PyTorchKR Papers

최신 논문

총 9,822편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2503.18785

LGI-DETR: Local-Global Interaction for UAV Object Detection

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.

arXiv:2503.18783공식 코드 · Papers with Code

Frequency Dynamic Convolution for Dense Image Prediction

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.

arXiv:2503.18430공식 코드 · Papers with Code

CQ-DINO: Mitigating Gradient Dilution via Category Queries for Vast Vocabulary Object Detection

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.

arXiv:2503.17700

MAMAT: 3D Mamba-Based Atmospheric Turbulence Removal and its Object Detection Capability

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.

arXiv:2503.17526

Should we pre-train a decoder in contrastive learning for dense prediction tasks?

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.

arXiv:2503.17499공식 코드 · Papers with Code

Event-Based Crossing Dataset (EBCD)

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

arXiv:2503.17497

You Only Look Once at Anytime (AnytimeYOLO): Analysis and Optimization of Early-Exits for Object-Detection

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.

arXiv:2503.17475

Spatiotemporal Learning with Context-aware Video Tubelets for Ultrasound Video Analysis

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.

arXiv:2503.17107

Exploring Few-Shot Object Detection on Blood Smear Images: A Case Study of Leukocytes and Schistocytes

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.

arXiv:2503.16775

Region Masking to Accelerate Video Processing on Neuromorphic Hardware

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%.

arXiv:2503.16546

A Comprehensive Survey on Architectural Advances in Deep CNNs: Challenges, Applications, and Emerging Research Directions

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.

arXiv:2503.16488

VocalEyes: Enhancing Environmental Perception for the Visually Impaired through Vision-Language Models and Distance-Aware Object Detection

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.

arXiv:2503.15295공식 코드 · Papers with Code

DCA: Dividing and Conquering Amnesia in Incremental Object Detection

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%.

arXiv:2503.15161공식 코드 · Papers with Code

UltraFlwr -- An Efficient Federated Medical and Surgical Object Detection Framework

Object detection shows promise for medical and surgical applications such as cell counting and tool tracking. However, its faces multiple real-world edge deployment challenges including limited high-quality annotated data, data sharing restrictions, and computational constraints. In this work, we introduce UltraFlwr, a framework for federated medical and surgical object detection. By leveraging Federated Learning (FL), UltraFlwr enables decentralized model training across multiple sites without sharing raw data. To further enhance UltraFlwr's efficiency, we propose YOLO-PA, a set of novel Partial Aggregation (PA) strategies specifically designed for YOLO models in FL. YOLO-PA significantly reduces communication overhead by up to 83% per round while maintaining performance comparable to Full Aggregation (FA) strategies. Our extensive experiments on BCCD and m2cai16-tool-locations datasets demonstrate that YOLO-PA not only provides better client models compared to client-wise centralized training and FA strategies, but also facilitates efficient training and deployment across resource-constrained edge devices. Further, we also establish one of the first benchmarks in federated medical and surgical object detection. This paper advances the feasibility of training and deploying detection models on the edge, making federated object detection more practical for time-critical and resource-constrained medical and surgical applications. UltraFlwr is publicly available at https://github.com/KCL-BMEIS/UltraFlwr.

arXiv:2503.16185

MapGlue: Multimodal Remote Sensing Image Matching

Multimodal remote sensing image (MRSI) matching is pivotal for cross-modal fusion, localization, and object detection, but it faces severe challenges due to geometric, radiometric, and viewpoint discrepancies across imaging modalities. Existing unimodal datasets lack scale and diversity, limiting deep learning solutions. This paper proposes MapGlue, a universal MRSI matching framework, and MapData, a large-scale multimodal dataset addressing these gaps. Our contributions are twofold. MapData, a globally diverse dataset spanning 233 sampling points, offers original images (7,000x5,000 to 20,000x15,000 pixels). After rigorous cleaning, it provides 121,781 aligned electronic map-visible image pairs (512x512 pixels) with hybrid manual-automated ground truth, addressing the scarcity of scalable multimodal benchmarks. MapGlue integrates semantic context with a dual graph-guided mechanism to extract cross-modal invariant features. This structure enables global-to-local interaction, enhancing descriptor robustness against modality-specific distortions. Extensive evaluations on MapData and five public datasets demonstrate MapGlue's superiority in matching accuracy under complex conditions, outperforming state-of-the-art methods. Notably, MapGlue generalizes effectively to unseen modalities without retraining, highlighting its adaptability. This work addresses longstanding challenges in MRSI matching by combining scalable dataset construction with a robust, semantics-driven framework. Furthermore, MapGlue shows strong generalization capabilities on other modality matching tasks for which it was not specifically trained. The dataset and code are available at https://github.com/PeihaoWu/MapGlue.

arXiv:2503.16125

Uncertainty Meets Diversity: A Comprehensive Active Learning Framework for Indoor 3D Object Detection

Active learning has emerged as a promising approach to reduce the substantial annotation burden in 3D object detection tasks, spurring several initiatives in outdoor environments. However, its application in indoor environments remains unexplored. Compared to outdoor 3D datasets, indoor datasets face significant challenges, including fewer training samples per class, a greater number of classes, more severe class imbalance, and more diverse scene types and intra-class variances. This paper presents the first study on active learning for indoor 3D object detection, where we propose a novel framework tailored for this task. Our method incorporates two key criteria - uncertainty and diversity - to actively select the most ambiguous and informative unlabeled samples for annotation. The uncertainty criterion accounts for both inaccurate detections and undetected objects, ensuring that the most ambiguous samples are prioritized. Meanwhile, the diversity criterion is formulated as a joint optimization problem that maximizes the diversity of both object class distributions and scene types, using a new Class-aware Adaptive Prototype (CAP) bank. The CAP bank dynamically allocates representative prototypes to each class, helping to capture varying intra-class diversity across different categories. We evaluate our method on SUN RGB-D and ScanNetV2, where it outperforms baselines by a significant margin, achieving over 85% of fully-supervised performance with just 10% of the annotation budget.

arXiv:2503.08144

Bring Remote Sensing Object Detect Into Nature Language Model: Using SFT Method

Recently, large language models (LLMs) and vision-language models (VLMs) have achieved significant success, demonstrating remarkable capabilities in understanding various images and videos, particularly in classification and detection tasks. However, due to the substantial differences between remote sensing images and conventional optical images, these models face considerable challenges in comprehension, especially in detection tasks. Directly prompting VLMs with detection instructions often leads to unsatisfactory results. To address this issue, this letter explores the application of VLMs for object detection in remote sensing images. Specifically, we constructed supervised fine-tuning (SFT) datasets using publicly available remote sensing object detection datasets, including SSDD, HRSID, and NWPU-VHR-10. In these new datasets, we converted annotation information into JSON-compliant natural language descriptions, facilitating more effective understanding and training for the VLM. We then evaluate the detection performance of various fine-tuning strategies for VLMs and derive optimized model weights for object detection in remote sensing images. Finally, we evaluate the model's prior knowledge capabilities using natural language queries. Experimental results demonstrate that, without modifying the model architecture, remote sensing object detection can be effectively achieved using natural language alone. Additionally, the model exhibits the ability to perform certain vision question answering (VQA) tasks. Our datasets and related code will be released soon.

arXiv:2503.15524

KHAIT: K-9 Handler Artificial Intelligence Teaming for Collaborative Sensemaking

In urban search and rescue (USAR) operations, communication between handlers and specially trained canines is crucial but often complicated by challenging environments and the specific behaviors canines are trained to exhibit when detecting a person. Since a USAR canine often works out of sight of the handler, the handler lacks awareness of the canine's location and situation, known as the 'sensemaking gap.' In this paper, we propose KHAIT, a novel approach to close the sensemaking gap and enhance USAR effectiveness by integrating object detection-based Artificial Intelligence (AI) and Augmented Reality (AR). Equipped with AI-powered cameras, edge computing, and AR headsets, KHAIT enables precise and rapid object detection from a canine's perspective, improving survivor localization. We evaluate this approach in a real-world USAR environment, demonstrating an average survival allocation time decrease of 22%, enhancing the speed and accuracy of operations.

arXiv:2503.14534

Ship Detection in Remote Sensing Imagery for Arbitrarily Oriented Object Detection

This research paper presents an innovative ship detection system tailored for applications like maritime surveillance and ecological monitoring. The study employs YOLOv8 and repurposed U-Net, two advanced deep learning models, to significantly enhance ship detection accuracy. Evaluation metrics include Mean Average Precision (mAP), processing speed, and overall accuracy. The research utilizes the "Airbus Ship Detection" dataset, featuring diverse remote sensing images, to assess the models' versatility in detecting ships with varying orientations and environmental contexts. Conventional ship detection faces challenges with arbitrary orientations, complex backgrounds, and obscured perspectives. Our approach incorporates YOLOv8 for real-time processing and U-Net for ship instance segmentation. Evaluation focuses on mAP, processing speed, and overall accuracy. The dataset is chosen for its diverse images, making it an ideal benchmark. Results demonstrate significant progress in ship detection. YOLOv8 achieves an 88% mAP, excelling in accurate and rapid ship detection. U Net, adapted for ship instance segmentation, attains an 89% mAP, improving boundary delineation and handling occlusions. This research enhances maritime surveillance, disaster response, and ecological monitoring, exemplifying the potential of deep learning models in ship detection.

arXiv:2503.16251

RESFL: An Uncertainty-Aware Framework for Responsible Federated Learning by Balancing Privacy, Fairness and Utility in Autonomous Vehicles

Autonomous vehicles (AVs) increasingly rely on Federated Learning (FL) to enhance perception models while preserving privacy. However, existing FL frameworks struggle to balance privacy, fairness, and robustness, leading to performance disparities across demographic groups. Privacy-preserving techniques like differential privacy mitigate data leakage risks but worsen fairness by restricting access to sensitive attributes needed for bias correction. This work explores the trade-off between privacy and fairness in FL-based object detection for AVs and introduces RESFL, an integrated solution optimizing both. RESFL incorporates adversarial privacy disentanglement and uncertainty-guided fairness-aware aggregation. The adversarial component uses a gradient reversal layer to remove sensitive attributes, reducing privacy risks while maintaining fairness. The uncertainty-aware aggregation employs an evidential neural network to weight client updates adaptively, prioritizing contributions with lower fairness disparities and higher confidence. This ensures robust and equitable FL model updates. We evaluate RESFL on the FACET dataset and CARLA simulator, assessing accuracy, fairness, privacy resilience, and robustness under varying conditions. RESFL improves detection accuracy, reduces fairness disparities, and lowers privacy attack success rates while demonstrating superior robustness to adversarial conditions compared to other approaches.