Related papers: Is Bigger Always Better? Efficiency Analysis in Re…

Recent results in image classification and extractive question answering have observed that pre-trained models trained on less in-distribution data have better out-of-distribution performance. However, it is unclear how broadly these trends…

Scalability of evolutionary algorithms refers to assessing how their performance changes as problem size increases. In the area of multi-objective optimisation, research on the scalability of multi-objective evolutionary algorithms (MOEAs)…

Robustness and Effectiveness are critical aspects of developing dense retrieval models for real-world applications. It is known that there is a trade-off between the two. Recent work has addressed scaling laws of effectiveness in dense…

Multi-scale resolution training has seen an increased adoption across multiple vision tasks, including classification and detection. Training with smaller resolutions enables faster training at the expense of a drop in accuracy. Conversely,…

Datasets for training object recognition systems are steadily increasing in size. This paper investigates the question of whether existing detectors will continue to improve as data grows, or saturate in performance due to limited model…

Object detection remains as one of the most notorious open problems in computer vision. Despite large strides in accuracy in recent years, modern object detectors have started to saturate on popular benchmarks raising the question of how…

Earth Observation (EO) data are increasingly used in policy analysis by enabling granular estimation of conditional average treatment effects (CATE). However, a challenge in EO-based causal inference is determining the scale of the input…

Visual detection of Unmanned Aerial Vehicles (UAVs) is a critical task in surveillance systems due to their small physical size and environmental challenges. Although deep learning models have achieved significant progress, deploying them…

Accurate apple detection in orchard images is important for yield prediction, fruit counting, robotic harvesting, and crop monitoring. However, changing illumination, leaf clutter, dense fruit clusters, and partial occlusion make detection…

Detecting small objects in complex scenes, such as those captured by drones, is a daunting challenge due to the difficulty in capturing the complex features of small targets. While the YOLO family has achieved great success in large target…

Ensembling is a simple and popular technique for boosting evaluation performance by training multiple models (e.g., with different initializations) and aggregating their predictions. This approach is commonly reserved for the largest…

The field of object detection using Deep Learning (DL) is constantly evolving with many new techniques and models being proposed. YOLOv7 is a state-of-the-art object detector based on the YOLO family of models which have become popular for…

Weeds compete with crops for light, water, and nutrients, reducing yield and crop quality. Efficient weed detection is essential for site-specific weed management (SSWM). Although deep learning models have been deployed on UAV-based edge…

In recent years, the development of robust multi-source models has emerged in the Earth Observation (EO) field. These are models that leverage data from diverse sources to improve predictive accuracy when there is missing data. Despite…

Traditionally, an object detector is applied to every part of the scene of interest, and its accuracy and computational cost increases with higher resolution images. However, in some application domains such as remote sensing, purchasing…

This research work dives into an in-depth evaluation of the YOLOv8 (You Only Look Once) algorithm's efficiency in object detection, specially focusing on Barcode and QR code recognition. Utilizing the real-time detection abilities of…

Now a days, UAVs such as drones are greatly used for various purposes like that of capturing and target detection from ariel imagery etc. Easy access of these small ariel vehicles to public can cause serious security threats. For instance,…

With the rapid development of global industrial production, the demand for reliability in power equipment has been continuously increasing. Ensuring the stability of power system operations requires accurate methods to detect potential…

This work investigates the ``small-vs-large gap'', where repeating on fewer samples can lead to compute saving during training compared to using a larger dataset. This is observed across algorithmic tasks, architectures and optimizers and…

Existing Real-Time Object Detection (RTOD) methods commonly adopt YOLO-like architectures for their favorable trade-off between accuracy and speed. However, these models rely on static dense computation that applies uniform processing to…