Related papers: Enhanced LULC Segmentation via Lightweight Model R…
Misuse of LLM-generated text can be curbed by watermarking techniques that embed implicit signals into the output. We propose a watermark that partitions the vocabulary at each decoding step into three sets (Green/Yellow/Red) with fixed…
We present LOCUS (LOw-cost Customization for Universal Specialization), a pipeline that consumes few-shot data to streamline the construction and training of NLP models through targeted retrieval, synthetic data generation, and…
Free space ground segmentation is essential to navigate autonomous robots, recognize drivable zones, and traverse efficiently. Fine-grained features remain challenging for existing segmentation models, particularly for robots in indoor,…
Pruning aims to accelerate and compress models by removing redundant parameters, identified by specifically designed importance scores which are usually imperfect. This removal is irreversible, often leading to subpar performance in pruned…
Confidence assessments of semantic segmentation algorithms are important. Ideally, deep learning models should have the ability to predict in advance whether their output is likely to be incorrect. Assessing the confidence levels of model…
Channel puncturing transforms a multiple-input multiple-output (MIMO) channel into a sparse lower-triangular form using the so-called WL decomposition scheme in order to reduce tree-based detection complexity. We propose computationally…
Language models (LMs) significantly improve the recognition accuracy of end-to-end (E2E) models on words rarely seen during training, when used in either the shallow fusion or the rescoring setups. In this work, we introduce LMs in the…
In industrial anomaly detection, model efficiency and mobile-friendliness become the primary concerns in real-world applications. Simultaneously, the impressive generalization capabilities of Segment Anything (SAM) have garnered broad…
We study the organization of channel-level importance in transformer feed-forward networks (FFNs). Using a Fisher-style loss proxy (LP) based on activation-gradient second moments, we show that loss sensitivity is concentrated in a small…
We present a weakly supervised deep learning method to perform instance segmentation of cells present in microscopy images. Annotation of biomedical images in the lab can be scarce, incomplete, and inaccurate. This is of concern when…
Underwater imagery is often compromised by factors such as color distortion and low contrast, posing challenges for high-level vision tasks. Recent underwater image restoration (UIR) methods either analyze the input image at full…
The autocovariance least squares (ALS) method is a computationally efficient approach for estimating noise covariances in Kalman filters without requiring specific noise models. However, conventional ALS and its variants rely on the classic…
Recent advancements in synthetic aperture radar (SAR) ship detection using deep learning have significantly improved accuracy and speed, yet effectively detecting small objects in complex backgrounds with fewer parameters remains a…
Semantic segmentation is the task of classifying each pixel in an image. Training a segmentation model achieves best results using annotated images, where each pixel is annotated with the corresponding class. When obtaining fine annotations…
Scene recognition, particularly for aerial and underwater images, often suffers from various types of degradation, such as blurring or overexposure. Previous works that focus on convolutional neural networks have been shown to be able to…
DL based Synthetic Aperture Radar (SAR) ship detection has tremendous advantages in numerous areas. However, it still faces some problems, such as the lack of prior knowledge, which seriously affects detection accuracy. In order to solve…
Land use / land cover (LULC) modeling is a challenging task due to long-range dependencies between geographic features and distinct spatial patterns related to topography, ecology, and human development. We identify a close connection…
Ireland's coastline, a critical and dynamic resource, is facing challenges such as erosion, sedimentation, and human activities. Monitoring these changes is a complex task we approach using a combination of satellite imagery and deep…
Satellite-based remote sensing is instrumental in the monitoring and mitigation of the effects of anthropogenic climate change. Large scale, high resolution data derived from these sensors can be used to inform intervention and policy…
This work presents use of Fully Convolutional Network (FCN-8) for semantic segmentation of high-resolution RGB earth surface satel-lite images into land use land cover (LULC) categories. Specically, we propose a non-overlapping grid-based…