Related papers: Rethinking Cell Counting Methods: Decoupling Count…
Can we automatically group images into semantically meaningful clusters when ground-truth annotations are absent? The task of unsupervised image classification remains an important, and open challenge in computer vision. Several recent…
Automated and semi-automated techniques in biomedical electron microscopy (EM) enable the acquisition of large datasets at a high rate. Segmentation methods are therefore essential to analyze and interpret these large volumes of data, which…
Efficiently merging several models fine-tuned for different tasks, but stemming from the same pretrained base model, is of great practical interest. Despite extensive prior work, most evaluations of model merging in computer vision are…
In this Technical Report we propose a set of improvements with respect to the KernelBoost classifier presented in [Becker et al., MICCAI 2013]. We start with a scheme inspired by Auto-Context, but that is suitable in situations where the…
We introduce DeSCo, a scalable neural deep subgraph counting pipeline, designed to accurately predict both the count and occurrence position of queries on target graphs post single training. Firstly, DeSCo uses a novel canonical partition…
We propose a new information aggregation method which called Localized Feature Aggregation Module based on the similarity between the feature maps of an encoder and a decoder. The proposed method recovers positional information by…
The number of leaves a plant has is one of the key traits (phenotypes) describing its development and growth. Here, we propose an automated, deep learning based approach for counting leaves in model rosette plants. While state-of-the-art…
Contrastive Language-Image Pre-training (CLIP) has achieved success on multiple downstream tasks by aligning image and text modalities. However, the nature of global contrastive learning limits CLIP's ability to comprehend compositional…
Change detection (CD) is an important yet challenging task in the Earth observation field for monitoring Earth surface dynamics. The advent of deep learning techniques has recently propelled automatic CD into a technological revolution.…
Deep models have improved state-of-the-art for both supervised and unsupervised learning. For example, deep embedded clustering (DEC) has greatly improved the unsupervised clustering performance, by using stacked autoencoders for…
High levels of noise usually exist in today's captured images due to the relatively small sensors equipped in the smartphone cameras, where the noise brings extra challenges to lossy image compression algorithms. Without the capacity to…
Continual Semantic Segmentation (CSS) requires learning new classes without forgetting previously acquired knowledge, addressing the fundamental challenge of catastrophic forgetting in dense prediction tasks. However, existing CSS methods…
In this work, we introduce a Denser Feature Network (DenserNet) for visual localization. Our work provides three principal contributions. First, we develop a convolutional neural network (CNN) architecture which aggregates feature maps at…
When capturing and storing images, devices inevitably introduce noise. Reducing this noise is a critical task called image denoising. Deep learning has become the de facto method for image denoising, especially with the emergence of…
Camera localization aims to estimate 6 DoF camera poses from RGB images. Traditional methods detect and match interest points between a query image and a pre-built 3D model. Recent learning-based approaches encode scene structures into a…
Identification and counting of cells and mitotic figures is a standard task in diagnostic histopathology. Due to the large overall cell count on histological slides and the potential sparse prevalence of some relevant cell types or mitotic…
Prompt learning has emerged as an efficient and effective approach for transferring foundational Vision-Language Models (e.g., CLIP) to downstream tasks. However, current methods tend to overfit to seen categories, thereby limiting their…
Model merging offers an effective strategy to combine the strengths of multiple finetuned models into a unified model that preserves the specialized capabilities of each. Existing methods merge models in a global manner, performing…
Medical image segmentation of anatomical structures and pathology is crucial in modern clinical diagnosis, disease study, and treatment planning. To date, great progress has been made in deep learning-based segmentation techniques, but most…
Semantic segmentation of microscopic cell images using deep learning is an important technique, however, it requires a large number of images and ground truth labels for training. To address the above problem, we consider an efficient…