Related papers: Task-Adapter++: Task-specific Adaptation with Orde…

Deep learning has achieved great success in video recognition, yet still struggles to recognize novel actions when faced with only a few examples. To tackle this challenge, few-shot action recognition methods have been proposed to transfer…

Few-shot learning and parameter-efficient fine-tuning (PEFT) are crucial to overcome the challenges of data scarcity and ever growing language model sizes. This applies in particular to specialized scientific domains, where researchers…

Large-scale vision-language pre-trained models have shown promising transferability to various downstream tasks. As the size of these foundation models and the number of downstream tasks grow, the standard full fine-tuning paradigm becomes…

The Few-Shot Segmentation (FSS) aims to accomplish the novel class segmentation task with a few annotated images. Current FSS research based on meta-learning focus on designing a complex interaction mechanism between the query and support…

We propose a few-shot adaptation framework, which bridges zero-shot learning and supervised many-shot learning, for semantic indexing of image and video data. Few-shot adaptation provides robust parameter estimation with few training…

Multi-label image recognition in the low-label regime is a task of great challenge and practical significance. Previous works have focused on learning the alignment between textual and visual spaces to compensate for limited image labels,…

Recent attempts mainly focus on learning deep representations for each video individually under the episodic meta-learning regime and then performing temporal alignment to match query and support videos. However, they still suffer from two…

Few-shot learning (FSL), which aims to recognise new classes by adapting the learned knowledge with extremely limited few-shot (support) examples, remains an important open problem in computer vision. Most of the existing methods for…

Recent progress in the few-shot adaptation of Vision-Language Models (VLMs) has further pushed their generalization capabilities, at the expense of just a few labeled samples within the target downstream task. However, this promising,…

Recent advances in flexible keyword spotting (KWS) with text enrollment allow users to personalize keywords without uttering them during enrollment. However, there is still room for improvement in target keyword performance. In this work,…

Image restoration has traditionally required training specialized models on thousands of paired examples per degradation type. We challenge this paradigm by demonstrating that powerful pre-trained text-conditioned image editing models can…

Fine-tuning pre-trained Neural Machine Translation (NMT) models is the dominant approach for adapting to new languages and domains. However, fine-tuning requires adapting and maintaining a separate model for each target task. We propose a…

We develop a novel approach to conformal prediction when the target task has limited data available for training. Conformal prediction identifies a small set of promising output candidates in place of a single prediction, with guarantees…

The existing few-shot video classification methods often employ a meta-learning paradigm by designing customized temporal alignment module for similarity calculation. While significant progress has been made, these methods fail to focus on…

Cross-Domain Few-Shot Learning (CDFSL) adapts models trained with large-scale general data (source domain) to downstream target domains with only scarce training data, where the research on vision-language models (e.g., CLIP) is still in…

Few-shot image classification remains difficult under limited supervision and visual domain shift. Recent cache-based adaptation approaches (e.g., Tip-Adapter) address this challenge to some extent by learning lightweight residual adapters…

The canonical approach to video action recognition dictates a neural model to do a classic and standard 1-of-N majority vote task. They are trained to predict a fixed set of predefined categories, limiting their transferable ability on new…

Prompt-based methods have been successfully applied in sentence-level few-shot learning tasks, mostly owing to the sophisticated design of templates and label words. However, when applied to token-level labeling tasks such as NER, it would…

Adapting CLIP for anomaly detection on unseen objects has shown strong potential in a zero-shot manner. However, existing methods typically rely on a single textual space to align with visual semantics across diverse objects and domains.…

Neural operator methods have emerged as powerful tools for learning mappings between infinite-dimensional function spaces, yet their potential in optimal control remains largely unexplored. We focus on multi-task control problems, whose…