Related papers: Episode-specific Fine-tuning for Metric-based Few-…
Training a modern deep neural network on massive labeled samples is the main paradigm in solving the scene classification problem for remote sensing, but learning from only a few data points remains a challenge. Existing methods for…
Few-shot semantic segmentation aims to segment the target objects in query under the condition of a few annotated support images. Most previous works strive to mine more effective category information from the support to match with the…
Parameter-efficient fine-tuning (PEFT) that was initially developed for exploiting pre-trained large language models has recently emerged as an effective approach to perform transfer learning on computer vision tasks. However, the…
Just like other few-shot learning problems, few-shot segmentation aims to minimize the need for manual annotation, which is particularly costly in segmentation tasks. Even though the few-shot setting reduces this cost for novel test…
Irrelevant features can significantly degrade few-shot learn ing performance. This problem is used to match queries and support images based on meaningful similarities despite the limited data. However, in this process, non-relevant fea…
Few-shot image classification is a challenging problem that aims to achieve the human level of recognition based only on a small number of training images. One main solution to few-shot image classification is deep metric learning. These…
Pre-trained vision-language models learn massive data to model unified representations of images and natural languages, which can be widely applied to downstream machine learning tasks. In addition to zero-shot inference, in order to better…
Current parameter-efficient fine-tuning (PEFT) methods build adapters widely agnostic of the context of downstream task to learn, or the context of important knowledge to maintain. As a result, there is often a performance gap compared to…
Pre-trained vision-language models (VLMs) exhibit strong zero-shot generalization but remain vulnerable to adversarial perturbations. Existing classification-guided adversarial fine-tuning methods often disrupt pre-trained cross-modal…
Few-shot learning aims to learn representations that can tackle novel tasks given a small number of examples. Recent studies show that cross-modal learning can improve representations for few-shot classification. More specifically, language…
Few-shot learning allows pre-trained language models to adapt to downstream tasks while using a limited number of training examples. However, practical applications are limited when all model parameters must be optimized. In this work we…
Adapting Foundation Models (FMs) for downstream tasks through Federated Learning (FL) emerges a promising strategy for protecting data privacy and valuable FMs. Existing methods fine-tune FM by allocating sub-FM to clients in FL, however,…
Remote sensing applications increasingly rely on deep learning for scene classification. However, their performance is often constrained by the scarcity of labeled data and the high cost of annotation across diverse geographic and sensor…
Recognition of remote sensing (RS) or aerial images is currently of great interest, and advancements in deep learning algorithms added flavor to it in recent years. Occlusion, intra-class variance, lighting, etc., might arise while training…
The rise of deep learning has marked significant progress in fields such as computer vision, natural language processing, and medical imaging, primarily through the adaptation of pre-trained models for specific tasks. Traditional…
The core idea of metric-based few-shot image classification is to directly measure the relations between query images and support classes to learn transferable feature embeddings. Previous work mainly focuses on image-level feature…
The ability to quickly learn a new task with minimal instruction - known as few-shot learning - is a central aspect of intelligent agents. Classical few-shot benchmarks make use of few-shot samples from a single modality, but such samples…
Transfer learning of diffusion models to smaller target domains is challenging, as naively fine-tuning the model often results in poor generalization. Test-time guidance methods help mitigate this by offering controllable improvements in…
Few-shot learning aims to adapt knowledge learned from previous tasks to novel tasks with only a limited amount of labeled data. Research literature on few-shot learning exhibits great diversity, while different algorithms often excel at…
Recent years have witnessed the great progress of deep neural networks on semantic segmentation, particularly in medical imaging. Nevertheless, training high-performing models require large amounts of pixel-level ground truth masks, which…