Related papers: Task-Adapter++: Task-specific Adaptation with Orde…
Gradient-based meta-learning techniques aim to distill useful prior knowledge from a set of training tasks such that new tasks can be learned more efficiently with gradient descent. While these methods have achieved successes in various…
Contrastive Vision-Language Pre-training, known as CLIP, has provided a new paradigm for learning visual representations using large-scale image-text pairs. It shows impressive performance on downstream tasks by zero-shot knowledge…
Assistive teleoperation enhances efficiency via shared control, yet inter-operator variability, stemming from diverse habits and expertise, induces highly heterogeneous trajectory distributions that undermine intent recognition stability.…
Meta-learning methods have been extensively studied and applied in computer vision, especially for few-shot classification tasks. The key idea of meta-learning for few-shot classification is to mimic the few-shot situations faced at test…
Few-shot learning has become essential for producing models that generalize from few examples. In this work, we identify that metric scaling and metric task conditioning are important to improve the performance of few-shot algorithms. Our…
Vision-language models have recently shown great potential on many tasks in computer vision. Meanwhile, prior work demonstrates prompt tuning designed for vision-language models could acquire superior performance on few-shot image…
Large vision-language representation learning models like CLIP have demonstrated impressive performance for zero-shot transfer to downstream tasks while largely benefiting from inter-modal (image-text) alignment via contrastive objectives.…
Successfully addressing a wide variety of tasks is a core ability of autonomous agents, requiring flexibly adapting the underlying decision-making strategies and, as we argue in this work, also adapting the perception modules. An analogical…
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 work on action recognition leverages 3D features and textual information to achieve state-of-the-art performance. However, most of the current few-shot action recognition methods still rely on 2D frame-level representations, often…
We study the problem of few-shot open-set recognition (FSOR), which learns a recognition system capable of both fast adaptation to new classes with limited labeled examples and rejection of unknown negative samples. Traditional large-scale…
In recent years, numerous domain adaptive strategies have been proposed to help deep learning models overcome the challenges posed by domain shift. However, even unsupervised domain adaptive strategies still require a large amount of target…
Pre-trained vision and language models such as CLIP have witnessed remarkable success in connecting images and texts with a primary focus on English texts. Despite recent efforts to extend CLIP to support other languages, disparities in…
Pre-trained Vision-Language Models (VLMs), like CLIP, exhibit strong generalization ability to downstream tasks but struggle in few-shot scenarios. Existing prompting techniques primarily focus on global text and image representations, yet…
Few-shot action recognition, i.e. recognizing new action classes given only a few examples, benefits from incorporating temporal information. Prior work either encodes such information in the representation itself and learns classifiers at…
The goal of few-shot learning is to classify unseen categories with few labeled samples. Recently, the low-level information metric-learning based methods have achieved satisfying performance, since local representations (LRs) are more…
Parameter-efficient fine-tuning methods have emerged as a promising solution for adapting pre-trained models to various downstream tasks. While these methods perform well in single-task learning, extending them to multi-task learning…
Few-shot action recognition (FSAR) requires models to generalize to novel action categories from only a handful of annotated samples. Despite progress with vision-language models, existing approaches still suffer from semantic-temporal…
Training a neural network model that can quickly adapt to a new task is highly desirable yet challenging for few-shot learning problems. Recent few-shot learning methods mostly concentrate on developing various meta-learning strategies from…
Contrastive Vision-Language Pre-training, known as CLIP, has provided a new paradigm for learning visual representations by using large-scale contrastive image-text pairs. It shows impressive performance on zero-shot knowledge transfer to…