Related papers: Zero-Training Task-Specific Model Synthesis for Fe…

Accurate and robust medical image classification is paramount for early disease diagnosis and treatment planning. However, challenges such as limited annotated data, high intra-class variability, and subtle inter-class differences often…

Few-shot semantic segmentation aims at recognizing the object regions of unseen categories with only a few annotated examples as supervision. The key to few-shot segmentation is to establish a robust semantic relationship between the…

Traditional semantic segmentation tasks require a large number of labels and are difficult to identify unlearned categories. Few-shot semantic segmentation (FSS) aims to use limited labeled support images to identify the segmentation of new…

Zero-shot Panoptic Segmentation (ZPS) aims to recognize foreground instances and background stuff without images containing unseen categories in training. Due to the visual data sparsity and the difficulty of generalizing from seen to…

Remote sensing imagery has attracted significant attention in recent years due to its instrumental role in global environmental monitoring, land usage monitoring, and more. As image databases grow each year, performing automatic…

Few-shot segmentation (FSS) aims to segment unseen classes given only a few annotated samples. Existing methods suffer the problem of feature undermining, i.e. potential novel classes are treated as background during training phase. Our…

In medical image segmentation, supervised deep networks' success comes at the cost of requiring abundant labeled data. While asking domain experts to annotate only one or a few of the cohort's images is feasible, annotating all available…

Deep learning-based semantic segmentation models achieve impressive results yet remain limited in handling distribution shifts between training and test data. In this paper, we present SDGPA (Synthetic Data Generation and Progressive…

Fully supervised semantic segmentation technologies bring a paradigm shift in scene understanding. However, the burden of expensive labeling cost remains as a challenge. To solve the cost problem, recent studies proposed language model…

Large pre-trained models achieve remarkable performance in vision tasks but are impractical for fine-tuning due to high computational and storage costs. Parameter-Efficient Fine-Tuning (PEFT) methods mitigate this issue by updating only a…

A primary challenge faced in few-shot action recognition is inadequate video data for training. To address this issue, current methods in this field mainly focus on devising algorithms at the feature level while little attention is paid to…

The objective of few-shot named entity recognition is to identify named entities with limited labeled instances. Previous works have primarily focused on optimizing the traditional token-wise classification framework, while neglecting the…

Few-Shot Segmentation(FSS) aims to efficient segmentation of new objects with few labeled samples. However, its performance significantly degrades when domain discrepancies exist between training and deployment. Cross-Domain Few-Shot…

Skin cancer is one of the deadliest diseases and has a high mortality rate if left untreated. The diagnosis generally starts with visual screening and is followed by a biopsy or histopathological examination. Early detection can aid in…

Zero-shot learning holds tremendous potential for histopathology image analysis by enabling models to generalize to unseen classes without extensive labeled data. Recent advancements in vision-language models (VLMs) have expanded the…

Zero-shot detection (ZSD) is a challenging task where we aim to recognize and localize objects simultaneously, even when our model has not been trained with visual samples of a few target ("unseen") classes. Recently, methods employing…

The high cost of creating pixel-by-pixel gold-standard labels, limited expert availability, and presence of diverse tasks make it challenging to generate segmentation labels to train deep learning models for medical imaging tasks. In this…

Learning from limited data is challenging because data scarcity leads to a poor generalization of the trained model. A classical global pooled representation will probably lose useful local information. Many few-shot learning methods have…

Weakly-supervised learning under image-level labels supervision has been widely applied to semantic segmentation of medical lesions regions. However, 1) most existing models rely on effective constraints to explore the internal…

Generative modeling in machine learning aims to synthesize new data samples that are statistically similar to those observed during training. While conventional generative models such as GANs and diffusion models typically assume access to…