Light Detection and Ranging (LiDAR) is an essential sensor technology for autonomous driving as it can capture high-resolution 3D data. As 3D object detection systems (OD) can interpret such point cloud data, they play a key role in the driving decisions of autonomous vehicles. Consequently, such 3D OD must be robust against all types of perturbations and must therefore be extensively tested. One approach is the use of adversarial examples, which are small, sometimes sophisticated perturbations in the input data that change, i.e., falsify, the prediction of the OD. These perturbations are carefully designed based on the weaknesses of the OD. The robustness of the OD cannot be quantified with adversarial examples in general, because if the OD is vulnerable to a given attack, it is unclear whether this is due to the robustness of the OD or whether the attack algorithm produces particularly strong adversarial examples. The contribution of this work is Hi-ALPS -- Hierarchical Adversarial-example-based LiDAR Perturbation Level System, where higher robustness of the OD is required to withstand the perturbations as the perturbation levels increase. In doing so, the Hi-ALPS levels successively implement a heuristic followed by established adversarial example approaches. In a series of comprehensive experiments using Hi-ALPS, we quantify the robustness of six state-of-the-art 3D OD under different types of perturbations. The results of the experiments show that none of the OD is robust against all Hi-ALPS levels; an important factor for the ranking is that human observers can still correctly recognize the perturbed objects, as the respective perturbations are small. To increase the robustness of the OD, we discuss the applicability of state-of-the-art countermeasures. In addition, we derive further suggestions for countermeasures based on our experimental results.
We introduce R2LDM, an innovative approach for generating dense and accurate 4D radar point clouds, guided by corresponding LiDAR point clouds. Instead of utilizing range images or bird's eye view (BEV) images, we represent both LiDAR and 4D radar point clouds using voxel features, which more effectively capture 3D shape information. Subsequently, we propose the Latent Voxel Diffusion Model (LVDM), which performs the diffusion process in the latent space. Additionally, a novel Latent Point Cloud Reconstruction (LPCR) module is utilized to reconstruct point clouds from high-dimensional latent voxel features. As a result, R2LDM effectively generates LiDAR-like point clouds from paired raw radar data. We evaluate our approach on two different datasets, and the experimental results demonstrate that our model achieves 6- to 10-fold densification of radar point clouds, outperforming state-of-the-art baselines in 4D radar point cloud super-resolution. Furthermore, the enhanced radar point clouds generated by our method significantly improve downstream tasks, achieving up to 31.7% improvement in point cloud registration recall rate and 24.9% improvement in object detection accuracy.
Open-vocabulary object detection (OvOD) is set to revolutionize security screening by enabling systems to recognize any item in X-ray scans. However, developing effective OvOD models for X-ray imaging presents unique challenges due to data scarcity and the modality gap that prevents direct adoption of RGB-based solutions. To overcome these limitations, we propose RAXO, a training-free framework that repurposes off-the-shelf RGB OvOD detectors for robust X-ray detection. RAXO builds high-quality X-ray class descriptors using a dual-source retrieval strategy. It gathers relevant RGB images from the web and enriches them via a novel X-ray material transfer mechanism, eliminating the need for labeled databases. These visual descriptors replace text-based classification in OvOD, leveraging intra-modal feature distances for robust detection. Extensive experiments demonstrate that RAXO consistently improves OvOD performance, providing an average mAP increase of up to 17.0 points over base detectors. To further support research in this emerging field, we also introduce DET-COMPASS, a new benchmark featuring bounding box annotations for over 300 object categories, enabling large-scale evaluation of OvOD in X-ray. Code and dataset available at: https://github.com/PAGF188/RAXO.
Video Camouflaged Object Detection (VCOD) aims to segment objects whose appearances closely resemble their surroundings, posing a challenging and emerging task. Existing vision models often struggle in such scenarios due to the indistinguishable appearance of camouflaged objects and the insufficient exploitation of dynamic information in videos. To address these challenges, we propose an end-to-end VCOD framework inspired by human memory-recognition, which leverages historical video information by integrating memory reference frames for camouflaged sequence processing. Specifically, we design a dual-purpose decoder that simultaneously generates predicted masks and scores, enabling reference frame selection based on scores while introducing auxiliary supervision to enhance feature extraction.Furthermore, this study introduces a novel reference-guided multilevel asymmetric attention mechanism, effectively integrating long-term reference information with short-term motion cues for comprehensive feature extraction. By combining these modules, we develop the Scoring, Remember, and Reference (SRR) framework, which efficiently extracts information to locate targets and employs memory guidance to improve subsequent processing. With its optimized module design and effective utilization of video data, our model achieves significant performance improvements, surpassing existing approaches by 10% on benchmark datasets while requiring fewer parameters (54M) and only a single pass through the video. The code will be made publicly available.
Our key innovation lies in bridging the semantic gap between object detection and event understanding without requiring expensive task-specific training. The proposed plug-and-play framework interfaces with any open-vocabulary detector while extending their inherent capabilities across architectures. At its core, our approach combines (i) a symbolic regression mechanism exploring relationship patterns among detected entities and (ii) a LLM-guided strategically guiding the search toward meaningful expressions. These discovered symbolic rules transform low-level visual perception into interpretable event understanding, providing a transparent reasoning path from objects to events with strong transferability across domains.We compared our training-free framework against specialized event recognition systems across diverse application domains. Experiments demonstrate that our framework enhances multiple object detector architectures to recognize complex events such as illegal fishing activities (75% AUROC, +8.36% improvement), construction safety violations (+15.77%), and abnormal crowd behaviors (+23.16%). The code will be released soon.
Semi-supervised object detection (SSOD) based on pseudo-labeling significantly reduces dependence on large labeled datasets by effectively leveraging both labeled and unlabeled data. However, real-world applications of SSOD often face critical challenges, including class imbalance, label noise, and labeling errors. We present an in-depth analysis of SSOD under real-world conditions, uncovering causes of suboptimal pseudo-labeling and key trade-offs between label quality and quantity. Based on our findings, we propose four building blocks that can be seamlessly integrated into an SSOD framework. Rare Class Collage (RCC): a data augmentation method that enhances the representation of rare classes by creating collages of rare objects. Rare Class Focus (RCF): a stratified batch sampling strategy that ensures a more balanced representation of all classes during training. Ground Truth Label Correction (GLC): a label refinement method that identifies and corrects false, missing, and noisy ground truth labels by leveraging the consistency of teacher model predictions. Pseudo-Label Selection (PLS): a selection method for removing low-quality pseudo-labeled images, guided by a novel metric estimating the missing detection rate while accounting for class rarity. We validate our methods through comprehensive experiments on autonomous driving datasets, resulting in up to 6% increase in SSOD performance. Overall, our investigation and novel, data-centric, and broadly applicable building blocks enable robust and effective SSOD in complex, real-world scenarios. Code is available at https://mos-ks.github.io/publications.
UAV has been widely used in various fields. However, most of the existing object detectors used in drones are not end-to-end and require the design of various complex components and careful fine-tuning. Most of the existing end-to-end object detectors are designed for natural scenes. It is not ideal to apply them directly to UAV images. In order to solve the above challenges, we design an local-global information interaction DETR for UAVs, namely LGI-DETR. Cross-layer bidirectional low-level and high-level feature information enhancement, this fusion method is effective especially in the field of small objection detection. At the initial stage of encoder, we propose a local spatial enhancement module (LSE), which enhances the low-level rich local spatial information into the high-level feature, and reduces the loss of local information in the transmission process of high-level information. At the final stage of the encoder, we propose a novel global information injection module (GII) designed to integrate rich high-level global semantic representations with low-level feature maps. This hierarchical fusion mechanism effectively addresses the inherent limitations of local receptive fields by propagating contextual information across the feature hierarchy. Experimental results on two challenging UAV image object detection benchmarks, VisDrone2019 and UAVDT, show that our proposed model outperforms the SOTA model. Compared to the baseline model, AP and AP50 improved by 1.9% and 2.4%, respectively.
While Dynamic Convolution (DY-Conv) has shown promising performance by enabling adaptive weight selection through multiple parallel weights combined with an attention mechanism, the frequency response of these weights tends to exhibit high similarity, resulting in high parameter costs but limited adaptability. In this work, we introduce Frequency Dynamic Convolution (FDConv), a novel approach that mitigates these limitations by learning a fixed parameter budget in the Fourier domain. FDConv divides this budget into frequency-based groups with disjoint Fourier indices, enabling the construction of frequency-diverse weights without increasing the parameter cost. To further enhance adaptability, we propose Kernel Spatial Modulation (KSM) and Frequency Band Modulation (FBM). KSM dynamically adjusts the frequency response of each filter at the spatial level, while FBM decomposes weights into distinct frequency bands in the frequency domain and modulates them dynamically based on local content. Extensive experiments on object detection, segmentation, and classification validate the effectiveness of FDConv. We demonstrate that when applied to ResNet-50, FDConv achieves superior performance with a modest increase of +3.6M parameters, outperforming previous methods that require substantial increases in parameter budgets (e.g., CondConv +90M, KW +76.5M). Moreover, FDConv seamlessly integrates into a variety of architectures, including ConvNeXt, Swin-Transformer, offering a flexible and efficient solution for modern vision tasks. The code is made publicly available at https://github.com/Linwei-Chen/FDConv.
With the exponential growth of data, traditional object detection methods are increasingly struggling to handle vast vocabulary object detection tasks effectively. We analyze two key limitations of classification-based detectors: positive gradient dilution, where rare positive categories receive insufficient learning signals, and hard negative gradient dilution, where discriminative gradients are overwhelmed by numerous easy negatives. To address these challenges, we propose CQ-DINO, a category query-based object detection framework that reformulates classification as a contrastive task between object queries and learnable category queries. Our method introduces image-guided query selection, which reduces the negative space by adaptively retrieving top-K relevant categories per image via cross-attention, thereby rebalancing gradient distributions and facilitating implicit hard example mining. Furthermore, CQ-DINO flexibly integrates explicit hierarchical category relationships in structured datasets (e.g., V3Det) or learns implicit category correlations via self-attention in generic datasets (e.g., COCO). Experiments demonstrate that CQ-DINO achieves superior performance on the challenging V3Det benchmark (surpassing previous methods by 2.1% AP) while maintaining competitiveness in COCO. Our work provides a scalable solution for real-world detection systems requiring wide category coverage. The code is publicly at https://github.com/RedAIGC/CQ-DINO.
Restoration and enhancement are essential for improving the quality of videos captured under atmospheric turbulence conditions, aiding visualization, object detection, classification, and tracking in surveillance systems. In this paper, we introduce a novel Mamba-based method, the 3D Mamba-Based Atmospheric Turbulence Removal (MAMAT), which employs a dual-module strategy to mitigate these distortions. The first module utilizes deformable 3D convolutions for non-rigid registration to minimize spatial shifts, while the second module enhances contrast and detail. Leveraging the advanced capabilities of the 3D Mamba architecture, experimental results demonstrate that MAMAT outperforms state-of-the-art learning-based methods, achieving up to a 3\% improvement in visual quality and a 15\% boost in object detection. It not only enhances visualization but also significantly improves object detection accuracy, bridging the gap between visual restoration and the effectiveness of surveillance applications.
Contrastive learning in self-supervised settings primarily focuses on pre-training encoders, while decoders are typically introduced and trained separately for downstream dense prediction tasks. This conventional approach, however, overlooks the potential benefits of jointly pre-training both the encoder and decoder. In this paper, we propose DeCon: a framework-agnostic adaptation to convert an encoder-only self-supervised learning (SSL) contrastive approach to an efficient encoder-decoder framework that can be pre-trained in a contrastive manner. We first update the existing architecture to accommodate a decoder and its respective contrastive loss. We then introduce a weighted encoder-decoder contrastive loss with non-competing objectives that facilitates the joint encoder-decoder architecture pre-training. We adapt two established contrastive SSL frameworks tailored for dense prediction tasks, achieve new state-of-the-art results in COCO object detection and instance segmentation, and match state-of-the-art performance on Pascal VOC semantic segmentation. We show that our approach allows for pre-training a decoder and enhances the representation power of the encoder and its performance in dense prediction tasks. This benefit holds across heterogeneous decoder architectures between pre-training and fine-tuning and persists in out-of-domain, limited-data scenarios.
Event-based vision revolutionizes traditional image sensing by capturing asynchronous intensity variations rather than static frames, enabling ultrafast temporal resolution, sparse data encoding, and enhanced motion perception. While this paradigm offers significant advantages, conventional event-based datasets impose a fixed thresholding constraint to determine pixel activations, severely limiting adaptability to real-world environmental fluctuations. Lower thresholds retain finer details but introduce pervasive noise, whereas higher thresholds suppress extraneous activations at the expense of crucial object information. To mitigate these constraints, we introduce the Event-Based Crossing Dataset (EBCD), a comprehensive dataset tailored for pedestrian and vehicle detection in dynamic outdoor environments, incorporating a multi-thresholding framework to refine event representations. By capturing event-based images at ten distinct threshold levels (4, 8, 12, 16, 20, 30, 40, 50, 60, and 75), this dataset facilitates an extensive assessment of object detection performance under varying conditions of sparsity and noise suppression. We benchmark state-of-the-art detection architectures-including YOLOv4, YOLOv7, EfficientDet-b0, MobileNet-v1, and Histogram of Oriented Gradients (HOG)-to experiment upon the nuanced impact of threshold selection on detection performance. By offering a systematic approach to threshold variation, we foresee that EBCD fosters a more adaptive evaluation of event-based object detection, aligning diverse neuromorphic vision with real-world scene dynamics. We present the dataset as publicly available to propel further advancements in low-latency, high-fidelity neuromorphic imaging: https://ieee-dataport.org/documents/event-based-crossing-dataset-ebcd
We introduce AnytimeYOLO, a family of variants of the YOLO architecture that enables anytime object detection. Our AnytimeYOLO networks allow for interruptible inference, i.e., they provide a prediction at any point in time, a property desirable for safety-critical real-time applications. We present structured explorations to modify the YOLO architecture, enabling early termination to obtain intermediate results. We focus on providing fine-grained control through high granularity of available termination points. First, we formalize Anytime Models as a special class of prediction models that offer anytime predictions. Then, we discuss a novel transposed variant of the YOLO architecture, that changes the architecture to enable better early predictions and greater freedom for the order of processing stages. Finally, we propose two optimization algorithms that, given an anytime model, can be used to determine the optimal exit execution order and the optimal subset of early-exits to select for deployment in low-resource environments. We evaluate the anytime performance and trade-offs of design choices, proposing a new anytime quality metric for this purpose. In particular, we also discuss key challenges for anytime inference that currently make its deployment costly.
Computer-aided pathology detection algorithms for video-based imaging modalities must accurately interpret complex spatiotemporal information by integrating findings across multiple frames. Current state-of-the-art methods operate by classifying on video sub-volumes (tubelets), but they often lose global spatial context by focusing only on local regions within detection ROIs. Here we propose a lightweight framework for tubelet-based object detection and video classification that preserves both global spatial context and fine spatiotemporal features. To address the loss of global context, we embed tubelet location, size, and confidence as inputs to the classifier. Additionally, we use ROI-aligned feature maps from a pre-trained detection model, leveraging learned feature representations to increase the receptive field and reduce computational complexity. Our method is efficient, with the spatiotemporal tubelet classifier comprising only 0.4M parameters. We apply our approach to detect and classify lung consolidation and pleural effusion in ultrasound videos. Five-fold cross-validation on 14,804 videos from 828 patients shows our method outperforms previous tubelet-based approaches and is suited for real-time workflows.
The detection of blood disorders often hinges upon the quantification of specific blood cell types. Variations in cell counts may indicate the presence of pathological conditions. Thus, the significance of developing precise automatic systems for blood cell enumeration is underscored. The investigation focuses on a novel approach termed DE-ViT. This methodology is employed in a Few-Shot paradigm, wherein training relies on a limited number of images. Two distinct datasets are utilised for experimental purposes: the Raabin-WBC dataset for Leukocyte detection and a local dataset for Schistocyte identification. In addition to the DE-ViT model, two baseline models, Faster R-CNN 50 and Faster R-CNN X 101, are employed, with their outcomes being compared against those of the proposed model. While DE-ViT has demonstrated state-of-the-art performance on the COCO and LVIS datasets, both baseline models surpassed its performance on the Raabin-WBC dataset. Moreover, only Faster R-CNN X 101 yielded satisfactory results on the SC-IDB. The observed disparities in performance may possibly be attributed to domain shift phenomena.
The rapidly growing demand for on-chip edge intelligence on resource-constrained devices has motivated approaches to reduce energy and latency of deep learning models. Spiking neural networks (SNNs) have gained particular interest due to their promise to reduce energy consumption using event-based processing. We assert that while sigma-delta encoding in SNNs can take advantage of the temporal redundancy across video frames, they still involve a significant amount of redundant computations due to processing insignificant events. In this paper, we propose a region masking strategy that identifies regions of interest at the input of the SNN, thereby eliminating computation and data movement for events arising from unimportant regions. Our approach demonstrates that masking regions at the input not only significantly reduces the overall spiking activity of the network, but also provides significant improvement in throughput and latency. We apply region masking during video object detection on Loihi 2, demonstrating that masking approximately 60% of input regions can reduce energy-delay product by 1.65x over a baseline sigma-delta network, with a degradation in [email omitted] by 1.09%.
Deep Convolutional Neural Networks (CNNs) have significantly advanced deep learning, driving breakthroughs in computer vision, natural language processing, medical diagnosis, object detection, and speech recognition. Architectural innovations including 1D, 2D, and 3D convolutional models, dilated and grouped convolutions, depthwise separable convolutions, and attention mechanisms address domain-specific challenges and enhance feature representation and computational efficiency. Structural refinements such as spatial-channel exploitation, multi-path design, and feature-map enhancement contribute to robust hierarchical feature extraction and improved generalization, particularly through transfer learning. Efficient preprocessing strategies, including Fourier transforms, structured transforms, low-precision computation, and weight compression, optimize inference speed and facilitate deployment in resource-constrained environments. This survey presents a unified taxonomy that classifies CNN architectures based on spatial exploitation, multi-path structures, depth, width, dimensionality expansion, channel boosting, and attention mechanisms. It systematically reviews CNN applications in face recognition, pose estimation, action recognition, text classification, statistical language modeling, disease diagnosis, radiological analysis, cryptocurrency sentiment prediction, 1D data processing, video analysis, and speech recognition. In addition to consolidating architectural advancements, the review highlights emerging learning paradigms such as few-shot, zero-shot, weakly supervised, federated learning frameworks and future research directions include hybrid CNN-transformer models, vision-language integration, generative learning, etc. This review provides a comprehensive perspective on CNN's evolution from 2015 to 2025, outlining key innovations, challenges, and opportunities.
With an increasing demand for assistive technologies that promote the independence and mobility of visually impaired people, this study suggests an innovative real-time system that gives audio descriptions of a user's surroundings to improve situational awareness. The system acquires live video input and processes it with a quantized and fine-tuned Florence-2 big model, adjusted to 4-bit accuracy for efficient operation on low-power edge devices such as the NVIDIA Jetson Orin Nano. By transforming the video signal into frames with a 5-frame latency, the model provides rapid and contextually pertinent descriptions of objects, pedestrians, and barriers, together with their estimated distances. The system employs Parler TTS Mini, a lightweight and adaptable Text-to-Speech (TTS) solution, for efficient audio feedback. It accommodates 34 distinct speaker types and enables customization of speech tone, pace, and style to suit user requirements. This study examines the quantization and fine-tuning techniques utilized to modify the Florence-2 model for this application, illustrating how the integration of a compact model architecture with a versatile TTS component improves real-time performance and user experience. The proposed system is assessed based on its accuracy, efficiency, and usefulness, providing a viable option to aid vision-impaired users in navigating their surroundings securely and successfully.
Object detection models are vulnerable to backdoor attacks, where attackers poison a small subset of training samples by embedding a predefined trigger to manipulate prediction. Detecting poisoned samples (i.e., those containing triggers) at test time can prevent backdoor activation. However, unlike image classification tasks, the unique characteristics of object detection -- particularly its output of numerous objects -- pose fresh challenges for backdoor detection. The complex attack effects (e.g., "ghost" object emergence or "vanishing" object) further render current defenses fundamentally inadequate. To this end, we design TRAnsformation Consistency Evaluation (TRACE), a brand-new method for detecting poisoned samples at test time in object detection. Our journey begins with two intriguing observations: (1) poisoned samples exhibit significantly more consistent detection results than clean ones across varied backgrounds. (2) clean samples show higher detection consistency when introduced to different focal information. Based on these phenomena, TRACE applies foreground and background transformations to each test sample, then assesses transformation consistency by calculating the variance in objects confidences. TRACE achieves black-box, universal backdoor detection, with extensive experiments showing a 30% improvement in AUROC over state-of-the-art defenses and resistance to adaptive attacks.
Incremental object detection (IOD) aims to cultivate an object detector that can continuously localize and recognize novel classes while preserving its performance on previous classes. Existing methods achieve certain success by improving knowledge distillation and exemplar replay for transformer-based detection frameworks, but the intrinsic forgetting mechanisms remain underexplored. In this paper, we dive into the cause of forgetting and discover forgetting imbalance between localization and recognition in transformer-based IOD, which means that localization is less-forgetting and can generalize to future classes, whereas catastrophic forgetting occurs primarily on recognition. Based on these insights, we propose a Divide-and-Conquer Amnesia (DCA) strategy, which redesigns the transformer-based IOD into a localization-then-recognition process. DCA can well maintain and transfer the localization ability, leaving decoupled fragile recognition to be specially conquered. To reduce feature drift in recognition, we leverage semantic knowledge encoded in pre-trained language models to anchor class representations within a unified feature space across incremental tasks. This involves designing a duplex classifier fusion and embedding class semantic features into the recognition decoding process in the form of queries. Extensive experiments validate that our approach achieves state-of-the-art performance, especially for long-term incremental scenarios. For example, under the four-step setting on MS-COCO, our DCA strategy significantly improves the final AP by 6.9%.