Existing perception models achieve great success by learning from large amounts of labeled data, but they still struggle with open-world scenarios. To alleviate this issue, researchers introduce open-set perception tasks to detect or segment unseen objects in the training set. However, these models require predefined object categories as inputs during inference, which are not available in real-world scenarios. Recently, researchers pose a new and more practical problem, \textit{i.e.}, open-ended object detection, which discovers unseen objects without any object categories as inputs. In this paper, we present VL-SAM, a training-free framework that combines the generalized object recognition model (\textit{i.e.,} Vision-Language Model) with the generalized object localization model (\textit{i.e.,} Segment-Anything Model), to address the open-ended object detection and segmentation task. Without additional training, we connect these two generalized models with attention maps as the prompts. Specifically, we design an attention map generation module by employing head aggregation and a regularized attention flow to aggregate and propagate attention maps across all heads and layers in VLM, yielding high-quality attention maps. Then, we iteratively sample positive and negative points from the attention maps with a prompt generation module and send the sampled points to SAM to segment corresponding objects. Experimental results on the long-tail instance segmentation dataset (LVIS) show that our method surpasses the previous open-ended method on the object detection task and can provide additional instance segmentation masks. Besides, VL-SAM achieves favorable performance on the corner case object detection dataset (CODA), demonstrating the effectiveness of VL-SAM in real-world applications. Moreover, VL-SAM exhibits good model generalization that can incorporate various VLMs and SAMs.
Accurate camera calibration is a well-known and widely used task in computer vision that has been researched for decades. However, the standard approach based on checkerboard calibration patterns has some drawbacks that limit its applicability. For example, the calibration pattern must be completely visible without any occlusions. Alternative solutions such as ChArUco boards allow partial occlusions, but require a higher camera resolution due to the fine details of the position encoding. We present a new calibration pattern that combines the advantages of checkerboard calibration patterns with a lightweight position coding that can be decoded at very low resolutions. The decoding algorithm includes error correction and is computationally efficient. The whole approach is backward compatible to both checkerboard calibration patterns and several checkerboard calibration algorithms. Furthermore, the method can be used not only for camera calibration but also for camera pose estimation and marker-based object localization tasks.
Low-shot object counters estimate the number of objects in an image using few or no annotated exemplars. Objects are localized by matching them to prototypes, which are constructed by unsupervised image-wide object appearance aggregation. Due to potentially diverse object appearances, the existing approaches often lead to overgeneralization and false positive detections. Furthermore, the best-performing methods train object localization by a surrogate loss, that predicts a unit Gaussian at each object center. This loss is sensitive to annotation error, hyperparameters and does not directly optimize the detection task, leading to suboptimal counts. We introduce GeCo, a novel low-shot counter that achieves accurate object detection, segmentation, and count estimation in a unified architecture. GeCo robustly generalizes the prototypes across objects appearances through a novel dense object query formulation. In addition, a novel counting loss is proposed, that directly optimizes the detection task and avoids the issues of the standard surrogate loss. GeCo surpasses the leading few-shot detection-based counters by $\sim$25\% in the total count MAE, achieves superior detection accuracy and sets a new solid state-of-the-art result across all low-shot counting setups.
Weakly supervised semantic segmentation (WSSS) approaches typically rely on class activation maps (CAMs) for initial seed generation, which often fail to capture global context due to limited supervision from image-level labels. To address this issue, we introduce DALNet, Dense Alignment Learning Network that leverages text embeddings to enhance the comprehensive understanding and precise localization of objects across different levels of granularity. Our key insight is to employ a dual-level alignment strategy: (1) Global Implicit Alignment (GIA) to capture global semantics by maximizing the similarity between the class token and the corresponding text embeddings while minimizing the similarity with background embeddings, and (2) Local Explicit Alignment (LEA) to improve object localization by utilizing spatial information from patch tokens. Moreover, we propose a cross-contrastive learning approach that aligns foreground features between image and text modalities while separating them from the background, encouraging activation in missing regions and suppressing distractions. Through extensive experiments on the PASCAL VOC and MS COCO datasets, we demonstrate that DALNet significantly outperforms state-of-the-art WSSS methods. Our approach, in particular, allows for more efficient end-to-end process as a single-stage method.
QUB-PHEO introduces a visual-based, dyadic dataset with the potential of advancing human-robot interaction (HRI) research in assembly operations and intention inference. This dataset captures rich multimodal interactions between two participants, one acting as a 'robot surrogate,' across a variety of assembly tasks that are further broken down into 36 distinct subtasks. With rich visual annotations, such as facial landmarks, gaze, hand movements, object localization, and more for 70 participants, QUB-PHEO offers two versions: full video data for 50 participants and visual cues for all 70. Designed to improve machine learning models for HRI, QUB-PHEO enables deeper analysis of subtle interaction cues and intentions, promising contributions to the field. The dataset will be available at https://github.com/exponentialR/QUB-PHEO subject to an End-User License Agreement (EULA).
In recent years, encoder-decoder networks have focused on expanding receptive fields and incorporating multi-scale context to capture global features for objects of varying sizes. However, as networks deepen, they often discard fine spatial details, impairing precise object localization. Additionally, conventional decoders' use of interpolation for upsampling leads to a loss of global context, diminishing edge segmentation accuracy. To address the above problems, we propose a novel parallel multi-resolution encoder-decoder network, namely PMR-Net for short. First, we design a parallel multi-resolution encoder and a multi-resolution context encoder. The parallel multi-resolution encoder can extract and fuse multi-scale fine-grained local features in parallel for input images with different resolutions. The multi-resolution context encoder fuses the global context semantic features of different receptive fields from different encoder branches to maintain effectively the integrity of global information. Secondly, we design a parallel multi-resolution decoder symmetrical to the structure of parallel multi-resolution encoder. The decoder can continuously supplement the global context features of low-resolution branches to the feature maps of high-resolution branches, and effectively solve the problem of global context feature loss caused by upsampling operation in the decoding process. Extensive experiment results demonstrate that our proposed PMR-Net can achieve more accurate segmentation results than state-of-the-art methods on five public available datasets. Moreover, PMR-Net is also a flexible network framework, which can meet the requirements of different scenarios by adjusting the number of network layers and the number of parallel encoder-decoder branches.
For a vision-language model (VLM) to understand the physical world, such as cause and effect, a first step is to capture the temporal dynamics of the visual world, for example how the physical states of objects evolve over time (e.g. a whole apple into a sliced apple). Our paper aims to investigate if VLMs pre-trained on web-scale data learn to encode object states, which can be extracted with zero-shot text prompts. We curate an object state recognition dataset ChangeIt-Frames, and evaluate nine open-source VLMs, including models trained with contrastive and generative objectives. We observe that while these state-of-the-art vision-language models can reliably perform object recognition, they consistently fail to accurately distinguish the objects' physical states. Through extensive experiments, we identify three areas for improvements for VLMs to better encode object states, namely the quality of object localization, the architecture to bind concepts to objects, and the objective to learn discriminative visual and language encoders on object states. Data and code are released.
This paper introduces Top-GAP, a novel regularization technique that enhances the explainability and robustness of convolutional neural networks. By constraining the spatial size of the learned feature representation, our method forces the network to focus on the most salient image regions, effectively reducing background influence. Using adversarial attacks and the Effective Receptive Field, we show that Top-GAP directs more attention towards object pixels rather than the background. This leads to enhanced interpretability and robustness. We achieve over 50% robust accuracy on CIFAR-10 with PGD $\epsilon=\frac{8}{255}$ and $20$ iterations while maintaining the original clean accuracy. Furthermore, we see increases of up to 5% accuracy against distribution shifts. Our approach also yields more precise object localization, as evidenced by up to 25% improvement in Intersection over Union (IOU) compared to methods like GradCAM and Recipro-CAM.
Natural distribution shift causes a deterioration in the perception performance of convolutional neural networks (CNNs). This comprehensive analysis for real-world traffic data addresses: 1) investigating the effect of natural distribution shift and weather augmentations on both detection quality and confidence estimation, 2) evaluating model performance for both classification and object localization, and 3) benchmarking two common uncertainty quantification methods - Ensembles and different variants of Monte-Carlo (MC) Dropout - under natural and close-to-natural distribution shift. For this purpose, a novel dataset has been curated from publicly available autonomous driving datasets. The in-distribution (ID) data is based on cutouts of a single object, for which both class and bounding box annotations are available. The six distribution-shift datasets cover adverse weather scenarios, simulated rain and fog, corner cases, and out-of-distribution data. A granular analysis of CNNs under distribution shift allows to quantize the impact of different types of shifts on both, task performance and confidence estimation: ConvNeXt-Tiny is more robust than EfficientNet-B0; heavy rain degrades classification stronger than localization, contrary to heavy fog; integrating MC-Dropout into selected layers only has the potential to enhance task performance and confidence estimation, whereby the identification of these layers depends on the type of distribution shift and the considered task.
Visual sound localization is a typical and challenging problem that predicts the location of objects corresponding to the sound source in a video. Previous methods mainly used the audio-visual association between global audio and one-scale visual features to localize sounding objects in each image. Despite their promising performance, they omitted multi-scale visual features of the corresponding image, and they cannot learn discriminative regions compared to ground truths. To address this issue, we propose a novel multi-scale multi-instance visual sound localization framework, namely M2VSL, that can directly learn multi-scale semantic features associated with sound sources from the input image to localize sounding objects. Specifically, our M2VSL leverages learnable multi-scale visual features to align audio-visual representations at multi-level locations of the corresponding image. We also introduce a novel multi-scale multi-instance transformer to dynamically aggregate multi-scale cross-modal representations for visual sound localization. We conduct extensive experiments on VGGSound-Instruments, VGG-Sound Sources, and AVSBench benchmarks. The results demonstrate that the proposed M2VSL can achieve state-of-the-art performance on sounding object localization and segmentation.
Recent developments in vision language models (VLM) have shown great potential for diverse applications related to image understanding. In this study, we have explored state-of-the-art VLM models for vision-based transportation engineering tasks such as image classification and object detection. The image classification task involves congestion detection and crack identification, whereas, for object detection, helmet violations were identified. We have applied open-source models such as CLIP, BLIP, OWL-ViT, Llava-Next, and closed-source GPT-4o to evaluate the performance of these state-of-the-art VLM models to harness the capabilities of language understanding for vision-based transportation tasks. These tasks were performed by applying zero-shot prompting to the VLM models, as zero-shot prompting involves performing tasks without any training on those tasks. It eliminates the need for annotated datasets or fine-tuning for specific tasks. Though these models gave comparative results with benchmark Convolutional Neural Networks (CNN) models in the image classification tasks, for object localization tasks, it still needs improvement. Therefore, this study provides a comprehensive evaluation of the state-of-the-art VLM models highlighting the advantages and limitations of the models, which can be taken as the baseline for future improvement and wide-scale implementation.
In clinical practice, segmenting specific lesions based on the needs of physicians can significantly enhance diagnostic accuracy and treatment efficiency. However, conventional lesion segmentation models lack the flexibility to distinguish lesions according to specific requirements. Given the practical advantages of using text as guidance, we propose a novel model, Language-guided Scale-aware MedSegmentor (LSMS), which segments target lesions in medical images based on given textual expressions. We define this as a new task termed Referring Lesion Segmentation (RLS). To address the lack of suitable benchmarks for RLS, we construct a vision-language medical dataset named Reference Hepatic Lesion Segmentation (RefHL-Seg). LSMS incorporates two key designs: (i) Scale-Aware Vision-Language attention module, which performs visual feature extraction and vision-language alignment in parallel. By leveraging diverse convolutional kernels, this module acquires rich visual representations and interacts closely with linguistic features, thereby enhancing the model's capacity for precise object localization. (ii) Full-Scale Decoder, which globally models multi-modal features across multiple scales and captures complementary information between them to accurately delineate lesion boundaries. Additionally, we design a specialized loss function comprising both segmentation loss and vision-language contrastive loss to better optimize cross-modal learning. We validate the performance of LSMS on RLS as well as on conventional lesion segmentation tasks across multiple datasets. Our LSMS consistently achieves superior performance with significantly lower computational cost. Code and datasets will be released.
Cooperative multi-monostatic sensing enables accurate positioning of passive targets by combining the sensed environment of multiple base stations (BS). In this work, we propose a novel fusion algorithm that optimally finds the weight to combine the time-of-arrival (ToA) and angle-of-arrival (AoA) likelihood probability density function (PDF) of multiple BSs. In particular, we employ a log-linear pooling function that fuses all BSs' PDFs using a weighted geometric average. We formulated an optimization problem that minimizes the Reverse Kullback Leibler Divergence (RKLD) and proposed an iterative algorithm based on the Monte Carlo importance sampling (MCIS) approach to obtain the optimal fusion weights. Numerical results verify that our proposed fusion scheme with optimal weights outperforms the existing benchmark in terms of positioning accuracy in both unbiased (line-of-sight only) and biased (multipath-rich environment) scenarios.
Millimeter wave (mmWave) multiple-input multiple-output (MIMO) systems capable of integrated sensing and communication (ISAC) constitute a key technology for connected autonomous vehicles (CAVs). In this context, we propose a multi-beam object-localization (MBOL) model for enhancing the sensing beampattern (SBP) gain of adjacent objects in CAV scenarios. Given the ultra-narrow beams of mmWave MIMO systems, a single pencil beam is unsuitable for closely located objects, which tend to require multiple beams. Hence, we formulate the SBP gain maximization problem, considering also the constraints on the signal-to-interference and noise ratio (SINR) of the communication users (CUs), on the transmit power, and the constant modulus of the phase-shifters in the mmWave hybrid transceiver. To solve this non-convex problem, we propose a penalty-based triple alternating optimization algorithm to design the hybrid beamformer. Finally, simulation results are provided for demonstrating the efficacy of the proposed model.
Event camera-based visual tracking has drawn more and more attention in recent years due to the unique imaging principle and advantages of low energy consumption, high dynamic range, and dense temporal resolution. Current event-based tracking algorithms are gradually hitting their performance bottlenecks, due to the utilization of vision Transformer and the static template for target object localization. In this paper, we propose a novel Mamba-based visual tracking framework that adopts the state space model with linear complexity as a backbone network. The search regions and target template are fed into the vision Mamba network for simultaneous feature extraction and interaction. The output tokens of search regions will be fed into the tracking head for target localization. More importantly, we consider introducing a dynamic template update strategy into the tracking framework using the Memory Mamba network. By considering the diversity of samples in the target template library and making appropriate adjustments to the template memory module, a more effective dynamic template can be integrated. The effective combination of dynamic and static templates allows our Mamba-based tracking algorithm to achieve a good balance between accuracy and computational cost on multiple large-scale datasets, including EventVOT, VisEvent, and FE240hz. The source code will be released on https://github.com/Event-AHU/MambaEVT
Today's advanced driver assistance systems (ADAS), like adaptive cruise control or rear collision warning, are finding broader adoption across vehicle classes. Integrating such advanced, multimodal Large Language Models (LLMs) on board a vehicle, which are capable of processing text, images, audio, and other data types, may have the potential to greatly enhance passenger comfort. Yet, an LLM's hallucinations are still a major challenge to be addressed. In this paper, we systematically assessed potential hallucination detection strategies for such LLMs in the context of object detection in vision-based data on the example of pedestrian detection and localization. We evaluate three hallucination detection strategies applied to two state-of-the-art LLMs, the proprietary GPT-4V and the open LLaVA, on two datasets (Waymo/US and PREPER CITY/Sweden). Our results show that these LLMs can describe a traffic situation to an impressive level of detail but are still challenged for further analysis activities such as object localization. We evaluate and extend hallucination detection approaches when applying these LLMs to video sequences in the example of pedestrian detection. Our experiments show that, at the moment, the state-of-the-art proprietary LLM performs much better than the open LLM. Furthermore, consistency enhancement techniques based on voting, such as the Best-of-Three (BO3) method, do not effectively reduce hallucinations in LLMs that tend to exhibit high false negatives in detecting pedestrians. However, extending the hallucination detection by including information from the past helps to improve results.
General-purpose object placement is a fundamental capability of an intelligent generalist robot, i.e., being capable of rearranging objects following human instructions even in novel environments. To achieve this, we break the rearrangement down into three parts, including object localization, goal imagination and robot control, and propose a framework named SPORT. SPORT leverages pre-trained large vision models for broad semantic reasoning about objects, and learns a diffusion-based 3D pose estimator to ensure physically-realistic results. Only object types (to be moved or reference) are communicated between these two parts, which brings two benefits. One is that we can fully leverage the powerful ability of open-set object localization and recognition since no specific fine-tuning is needed for robotic scenarios. Furthermore, the diffusion-based estimator only need to "imagine" the poses of the moving and reference objects after the placement, while no necessity for their semantic information. Thus the training burden is greatly reduced and no massive training is required. The training data for goal pose estimation is collected in simulation and annotated with GPT-4. A set of simulation and real-world experiments demonstrate the potential of our approach to accomplish general-purpose object rearrangement, placing various objects following precise instructions.
Image classification is a fundamental computer vision task and an important baseline for deep metric learning. In decades efforts have been made on enhancing image classification accuracy by using deep learning models while less attention has been paid on the reasoning aspect of the recognition, i.e., predictions could be made because of background or other surrounding objects rather than the target object. Hierarchical knowledge about image categories depicts inter-class similarities or dissimilarities. Effective fusion of such knowledge with deep learning image classification models is promising in improving target object identification and enhancing the reasoning aspect of the recognition. In this paper, we propose a novel deep metric learning based method to effectively fuse prior knowledge about image categories with mainstream backbone image classification models and enhance the reasoning aspect of the recognition in an end-to-end manner. Existing deep metric learning incorporated image classification methods mainly focus on whether sampled images are from the same class. A new triplet loss function term that aligns distances in the model latent space with those in knowledge space is presented and incorporated in the proposed method to facilitate the dual-modality fusion. Extensive experiments on the CIFAR-10, CIFAR-100, Mini-ImageNet, and ImageNet-1K datasets evaluated the proposed method, and results indicate that the proposed method is effective in enhancing the reasoning aspect of image recognition in terms of weakly-supervised object localization performance.
Precision livestock farming (PLF) increasingly relies on advanced object localization techniques to monitor livestock health and optimize resource management. This study investigates the generalization capabilities of YOLOv8 and YOLOv9 models for cow detection in indoor free-stall barn settings, focusing on varying training data characteristics such as view angles and lighting, and model complexities. Leveraging the newly released public dataset, COws LOcalization (COLO) dataset, we explore three key hypotheses: (1) Model generalization is equally influenced by changes in lighting conditions and camera angles; (2) Higher model complexity guarantees better generalization performance; (3) Fine-tuning with custom initial weights trained on relevant tasks always brings advantages to detection tasks. Our findings reveal considerable challenges in detecting cows in images taken from side views and underscore the importance of including diverse camera angles in building a detection model. Furthermore, our results emphasize that higher model complexity does not necessarily lead to better performance. The optimal model configuration heavily depends on the specific task and dataset. Lastly, while fine-tuning with custom initial weights trained on relevant tasks offers advantages to detection tasks, simpler models do not benefit similarly from this approach. It is more efficient to train a simple model with pre-trained weights without relying on prior relevant information, which can require intensive labor efforts. Future work should focus on adaptive methods and advanced data augmentation to improve generalization and robustness. This study provides practical guidelines for PLF researchers on deploying computer vision models from existing studies, highlights generalization issues, and contributes the COLO dataset containing 1254 images and 11818 cow instances for further research.
Individuals who are blind or have low vision (BLV) are at a heightened risk of sharing private information if they share photographs they have taken. To facilitate developing technologies that can help them preserve privacy, we introduce BIV-Priv-Seg, the first localization dataset originating from people with visual impairments that shows private content. It contains 1,028 images with segmentation annotations for 16 private object categories. We first characterize BIV-Priv-Seg and then evaluate modern models' performance for locating private content in the dataset. We find modern models struggle most with locating private objects that are not salient, small, and lack text as well as recognizing when private content is absent from an image. We facilitate future extensions by sharing our new dataset with the evaluation server at https://vizwiz.org/tasks-and-datasets/object-localization.