Related papers: A Probabilistic Framework for Improving Dense Obje…
Region modification-based data augmentation techniques have shown to improve performance for high level vision tasks (object detection, semantic segmentation, image classification, etc.) by encouraging underlying algorithms to focus on…
Underwater robots play an important role in oceanic geological exploration, resource exploitation, ecological research, and other fields. However, the visual perception of underwater robots is affected by various environmental factors. The…
Training deep neural networks requires datasets with a large number of annotated examples. The collection and annotation of these datasets is not only extremely expensive but also faces legal and privacy problems. These factors are a…
7,651 cases of Search and Rescue Missions (SAR) were reported by the United States Coast Guard in 2024, with over 1322 SAR helicopters deployed in the 6 first months alone. Through the utilizations of YOLO, we were able to run different…
Deep convolutional neural networks have shown remarkable results on multiple detection tasks. Despite the significant progress, the performance of such detectors are often assessed in public benchmarks under non-realistic conditions.…
The efficiency of using the YOLOV5 machine learning model for solving the problem of automatic de-tection and recognition of micro-objects in the marine environment is studied. Samples of microplankton and microplastics were prepared,…
Supervised training of object detectors requires well-annotated large-scale datasets, whose production is costly. Therefore, some efforts have been made to obtain annotations in economical ways, such as cloud sourcing. However, datasets…
Wide-angle fisheye cameras are commonly used in automated driving for parking and low-speed navigation tasks. Four of such cameras form a surround-view system that provides a complete and detailed view of the vehicle. These cameras are…
The success of deep learning in computer vision is based on availability of large annotated datasets. To lower the need for hand labeled images, virtually rendered 3D worlds have recently gained popularity. Creating realistic 3D content is…
Dense Self-Supervised Learning (SSL) methods address the limitations of using image-level feature representations when handling images with multiple objects. Although the dense features extracted by employing segmentation maps and bounding…
Floods cause serious problems around the world. Responding quickly and effectively requires accurate and timely information about the affected areas. The effective use of Remote Sensing images for accurate flood detection requires specific…
This work investigates how the traditional image classification pipelines can be extended into a deep architecture, inspired by recent successes of deep neural networks. We propose a deep boosting framework based on layer-by-layer joint…
Camera traps have become integral tools in wildlife conservation, providing non-intrusive means to monitor and study wildlife in their natural habitats. The utilization of object detection algorithms to automate species identification from…
Satellite remote sensing images pose significant challenges for object detection due to their high resolution, complex scenes, and large variations in target scales. To address the insufficient detection accuracy of the YOLOv11n model in…
In this work, we present a novel and effective framework to facilitate object detection with the instance-level segmentation information that is only supervised by bounding box annotation. Starting from the joint object detection and…
In this paper, we present an Improved Data Augmentation (IDA) technique focused on Salient Object Detection (SOD). Standard data augmentation techniques proposed in the literature, such as image cropping, rotation, flipping, and resizing,…
This work presents a novel deep-learning-based pipeline for the inverse problem of image deblurring, leveraging augmentation and pre-training with synthetic data. Our results build on our winning submission to the recent Helsinki Deblur…
This research presents ADOD, a novel approach to address domain generalization in underwater object detection. Our method enhances the model's ability to generalize across diverse and unseen domains, ensuring robustness in various…
In this paper we have present an improved Cycle GAN based model for under water image enhancement. We have utilized the cycle consistent learning technique of the state-of-the-art Cycle GAN model with modification in the loss function in…
Uses of underwater videos to assess diversity and abundance of fish are being rapidly adopted by marine biologists. Manual processing of videos for quantification by human analysts is time and labour intensive. Automatic processing of…