The increasing adoption of 3D point cloud data in various applications, such as autonomous vehicles, robotics, and virtual reality, has brought about significant advancements in object recognition and scene understanding. However, this progress is accompanied by new security challenges, particularly in the form of backdoor attacks. These attacks involve inserting malicious information into the training data of machine learning models, potentially compromising the model's behavior. In this paper, we propose CloudFort, a novel defense mechanism designed to enhance the robustness of 3D point cloud classifiers against backdoor attacks. CloudFort leverages spatial partitioning and ensemble prediction techniques to effectively mitigate the impact of backdoor triggers while preserving the model's performance on clean data. We evaluate the effectiveness of CloudFort through extensive experiments, demonstrating its strong resilience against the Point Cloud Backdoor Attack (PCBA). Our results show that CloudFort significantly enhances the security of 3D point cloud classification models without compromising their accuracy on benign samples. Furthermore, we explore the limitations of CloudFort and discuss potential avenues for future research in the field of 3D point cloud security. The proposed defense mechanism represents a significant step towards ensuring the trustworthiness and reliability of point-cloud-based systems in real-world applications.
Large Vision Language Models (VLMs), such as CLIP, have significantly contributed to various computer vision tasks, including object recognition and object detection. Their open vocabulary feature enhances their value. However, their black-box nature and lack of explainability in predictions make them less trustworthy in critical domains. Recently, some work has been done to force VLMs to provide reasonable rationales for object recognition, but this often comes at the expense of classification accuracy. In this paper, we first propose a mathematical definition of explainability in the object recognition task based on the joint probability distribution of categories and rationales, then leverage this definition to fine-tune CLIP in an explainable manner. Through evaluations of different datasets, our method demonstrates state-of-the-art performance in explainable classification. Notably, it excels in zero-shot settings, showcasing its adaptability. This advancement improves explainable object recognition, enhancing trust across diverse applications. The code will be made available online upon publication.
Achieving rotation invariance in deep neural networks without relying on data has always been a hot research topic. Intrinsic rotation invariance can enhance the model's feature representation capability, enabling better performance in tasks such as multi-orientation object recognition and detection. Based on various types of non-learnable operators, including gradient, sort, local binary pattern, maximum, etc., this paper designs a set of new convolution operations that are natually invariant to arbitrary rotations. Unlike most previous studies, these rotation-invariant convolutions (RIConvs) have the same number of learnable parameters and a similar computational process as conventional convolution operations, allowing them to be interchangeable. Using the MNIST-Rot dataset, we first verify the invariance of these RIConvs under various rotation angles and compare their performance with previous rotation-invariant convolutional neural networks (RI-CNNs). Two types of RIConvs based on gradient operators achieve state-of-the-art results. Subsequently, we combine RIConvs with different types and depths of classic CNN backbones. Using the OuTex_00012, MTARSI, and NWPU-RESISC-45 datasets, we test their performance on texture recognition, aircraft type recognition, and remote sensing image classification tasks. The results show that RIConvs significantly improve the accuracy of these CNN backbones, especially when the training data is limited. Furthermore, we find that even with data augmentation, RIConvs can further enhance model performance.
Vision sensors are versatile and can capture a wide range of visual cues, such as color, texture, shape, and depth. This versatility, along with the relatively inexpensive availability of machine vision cameras, played an important role in adopting vision-based environment perception systems in autonomous vehicles (AVs). However, vision-based perception systems can be easily affected by glare in the presence of a bright source of light, such as the sun or the headlights of the oncoming vehicle at night or simply by light reflecting off snow or ice-covered surfaces; scenarios encountered frequently during driving. In this paper, we investigate various glare reduction techniques, including the proposed saturated pixel-aware glare reduction technique for improved performance of the computer vision (CV) tasks employed by the perception layer of AVs. We evaluate these glare reduction methods based on various performance metrics of the CV algorithms used by the perception layer. Specifically, we considered object detection, object recognition, object tracking, depth estimation, and lane detection which are crucial for autonomous driving. The experimental findings validate the efficacy of the proposed glare reduction approach, showcasing enhanced performance across diverse perception tasks and remarkable resilience against varying levels of glare.
Although Multimodal Large Language Models (MLLMs) have demonstrated promising versatile capabilities, their performance is still inferior to specialized models on downstream tasks, which makes adaptation necessary to enhance their utility. However, fine-tuning methods require independent training for every model, leading to huge computation and memory overheads. In this paper, we propose a novel setting where we aim to improve the performance of diverse MLLMs with a group of shared parameters optimized for a downstream task. To achieve this, we propose Transferable Visual Prompting (TVP), a simple and effective approach to generate visual prompts that can transfer to different models and improve their performance on downstream tasks after trained on only one model. We introduce two strategies to address the issue of cross-model feature corruption of existing visual prompting methods and enhance the transferability of the learned prompts, including 1) Feature Consistency Alignment: which imposes constraints to the prompted feature changes to maintain task-agnostic knowledge; 2) Task Semantics Enrichment: which encourages the prompted images to contain richer task-specific semantics with language guidance. We validate the effectiveness of TVP through extensive experiments with 6 modern MLLMs on a wide variety of tasks ranging from object recognition and counting to multimodal reasoning and hallucination correction.
Object recognition, commonly performed by a camera, is a fundamental requirement for robots to complete complex tasks. Some tasks require recognizing objects far from the robot's camera. A challenging example is Ultra-Range Gesture Recognition (URGR) in human-robot interaction where the user exhibits directive gestures at a distance of up to 25~m from the robot. However, training a model to recognize hardly visible objects located in ultra-range requires an exhaustive collection of a significant amount of labeled samples. The generation of synthetic training datasets is a recent solution to the lack of real-world data, while unable to properly replicate the realistic visual characteristics of distant objects in images. In this letter, we propose the Diffusion in Ultra-Range (DUR) framework based on a Diffusion model to generate labeled images of distant objects in various scenes. The DUR generator receives a desired distance and class (e.g., gesture) and outputs a corresponding synthetic image. We apply DUR to train a URGR model with directive gestures in which fine details of the gesturing hand are challenging to distinguish. DUR is compared to other types of generative models showcasing superiority both in fidelity and in recognition success rate when training a URGR model. More importantly, training a DUR model on a limited amount of real data and then using it to generate synthetic data for training a URGR model outperforms directly training the URGR model on real data. The synthetic-based URGR model is also demonstrated in gesture-based direction of a ground robot.
Contrastive vision-language models (VLMs), like CLIP, have gained popularity for their versatile applicability to various downstream tasks. Despite their successes in some tasks, like zero-shot object recognition, they perform surprisingly poor on other tasks, like attribute recognition. Previous work has attributed these challenges to the modality gap, a separation of image and text in the shared representation space, and to a bias towards objects over other factors, such as attributes. In this analysis paper, we investigate both phenomena thoroughly. We evaluated off-the-shelf VLMs and while the gap's influence on performance is typically overshadowed by other factors, we find indications that closing the gap indeed leads to improvements. Moreover, we find that, contrary to intuition, only few embedding dimensions drive the gap and that the embedding spaces are differently organized. To allow for a clean study of object bias, we introduce a definition and a corresponding measure of it. Equipped with this tool, we find that object bias does not lead to worse performance on other concepts, such as attributes per se. However, why do both phenomena, modality gap and object bias, emerge in the first place? To answer this fundamental question and uncover some of the inner workings of contrastive VLMs, we conducted experiments that allowed us to control the amount of shared information between the modalities. These experiments revealed that the driving factor behind both the modality gap and the object bias, is an information imbalance between images and captions, and unveiled an intriguing connection between the modality gap and entropy of the logits.
We add one more invariance - the state invariance - to the more commonly used other invariances for learning object representations for recognition and retrieval. By state invariance, we mean robust with respect to changes in the structural form of the objects, such as when an umbrella is folded, or when an item of clothing is tossed on the floor. In this work, we present a novel dataset, ObjectsWithStateChange, which captures state and pose variations in the object images recorded from arbitrary viewpoints. We believe that this dataset will facilitate research in fine-grained object recognition and retrieval of 3D objects that are capable of state changes. The goal of such research would be to train models capable of learning discriminative object embeddings that remain invariant to state changes while also staying invariant to transformations induced by changes in viewpoint, pose, illumination, etc. A major challenge in this regard is that instances of different objects (both within and across different categories) under various state changes may share similar visual characteristics and therefore may be close to one another in the learned embedding space, which would make it more difficult to discriminate between them. To address this, we propose a curriculum learning strategy that progressively selects object pairs with smaller inter-object distances in the learned embedding space during the training phase. This approach gradually samples harder-to-distinguish examples of visually similar objects, both within and across different categories. Our ablation related to the role played by curriculum learning indicates an improvement in object recognition accuracy of 7.9% and retrieval mAP of 9.2% over the state-of-the-art on our new dataset, as well as three other challenging multi-view datasets such as ModelNet40, ObjectPI, and FG3D.
In the era of modern technology, object detection using the Gray Level Co-occurrence Matrix (GLCM) extraction method plays a crucial role in object recognition processes. It finds applications in real-time scenarios such as security surveillance and autonomous vehicle navigation, among others. Computational efficiency becomes a critical factor in achieving real-time object detection. Hence, there is a need for a detection model with low complexity and satisfactory accuracy. This research aims to enhance computational efficiency by selecting appropriate features within the GLCM framework. Two classification models, namely K-Nearest Neighbours (K-NN) and Support Vector Machine (SVM), were employed, with the results indicating that K-Nearest Neighbours (K-NN) outperforms SVM in terms of computational complexity. Specifically, K-NN, when utilizing a combination of Correlation, Energy, and Homogeneity features, achieves a 100% accuracy rate with low complexity. Moreover, when using a combination of Energy and Homogeneity features, K-NN attains an almost perfect accuracy level of 99.9889%, while maintaining low complexity. On the other hand, despite SVM achieving 100% accuracy in certain feature combinations, its high or very high complexity can pose challenges, particularly in real-time applications. Therefore, based on the trade-off between accuracy and complexity, the K-NN model with a combination of Correlation, Energy, and Homogeneity features emerges as a more suitable choice for real-time applications that demand high accuracy and low complexity. This research provides valuable insights for optimizing object detection in various applications requiring both high accuracy and rapid responsiveness.
Multiple benchmarks have been developed to assess the alignment between deep neural networks (DNNs) and human vision. In almost all cases these benchmarks are observational in the sense they are composed of behavioural and brain responses to naturalistic images that have not been manipulated to test hypotheses regarding how DNNs or humans perceive and identify objects. Here we introduce the toolbox MindSet: Vision, consisting of a collection of image datasets and related scripts designed to test DNNs on 30 psychological findings. In all experimental conditions, the stimuli are systematically manipulated to test specific hypotheses regarding human visual perception and object recognition. In addition to providing pre-generated datasets of images, we provide code to regenerate these datasets, offering many configurable parameters which greatly extend the dataset versatility for different research contexts, and code to facilitate the testing of DNNs on these image datasets using three different methods (similarity judgments, out-of-distribution classification, and decoder method), accessible at https://github.com/MindSetVision/mindset-vision. We test ResNet-152 on each of these methods as an example of how the toolbox can be used.
Modern applications increasingly demand flexible computer vision models that adapt to novel concepts not encountered during training. This necessity is pivotal in emerging domains like extended reality, robotics, and autonomous driving, which require the ability to respond to open-world stimuli. A key ingredient is the ability to identify objects based on free-form textual queries defined at inference time - a task known as open-vocabulary object detection. Multimodal backbones like CLIP are the main enabling technology for current open-world perception solutions. Despite performing well on generic queries, recent studies highlighted limitations on the fine-grained recognition capabilities in open-vocabulary settings - i.e., for distinguishing subtle object features like color, shape, and material. In this paper, we perform a detailed examination of these open-vocabulary object recognition limitations to find the root cause. We evaluate the performance of CLIP, the most commonly used vision-language backbone, against a fine-grained object-matching benchmark, revealing interesting analogies between the limitations of open-vocabulary object detectors and their backbones. Experiments suggest that the lack of fine-grained understanding is caused by the poor separability of object characteristics in the CLIP latent space. Therefore, we try to understand whether fine-grained knowledge is present in CLIP embeddings but not exploited at inference time due, for example, to the unsuitability of the cosine similarity matching function, which may discard important object characteristics. Our preliminary experiments show that simple CLIP latent-space re-projections help separate fine-grained concepts, paving the way towards the development of backbones inherently able to process fine-grained details. The code for reproducing these experiments is available at https://github.com/lorebianchi98/FG-CLIP.
This paper presents a novel universal perturbation method for generating robust multi-view adversarial examples in 3D object recognition. Unlike conventional attacks limited to single views, our approach operates on multiple 2D images, offering a practical and scalable solution for enhancing model scalability and robustness. This generalizable method bridges the gap between 2D perturbations and 3D-like attack capabilities, making it suitable for real-world applications. Existing adversarial attacks may become ineffective when images undergo transformations like changes in lighting, camera position, or natural deformations. We address this challenge by crafting a single universal noise perturbation applicable to various object views. Experiments on diverse rendered 3D objects demonstrate the effectiveness of our approach. The universal perturbation successfully identified a single adversarial noise for each given set of 3D object renders from multiple poses and viewpoints. Compared to single-view attacks, our universal attacks lower classification confidence across multiple viewing angles, especially at low noise levels. A sample implementation is made available at https://github.com/memoatwit/UniversalPerturbation.
Learning generalizable visual representations from Internet data has yielded promising results for robotics. Yet, prevailing approaches focus on pre-training 2D representations, being sub-optimal to deal with occlusions and accurately localize objects in complex 3D scenes. Meanwhile, 3D representation learning has been limited to single-object understanding. To address these limitations, we introduce a novel 3D pre-training framework for robotics named SUGAR that captures semantic, geometric and affordance properties of objects through 3D point clouds. We underscore the importance of cluttered scenes in 3D representation learning, and automatically construct a multi-object dataset benefiting from cost-free supervision in simulation. SUGAR employs a versatile transformer-based model to jointly address five pre-training tasks, namely cross-modal knowledge distillation for semantic learning, masked point modeling to understand geometry structures, grasping pose synthesis for object affordance, 3D instance segmentation and referring expression grounding to analyze cluttered scenes. We evaluate our learned representation on three robotic-related tasks, namely, zero-shot 3D object recognition, referring expression grounding, and language-driven robotic manipulation. Experimental results show that SUGAR's 3D representation outperforms state-of-the-art 2D and 3D representations.
Nowadays, users demand for increased personalization of vision systems to localize and identify personal instances of objects (e.g., my dog rather than dog) from a few-shot dataset only. Despite outstanding results of deep networks on classical label-abundant benchmarks (e.g., those of the latest YOLOv8 model for standard object detection), they struggle to maintain within-class variability to represent different instances rather than object categories only. We construct an Object-conditioned Bag of Instances (OBoI) based on multi-order statistics of extracted features, where generic object detection models are extended to search and identify personal instances from the OBoI's metric space, without need for backpropagation. By relying on multi-order statistics, OBoI achieves consistent superior accuracy in distinguishing different instances. In the results, we achieve 77.1% personal object recognition accuracy in case of 18 personal instances, showing about 12% relative gain over the state of the art.
Although mobile robots have on-board sensors to perform navigation, their efficiency in completing paths can be enhanced by planning to avoid human interaction. Infrastructure cameras can capture human activity continuously for the purpose of compiling activity analytics to choose efficient times and routes. We describe a cascade temporal filtering method to efficiently extract short- and long-term activity in two time dimensions, isochronal and chronological, for use in global path planning and local navigation respectively. The temporal filter has application either independently, or, if object recognition is also required, it can be used as a pre-filter to perform activity-gating of the more computationally expensive neural network processing. For a testbed 32-camera network, we show how this hybrid approach can achieve over 8 times improvement in frames per second throughput and 6.5 times reduction of system power use. We also show how the cost map of static objects in the ROS robot software development framework is augmented with dynamic regions determined from the temporal filter.
Tactile sensing is vital for human dexterous manipulation, however, it has not been widely used in robotics. Compact, low-cost sensing platforms can facilitate a change, but unlike their popular optical counterparts, they are difficult to deploy in high-fidelity tasks due to their low signal dimensionality and lack of a simulation model. To overcome these challenges, we introduce PseudoTouch which links high-dimensional structural information to low-dimensional sensor signals. It does so by learning a low-dimensional visual-tactile embedding, wherein we encode a depth patch from which we decode the tactile signal. We collect and train PseudoTouch on a dataset comprising aligned tactile and visual data pairs obtained through random touching of eight basic geometric shapes. We demonstrate the utility of our trained PseudoTouch model in two downstream tasks: object recognition and grasp stability prediction. In the object recognition task, we evaluate the learned embedding's performance on a set of five basic geometric shapes and five household objects. Using PseudoTouch, we achieve an object recognition accuracy 84% after just ten touches, surpassing a proprioception baseline. For the grasp stability task, we use ACRONYM labels to train and evaluate a grasp success predictor using PseudoTouch's predictions derived from virtual depth information. Our approach yields a 32% absolute improvement in accuracy compared to the baseline relying on partial point cloud data. We make the data, code, and trained models publicly available at https://pseudotouch.cs.uni-freiburg.de.
Convolutional Neural Networks (CNNs) and Transformers have achieved remarkable success in computer vision tasks. However, their deep architectures often lead to high computational redundancy, making them less suitable for resource-constrained environments, such as edge devices. This paper introduces ParFormer, a novel vision transformer that addresses this challenge by incorporating a Parallel Mixer and a Sparse Channel Attention Patch Embedding (SCAPE). By combining convolutional and attention mechanisms, ParFormer improves feature extraction. This makes spatial feature extraction more efficient and cuts down on unnecessary computation. The SCAPE module further reduces computational redundancy while preserving essential feature information during down-sampling. Experimental results on the ImageNet-1K dataset show that ParFormer-T achieves 78.9\% Top-1 accuracy with a high throughput on a GPU that outperforms other small models with 2.56$\times$ higher throughput than MobileViT-S, 0.24\% faster than FasterNet-T2, and 1.79$\times$ higher than EdgeNeXt-S. For edge device deployment, ParFormer-T excels with a throughput of 278.1 images/sec, which is 1.38 $\times$ higher than EdgeNeXt-S and 2.36$\times$ higher than MobileViT-S, making it highly suitable for real-time applications in resource-constrained settings. The larger variant, ParFormer-L, reaches 83.5\% Top-1 accuracy, offering a balanced trade-off between accuracy and efficiency, surpassing many state-of-the-art models. In COCO object detection, ParFormer-M achieves 40.7 AP for object detection and 37.6 AP for instance segmentation, surpassing models like ResNet-50, PVT-S and PoolFormer-S24 with significantly higher efficiency. These results validate ParFormer as a highly efficient and scalable model for both high-performance and resource-constrained scenarios, making it an ideal solution for edge-based AI applications.
Recent model inversion attack algorithms permit adversaries to reconstruct a neural network's private and potentially sensitive training data by repeatedly querying the network. In this work, we develop a novel network architecture that leverages sparse-coding layers to obtain superior robustness to this class of attacks. Three decades of computer science research has studied sparse coding in the context of image denoising, object recognition, and adversarial misclassification settings, but to the best of our knowledge, its connection to state-of-the-art privacy vulnerabilities remains unstudied. In this work, we hypothesize that sparse coding architectures suggest an advantageous means to defend against model inversion attacks because they allow us to control the amount of irrelevant private information encoded by a network in a manner that is known to have little effect on classification accuracy. Specifically, compared to networks trained with a variety of state-of-the-art defenses, our sparse-coding architectures maintain comparable or higher classification accuracy while degrading state-of-the-art training data reconstructions by factors of 1.1 to 18.3 across a variety of reconstruction quality metrics (PSNR, SSIM, FID). This performance advantage holds across 5 datasets ranging from CelebA faces to medical images and CIFAR-10, and across various state-of-the-art SGD-based and GAN-based inversion attacks, including Plug-&-Play attacks. We provide a cluster-ready PyTorch codebase to promote research and standardize defense evaluations.
In this paper, we make the first attempt at achieving the cross-modal (i.e., image-to-events) adaptation for event-based object recognition without accessing any labeled source image data owning to privacy and commercial issues. Tackling this novel problem is non-trivial due to the novelty of event cameras and the distinct modality gap between images and events. In particular, as only the source model is available, a hurdle is how to extract the knowledge from the source model by only using the unlabeled target event data while achieving knowledge transfer. To this end, we propose a novel framework, dubbed EventDance for this unsupervised source-free cross-modal adaptation problem. Importantly, inspired by event-to-video reconstruction methods, we propose a reconstruction-based modality bridging (RMB) module, which reconstructs intensity frames from events in a self-supervised manner. This makes it possible to build up the surrogate images to extract the knowledge (i.e., labels) from the source model. We then propose a multi-representation knowledge adaptation (MKA) module that transfers the knowledge to target models learning events with multiple representation types for fully exploring the spatiotemporal information of events. The two modules connecting the source and target models are mutually updated so as to achieve the best performance. Experiments on three benchmark datasets with two adaption settings show that EventDance is on par with prior methods utilizing the source data.
Taking advantage of multi-view aggregation presents a promising solution to tackle challenges such as occlusion and missed detection in multi-object tracking and detection. Recent advancements in multi-view detection and 3D object recognition have significantly improved performance by strategically projecting all views onto the ground plane and conducting detection analysis from a Bird's Eye View. In this paper, we compare modern lifting methods, both parameter-free and parameterized, to multi-view aggregation. Additionally, we present an architecture that aggregates the features of multiple times steps to learn robust detection and combines appearance- and motion-based cues for tracking. Most current tracking approaches either focus on pedestrians or vehicles. In our work, we combine both branches and add new challenges to multi-view detection with cross-scene setups. Our method generalizes to three public datasets across two domains: (1) pedestrian: Wildtrack and MultiviewX, and (2) roadside perception: Synthehicle, achieving state-of-the-art performance in detection and tracking. https://github.com/tteepe/TrackTacular