#object detection
24 resultsSequence-SOD: Bio-inspired Sequence-aware Spiking ObjectDetection for Event Cameras
Katharina Bendig, René Schuster, Didier Stricker
The paper presents Sequence-SOD, a spiking neural network object detector for event cameras that processes continuous sequences of events while preserving membrane potentials, lead…
Object Detection for Autonomous Driving in Chinese Rural Scenes: An Experimental Study on Real-Synthetic Data Mixing and Model Evaluation
Danning Zhu, Ziyan Lin, Jing Wu
The paper introduces a mixed real‑synthetic dataset for object detection on Chinese rural roads and evaluates 13 popular detectors, finding that a moderate amount of synthetic data…
Image Quality Dependent Degradation for AI Systems
Yannick Kees, Elena Hoemann, Frank Köster +1
The paper proposes a method to estimate image quality using normalizing flows and adjust object detection confidence thresholds, enabling safer AI-driven perception in low-quality…
Automated identification of Ichneumonoidea wasps via YOLO-based deep learning: Integrating HiresCam for Explainable AI
Joao Manoel Herrera Pinheiro, Gabriela Do Nascimento Herrera, Alvaro Doria Dos Santos +7
The paper presents a YOLO-based deep learning system combined with HiResCAM to automatically identify Ichneumonoidea wasp families from high‑resolution images, achieving over 96% a…
Training-Free Metrics for Synthetic Object Detection Data: A Proxy for Detector Performance
Myeongseok Nam, Donghun Yeo, Seungwook Kim
The paper introduces Conditional-Composition Domain Match (CCDM), a training-free metric that ranks synthetic object detection datasets by comparing feature distributions within co…
Cotton-SF YOLO: Learning Structural and Frequency Cues for Early Cotton Square Detection in Complex Field Environments
Chengjia Zhang, Yu Li, Feiri Ali +5
The paper introduces Cotton-SF YOLO, a YOLO‑based detector that uses dynamic snake convolution and frequency‑domain feature modulation to improve detection of small, occluded cotto…
Still image and spatial-temporal tomato data enabling detection, segmentation, tracking, and video-instance segmentation using strong and weak labels
Michael Halstead, Esra Guclu, Mohamed Farag +7
The paper introduces two new datasets of tomato plants captured by a robot—still images (BUTom21) and video sequences (BUTom-ST21)—with pixel‑level annotations for fruit detection,…
Zero-Shot Quantization for Object Detectors using Off-the-Shelf Generative Models
Hyunho Lee, Kyomin Hwang, Hyeonjin Kim +3
The paper proposes GoodQ, a method that uses off-the-shelf generative models to create synthetic training data for zero-shot quantization of object detectors, enabling low-bit quan…
Detector Confidence Signals Presence Rather Than Occlusion in Cluttered Manipulation
Yuanzhi He
The paper shows that confidence scores from open‑vocabulary object detectors do not reflect how much of a target object is visible, staying high even when the object is heavily occ…
Symbiosis-Inspired Knowledge Distillation for Incremental Object Detection
Mingyue Zeng, De Cheng, Zhipeng Xu +3
The paper introduces Symbiosis-Inspired Knowledge Distillation (SIKD), a method for incremental object detection that leverages spatial and semantic relationships between old and n…
Star-forming clump detection in nearby galaxies using Faster R-CNN and $ugrizy$ imaging data from CLAUDS and HSC-SSP
Jürgen J. Popp, Hugh Dickinson, Stephen Serjeant +4
The paper presents a deep‑learning object detection pipeline based on Faster R‑CNN and a Zoobot backbone to locate giant star‑forming clumps in low‑redshift galaxies using six‑band…
Low-latency Event-based Object Detection with Spatially-Sparse Linear Attention
Haiqing Hao, Zhipeng Sui, Rong Zou +4
The paper introduces Spatially‑Sparse Linear Attention (SSLA) to exploit the spatial sparsity of event‑camera data, enabling efficient parallel training and low‑latency object dete…
A Comprehensive Evaluation of Deep Learning Object Detection Models on Heterogeneous Edge Devices
Daghash K. Alqahtani, Muhammad Aamir Cheema, Maria A. Rodriguez +1
The paper benchmarks several deep learning object detection models on various edge devices, measuring accuracy, latency, and energy use while also analyzing performance as scene co…
Automatic Labelling for Low-Light Pedestrian Detection
Dimitrios Bouzoulas, Eerik Alamikkotervo, Risto Ojala
The paper introduces an automated infrared‑RGB pipeline that generates labels for low‑light RGB pedestrian images, and shows that object detectors trained on these auto‑generated l…
Leveraging Prior Knowledge of Diffusion Model for Person Search
Giyeol Kim, Sooyoung Yang, Jihyong Oh +2
The paper presents DiffPS, a person search framework that incorporates a pre-trained diffusion model to improve both person detection and re-identification, using three specialized…
MambaPSA: A Mamba-based Replacement for C2PSA in YOLO26
Sheng-Wei Chan, Chia-Min Lin, Hsin-Jui Pan +4
The paper introduces MambaPSA, a lightweight Mamba‑based module that replaces the C2PSA block in the YOLO26 object detector and adds a bidirectional Vision Mamba (BiViM) to the nec…
Metric-Guided Synthetic Image Data Rendering for Deep Learning compatible with Agentic AI
Martina Radoynova, Samuel Pantze, Trina De +2
The paper introduces GraNatPy, a Python toolkit that uses quantitative metrics to improve the realism and diversity of synthetically rendered images for training deep learning visi…
Inhibited Self-Attention: Sharpening Focus in Vision Transformers
Peter R. D. van der Wal, Nicola Strisciuglio, George Azzopardi
The paper proposes Inhibited Self-Attention (ISA), a modification to Vision Transformers that incorporates negative attention scores to suppress background features, leading to sha…
No Attention, No Problem: DPU-Aware Attention Approximation in Modern YOLO on FPGA
Suraj Karki, Qazi Arbab Ahmed, Thorsten Jungeblut
The paper presents a DPU‑aware architecture that approximates spatial attention for modern YOLO models on AMD FPGAs, enabling efficient edge‑based object detection with reduced pow…
C-Norm: Cell-Distribution Normalization Enables Precision Recognition of Medical-Cell Image
Yang Qianl, Liu Xiany, Dai Daw +5
The paper proposes a Cell-Distribution Normalization (C‑Norm) technique that balances the spatial distribution of cells in ThinPrep Cytologic Test images and combines YOLOv12 with…
A Comparative Evaluation of Large Vision-Language Models for 2D Object Detection under SOTIF Conditions
Ji Zhou, Yilin Ding, Yongqi Zhao +4
The paper systematically evaluates ten large vision‑language models for 2D object detection on the PeSOTIF benchmark, comparing their recall and precision to YOLOv5 and RT‑DETRv4 u…
Event Burst Trigger: An Availability Backdoor Attack on Event-Based SNN Object Detection
Jaesun Baek, Chanwook Lee, Eun-Kyu Lee
The paper introduces Event Burst Trigger, a backdoor attack that injects event‑based triggers into training data of spiking neural network (SNN) object detectors, causing bursty ev…
Antineutron reconstruction in electromagnetic calorimeters with mixed-representation learning
Yangu Li, Hongtian Yu, Yuyang Huang +7
The paper introduces a mixed‑representation neural network that combines visual and sequential features to identify antineutrons in electromagnetic calorimeters, enabling direct me…
NEEDL-Bench: Dataset for Swiss Needle Cast and Stomata Detection in Microscopy Images
Benjamin Blake, Declan McIntosh, Jürgen Ehlting +3
The paper introduces NEEDL-Bench, a microscopy image dataset with annotations for detecting Swiss Needle Cast disease structures and stomata in Douglas-fir needles, and provides ba…