Online construction of open-ended language scenes is crucial for robotic applications, where open-vocabulary interactive scene understanding is required. Recently, neural implicit representation has provided a promising direction for online interactive mapping. However, implementing open-vocabulary scene understanding capability into online neural implicit mapping still faces three challenges: lack of local scene updating ability, blurry spatial hierarchical semantic segmentation and difficulty in maintaining multi-view consistency. To this end, we proposed O2V-mapping, which utilizes voxel-based language and geometric features to create an open-vocabulary field, thus allowing for local updates during online training process. Additionally, we leverage a foundational model for image segmentation to extract language features on object-level entities, achieving clear segmentation boundaries and hierarchical semantic features. For the purpose of preserving consistency in 3D object properties across different viewpoints, we propose a spatial adaptive voxel adjustment mechanism and a multi-view weight selection method. Extensive experiments on open-vocabulary object localization and semantic segmentation demonstrate that O2V-mapping achieves online construction of language scenes while enhancing accuracy, outperforming the previous SOTA method.
3D object detection based on roadside cameras is an additional way for autonomous driving to alleviate the challenges of occlusion and short perception range from vehicle cameras. Previous methods for roadside 3D object detection mainly focus on modeling the depth or height of objects, neglecting the stationary of cameras and the characteristic of inter-frame consistency. In this work, we propose a novel framework, namely MOSE, for MOnocular 3D object detection with Scene cuEs. The scene cues are the frame-invariant scene-specific features, which are crucial for object localization and can be intuitively regarded as the height between the surface of the real road and the virtual ground plane. In the proposed framework, a scene cue bank is designed to aggregate scene cues from multiple frames of the same scene with a carefully designed extrinsic augmentation strategy. Then, a transformer-based decoder lifts the aggregated scene cues as well as the 3D position embeddings for 3D object location, which boosts generalization ability in heterologous scenes. The extensive experiment results on two public benchmarks demonstrate the state-of-the-art performance of the proposed method, which surpasses the existing methods by a large margin.
Object detection in remotely sensed satellite pictures is fundamental in many fields such as biophysical, and environmental monitoring. While deep learning algorithms are constantly evolving, they have been mostly implemented and tested on popular ground-based taken photos. This paper critically evaluates and compares a suite of advanced object detection algorithms customized for the task of identifying aircraft within satellite imagery. Using the large HRPlanesV2 dataset, together with a rigorous validation with the GDIT dataset, this research encompasses an array of methodologies including YOLO versions 5 and 8, Faster RCNN, CenterNet, RetinaNet, RTMDet, and DETR, all trained from scratch. This exhaustive training and validation study reveal YOLOv5 as the preeminent model for the specific case of identifying airplanes from remote sensing data, showcasing high precision and adaptability across diverse imaging conditions. This research highlight the nuanced performance landscapes of these algorithms, with YOLOv5 emerging as a robust solution for aerial object detection, underlining its importance through superior mean average precision, Recall, and Intersection over Union scores. The findings described here underscore the fundamental role of algorithm selection aligned with the specific demands of satellite imagery analysis and extend a comprehensive framework to evaluate model efficacy. The benchmark toolkit and codes, available via https://github.com/toelt-llc/FlightScope_Bench, aims to further exploration and innovation in the realm of remote sensing object detection, paving the way for improved analytical methodologies in satellite imagery applications.
Rotation-equivariance is an essential yet challenging property in oriented object detection. While general object detectors naturally leverage robustness to spatial shifts due to the translation-equivariance of the conventional CNNs, achieving rotation-equivariance remains an elusive goal. Current detectors deploy various alignment techniques to derive rotation-invariant features, but still rely on high capacity models and heavy data augmentation with all possible rotations. In this paper, we introduce a Fully Rotation-Equivariant Oriented Object Detector (FRED), whose entire process from the image to the bounding box prediction is strictly equivariant. Specifically, we decouple the invariant task (object classification) and the equivariant task (object localization) to achieve end-to-end equivariance. We represent the bounding box as a set of rotation-equivariant vectors to implement rotation-equivariant localization. Moreover, we utilized these rotation-equivariant vectors as offsets in the deformable convolution, thereby enhancing the existing advantages of spatial adaptation. Leveraging full rotation-equivariance, our FRED demonstrates higher robustness to image-level rotation compared to existing methods. Furthermore, we show that FRED is one step closer to non-axis aligned learning through our experiments. Compared to state-of-the-art methods, our proposed method delivers comparable performance on DOTA-v1.0 and outperforms by 1.5 mAP on DOTA-v1.5, all while significantly reducing the model parameters to 16%.
The advent of Vision Language Models (VLM) has allowed researchers to investigate the visual understanding of a neural network using natural language. Beyond object classification and detection, VLMs are capable of visual comprehension and common-sense reasoning. This naturally led to the question: How do VLMs respond when the image itself is inherently unreasonable? To this end, we present IllusionVQA: a diverse dataset of challenging optical illusions and hard-to-interpret scenes to test the capability of VLMs in two distinct multiple-choice VQA tasks - comprehension and soft localization. GPT4V, the best performing VLM, achieves 62.99% accuracy (4-shot) on the comprehension task and 49.7% on the localization task (4-shot and Chain-of-Thought). Human evaluation reveals that humans achieve 91.03% and 100% accuracy in comprehension and localization. We discover that In-Context Learning (ICL) and Chain-of-Thought reasoning substantially degrade the performance of Gemini-Pro in the localization task. Tangentially, we discover a potential weakness in the ICL capabilities of VLMs: they fail to locate optical illusions even when the correct answer is in the context window as a few-shot example.
3D single object tracking within LIDAR point clouds is a pivotal task in computer vision, with profound implications for autonomous driving and robotics. However, existing methods, which depend solely on appearance matching via Siamese networks or utilize motion information from successive frames, encounter significant challenges. Issues such as similar objects nearby or occlusions can result in tracker drift. To mitigate these challenges, we design an innovative spatio-temporal bi-directional cross-frame distractor filtering tracker, named STMD-Tracker. Our first step involves the creation of a 4D multi-frame spatio-temporal graph convolution backbone. This design separates KNN graph spatial embedding and incorporates 1D temporal convolution, effectively capturing temporal fluctuations and spatio-temporal information. Subsequently, we devise a novel bi-directional cross-frame memory procedure. This integrates future and synthetic past frame memory to enhance the current memory, thereby improving the accuracy of iteration-based tracking. This iterative memory update mechanism allows our tracker to dynamically compensate for information in the current frame, effectively reducing tracker drift. Lastly, we construct spatially reliable Gaussian masks on the fused features to eliminate distractor points. This is further supplemented by an object-aware sampling strategy, which bolsters the efficiency and precision of object localization, thereby reducing tracking errors caused by distractors. Our extensive experiments on KITTI, NuScenes and Waymo datasets demonstrate that our approach significantly surpasses the current state-of-the-art methods.
Open-vocabulary 3D scene understanding presents a significant challenge in computer vision, with wide-ranging applications in embodied agents and augmented reality systems. Existing methods adopt neurel rendering methods as 3D representations and jointly optimize color and semantic features to achieve rendering and scene understanding simultaneously. In this paper, we introduce Semantic Gaussians, a novel open-vocabulary scene understanding approach based on 3D Gaussian Splatting. Our key idea is to distill knowledge from 2D pre-trained models to 3D Gaussians. Unlike existing methods, we design a versatile projection approach that maps various 2D semantic features from pre-trained image encoders into a novel semantic component of 3D Gaussians, which is based on spatial relationship and need no additional training. We further build a 3D semantic network that directly predicts the semantic component from raw 3D Gaussians for fast inference. The quantitative results on ScanNet segmentation and LERF object localization demonstates the superior performance of our method. Additionally, we explore several applications of Semantic Gaussians including object part segmentation, instance segmentation, scene editing, and spatiotemporal segmentation with better qualitative results over 2D and 3D baselines, highlighting its versatility and effectiveness on supporting diverse downstream tasks.
Deep neural network (DNN) based machine perception frameworks process the entire input in a one-shot manner to provide answers to both "what object is being observed" and "where it is located". In contrast, the "two-stream hypothesis" from neuroscience explains the neural processing in the human visual cortex as an active vision system that utilizes two separate regions of the brain to answer the what and the where questions. In this work, we propose a machine learning framework inspired by the "two-stream hypothesis" and explore the potential benefits that it offers. Specifically, the proposed framework models the following mechanisms: 1) ventral (what) stream focusing on the input regions perceived by the fovea part of an eye (foveation), 2) dorsal (where) stream providing visual guidance, and 3) iterative processing of the two streams to calibrate visual focus and process the sequence of focused image patches. The training of the proposed framework is accomplished by label-based DNN training for the ventral stream model and reinforcement learning for the dorsal stream model. We show that the two-stream foveation-based learning is applicable to the challenging task of weakly-supervised object localization (WSOL), where the training data is limited to the object class or its attributes. The framework is capable of both predicting the properties of an object and successfully localizing it by predicting its bounding box. We also show that, due to the independent nature of the two streams, the dorsal model can be applied on its own to unseen images to localize objects from different datasets.
Training high-accuracy 3D detectors necessitates massive labeled 3D annotations with 7 degree-of-freedom, which is laborious and time-consuming. Therefore, the form of point annotations is proposed to offer significant prospects for practical applications in 3D detection, which is not only more accessible and less expensive but also provides strong spatial information for object localization. In this paper, we empirically discover that it is non-trivial to merely adapt Point-DETR to its 3D form, encountering two main bottlenecks: 1) it fails to encode strong 3D prior into the model, and 2) it generates low-quality pseudo labels in distant regions due to the extreme sparsity of LiDAR points. To overcome these challenges, we introduce Point-DETR3D, a teacher-student framework for weakly semi-supervised 3D detection, designed to fully capitalize on point-wise supervision within a constrained instance-wise annotation budget.Different from Point-DETR which encodes 3D positional information solely through a point encoder, we propose an explicit positional query initialization strategy to enhance the positional prior. Considering the low quality of pseudo labels at distant regions produced by the teacher model, we enhance the detector's perception by incorporating dense imagery data through a novel Cross-Modal Deformable RoI Fusion (D-RoI).Moreover, an innovative point-guided self-supervised learning technique is proposed to allow for fully exploiting point priors, even in student models.Extensive experiments on representative nuScenes dataset demonstrate our Point-DETR3D obtains significant improvements compared to previous works. Notably, with only 5% of labeled data, Point-DETR3D achieves over 90% performance of its fully supervised counterpart.
Detecting marine objects inshore presents challenges owing to algorithmic intricacies and complexities in system deployment. We propose a difficulty-aware edge-cloud collaborative sensing system that splits the task into object localization and fine-grained classification. Objects are classified either at the edge or within the cloud, based on their estimated difficulty. The framework comprises a low-power device-tailored front-end model for object localization, classification, and difficulty estimation, along with a transformer-graph convolutional network-based back-end model for fine-grained classification. Our system demonstrates superior performance ([email omitted] +4.3%}) on widely used marine object detection datasets, significantly reducing both data transmission volume (by 95.43%) and energy consumption (by 72.7%}) at the system level. We validate the proposed system across various embedded system platforms and in real-world scenarios involving drone deployment.
Existing object localization methods are tailored to locate specific classes of objects, relying heavily on abundant labeled data for model optimization. However, acquiring large amounts of labeled data is challenging in many real-world scenarios, significantly limiting the broader application of localization models. To bridge this research gap, this paper defines a novel task named Few-Shot Object Localization (FSOL), which aims to achieve precise localization with limited samples. This task achieves generalized object localization by leveraging a small number of labeled support samples to query the positional information of objects within corresponding images. To advance this field, we design an innovative high-performance baseline model. This model integrates a dual-path feature augmentation module to enhance shape association and gradient differences between supports and query images, alongside a self query module to explore the association between feature maps and query images. Experimental results demonstrate a significant performance improvement of our approach in the FSOL task, establishing an efficient benchmark for further research. All codes and data are available at https://github.com/Ryh1218/FSOL.
Automation in medical imaging is quite challenging due to the unavailability of annotated datasets and the scarcity of domain experts. In recent years, deep learning techniques have solved some complex medical imaging tasks like disease classification, important object localization, segmentation, etc. However, most of the task requires a large amount of annotated data for their successful implementation. To mitigate the shortage of data, different generative models are proposed for data augmentation purposes which can boost the classification performances. For this, different synthetic medical image data generation models are developed to increase the dataset. Unpaired image-to-image translation models here shift the source domain to the target domain. In the breast malignancy identification domain, FNAC is one of the low-cost low-invasive modalities normally used by medical practitioners. But availability of public datasets in this domain is very poor. Whereas, for automation of cytology images, we need a large amount of annotated data. Therefore synthetic cytology images are generated by translating breast histopathology samples which are publicly available. In this study, we have explored traditional image-to-image transfer models like CycleGAN, and Neural Style Transfer. Further, it is observed that the generated cytology images are quite similar to real breast cytology samples by measuring FID and KID scores.
Recently, convolutional neural networks (CNNs) with large size kernels have attracted much attention in the computer vision field, following the success of the Vision Transformers. Large kernel CNNs have been reported to perform well in downstream vision tasks as well as in classification performance. The reason for the high-performance of large kernel CNNs in downstream tasks has been attributed to the large effective receptive field (ERF) produced by large size kernels, but this view has not been fully tested. We therefore revisit the performance of large kernel CNNs in downstream task, focusing on the weakly supervised object localization (WSOL) task. WSOL, a difficult downstream task that is not fully supervised, provides a new angle to explore the capabilities of the large kernel CNNs. Our study compares the modern large kernel CNNs ConvNeXt, RepLKNet, and SLaK to test the validity of the naive expectation that ERF size is important for improving downstream task performance. Our analysis of the factors contributing to high performance provides a different perspective, in which the main factor is feature map improvement. Furthermore, we find that modern CNNs are robust to the CAM problems of local regions of objects being activated, which has long been discussed in WSOL. CAM is the most classic WSOL method, but because of the above-mentioned problems, it is often used as a baseline method for comparison. However, experiments on the CUB-200-2011 dataset show that simply combining a large kernel CNN, CAM, and simple data augmentation methods can achieve performance (90.99% MaxBoxAcc) comparable to the latest WSOL method, which is CNN-based and requires special training or complex post-processing. The code is available at https://github.com/snskysk/CAM-Back-Again.
We present the All-Seeing Project V2: a new model and dataset designed for understanding object relations in images. Specifically, we propose the All-Seeing Model V2 (ASMv2) that integrates the formulation of text generation, object localization, and relation comprehension into a relation conversation (ReC) task. Leveraging this unified task, our model excels not only in perceiving and recognizing all objects within the image but also in grasping the intricate relation graph between them, diminishing the relation hallucination often encountered by Multi-modal Large Language Models (MLLMs). To facilitate training and evaluation of MLLMs in relation understanding, we created the first high-quality ReC dataset ({AS-V2) which is aligned with the format of standard instruction tuning data. In addition, we design a new benchmark, termed Circular-based Relation Probing Evaluation (CRPE) for comprehensively evaluating the relation comprehension capabilities of MLLMs. Notably, our ASMv2 achieves an overall accuracy of 52.04 on this relation-aware benchmark, surpassing the 43.14 of LLaVA-1.5 by a large margin. We hope that our work can inspire more future research and contribute to the evolution towards artificial general intelligence. Our project is released at https://github.com/OpenGVLab/all-seeing.
Monocular 3D detection (M3D) aims for precise 3D object localization from a single-view image which usually involves labor-intensive annotation of 3D detection boxes. Weakly supervised M3D has recently been studied to obviate the 3D annotation process by leveraging many existing 2D annotations, but it often requires extra training data such as LiDAR point clouds or multi-view images which greatly degrades its applicability and usability in various applications. We propose SKD-WM3D, a weakly supervised monocular 3D detection framework that exploits depth information to achieve M3D with a single-view image exclusively without any 3D annotations or other training data. One key design in SKD-WM3D is a self-knowledge distillation framework, which transforms image features into 3D-like representations by fusing depth information and effectively mitigates the inherent depth ambiguity in monocular scenarios with little computational overhead in inference. In addition, we design an uncertainty-aware distillation loss and a gradient-targeted transfer modulation strategy which facilitate knowledge acquisition and knowledge transfer, respectively. Extensive experiments show that SKD-WM3D surpasses the state-of-the-art clearly and is even on par with many fully supervised methods.
From a falcon detecting prey to humans recognizing faces, many species exhibit extraordinary abilities in rapid visual localization and classification. These are made possible by a specialized retinal region called the fovea, which provides high acuity at the center of vision while maintaining lower resolution in the periphery. This distinctive spatial organization, preserved along the early visual pathway through retinotopic mapping, is fundamental to biological vision, yet remains largely unexplored in machine learning. Our study investigates how incorporating foveated retinotopy may benefit deep convolutional neural networks (CNNs) in image classification tasks. By implementing a foveated retinotopic transformation in the input layer of standard ResNet models and re-training them, we maintain comparable classification accuracy while enhancing the network's robustness to scale and rotational perturbations. Although this architectural modification introduces increased sensitivity to fixation point shifts, we demonstrate how this apparent limitation becomes advantageous: variations in classification probabilities across different gaze positions serve as effective indicators for object localization. Our findings suggest that foveated retinotopic mapping encodes implicit knowledge about visual object geometry, offering an efficient solution to the visual search problem - a capability crucial for many living species.
Visually-conditioned language models (VLMs) have seen growing adoption in applications such as visual dialogue, scene understanding, and robotic task planning; adoption that has fueled a wealth of new models such as LLaVa, InstructBLIP, and PaLI-3. Despite the volume of new releases, key design decisions around image preprocessing, architecture, and optimization are under-explored, making it challenging to understand what factors account for model performance $-$ a challenge further complicated by the lack of objective, consistent evaluations. To address these gaps, we first compile a suite of standardized evaluations spanning visual question answering, object localization, and challenge sets that probe properties such as hallucination; evaluations that provide fine-grained insight VLM capabilities. Second, we rigorously investigate VLMs along key design axes, including pretrained visual representations and training from base vs. instruct-tuned language models, amongst others. We couple our analysis with three resource contributions: (1) a unified framework for evaluating VLMs, (2) optimized, flexible training code, and (3) checkpoints for all models, including a family of VLMs at the 7-13B scale that strictly outperform InstructBLIP and LLaVa v1.5, the state-of-the-art in open VLMs.
Recent camera-based 3D object detection is limited by the precision of transforming from image to 3D feature spaces, as well as the accuracy of object localization within the 3D space. This paper aims to address such a fundamental problem of camera-based 3D object detection: How to effectively learn depth information for accurate feature lifting and object localization. Different from previous methods which directly predict depth distributions by using a supervised estimation model, we propose a cascade framework consisting of two depth-aware learning paradigms. First, a depth estimation (DE) scheme leverages relative depth information to realize the effective feature lifting from 2D to 3D spaces. Furthermore, a depth calibration (DC) scheme introduces depth reconstruction to further adjust the 3D object localization perturbation along the depth axis. In practice, the DE is explicitly realized by using both the absolute and relative depth optimization loss to promote the precision of depth prediction, while the capability of DC is implicitly embedded into the detection Transformer through a depth denoising mechanism in the training phase. The entire model training is accomplished through an end-to-end manner. We propose a baseline detector and evaluate the effectiveness of our proposal with +2.2%/+2.7% NDS/mAP improvements on NuScenes benchmark, and gain a comparable performance with 55.9%/45.7% NDS/mAP. Furthermore, we conduct extensive experiments to demonstrate its generality based on various detectors with about +2% NDS improvements.
Large Vision-Language Models (VLMs) have demonstrated impressive performance on complex tasks involving visual input with natural language instructions. However, it remains unclear to what extent capabilities on natural images transfer to Earth observation (EO) data, which are predominantly satellite and aerial images less common in VLM training data. In this work, we propose a comprehensive benchmark to gauge the progress of VLMs toward being useful tools for EO data by assessing their abilities on scene understanding, localization and counting, and change detection tasks. Motivated by real-world applications, our benchmark includes scenarios like urban monitoring, disaster relief, land use, and conservation. We discover that, although state-of-the-art VLMs like GPT-4V possess extensive world knowledge that leads to strong performance on open-ended tasks like location understanding and image captioning, their poor spatial reasoning limits usefulness on object localization and counting tasks. Our benchmark will be made publicly available at https://vleo.danielz.ch/ and on Hugging Face at https://huggingface.co/collections/mit-ei/vleo-benchmark-datasets-65b789b0466555489cce0d70 for easy model evaluation.
Point-based object localization (POL), which pursues high-performance object sensing under low-cost data annotation, has attracted increased attention. However, the point annotation mode inevitably introduces semantic variance due to the inconsistency of annotated points. Existing POL heavily rely on strict annotation rules, which are difficult to define and apply, to handle the problem. In this study, we propose coarse point refinement (CPR), which to our best knowledge is the first attempt to alleviate semantic variance from an algorithmic perspective. CPR reduces the semantic variance by selecting a semantic centre point in a neighbourhood region to replace the initial annotated point. Furthermore, We design a sampling region estimation module to dynamically compute a sampling region for each object and use a cascaded structure to achieve end-to-end optimization. We further integrate a variance regularization into the structure to concentrate the predicted scores, yielding CPR++. We observe that CPR++ can obtain scale information and further reduce the semantic variance in a global region, thus guaranteeing high-performance object localization. Extensive experiments on four challenging datasets validate the effectiveness of both CPR and CPR++. We hope our work can inspire more research on designing algorithms rather than annotation rules to address the semantic variance problem in POL. The dataset and code will be public at github.com/ucas-vg/PointTinyBenchmark.