student. Extensive experiments are conducted on the transfers across Cityscapes, Foggy Cityscapes, and SIM10k, and superior results are reported when comparing to state-of-the-art approaches. More remarkably, we obtain a new record of single model: 22.8% of mAP on Syn2Real detection dataset.
Recent vision-only perception models for autonomous driving achieved promising results by encoding multi-view image features into Bird's-Eye-View (BEV) space. A critical step and the main bottleneck of these methods is transforming image features into the BEV coordinate frame. This paper focuses on leveraging geometry information, such as depth, to model such feature transformation. Existing works rely on non-parametric depth distribution modeling leading to significant memory consumption, or ignore the geometry information to address this problem. In contrast, we propose to use parametric depth distribution modeling for feature transformation. We first lift the 2D image features to the 3D space defined for the ego vehicle via a predicted parametric depth distribution for each pixel in each view. Then, we aggregate the 3D feature volume based on the 3D space occupancy derived from depth to the BEV frame. Finally, we use the transformed features for downstream tasks such as object detection and semantic segmentation. Existing semantic segmentation methods do also suffer from an hallucination problem as they do not take visibility information into account. This hallucination can be particularly problematic for subsequent modules such as control and planning. To mitigate the issue, our method provides depth uncertainty and reliable visibility-aware estimations. We further leverage our parametric depth modeling to present a novel visibility-aware evaluation metric that, when taken into account, can mitigate the hallucination problem. Extensive experiments on object detection and semantic segmentation on the nuScenes datasets demonstrate that our method outperforms existing methods on both tasks.