相关论文: Zero-shot Learning of Individualized Task Contrast…

Prompt learning has become one of the most efficient paradigms for adapting large pre-trained vision-language models to downstream tasks. Current state-of-the-art methods, like CoOp and ProDA, tend to adopt soft prompts to learn an…

Zero-shot inference is a powerful paradigm that enables the use of large pretrained models for downstream classification tasks without further training. However, these models are vulnerable to inherited biases that can impact their…

Contrastive visual language pretraining has emerged as a powerful method for either training new language-aware image encoders or augmenting existing pretrained models with zero-shot visual recognition capabilities. However, existing works…

The high cost of annotating data makes self-supervised approaches, such as contrastive learning methods, appealing for Human Activity Recognition (HAR). Effective contrastive learning relies on selecting informative positive and negative…

While developments in machine learning led to impressive performance gains on big data, many human subjects data are, in actuality, small and sparsely labeled. Existing methods applied to such data often do not easily generalize to…

Self-supervised pre-training of deep learning models with contrastive learning is a widely used technique in image analysis. Current findings indicate a strong potential for contrastive pre-training on medical images. However, further…

Zero-shot learning (ZSL) which aims to recognize unseen object classes by only training on seen object classes, has increasingly been of great interest in Machine Learning, and has registered with some successes. Most existing ZSL methods…

Zero-shot imitation learning algorithms hold the promise of reproducing unseen behavior from as little as a single demonstration at test time. Existing practical approaches view the expert demonstration as a sequence of goals, enabling…

Contrastive Language-Image Pretraining (CLIP) has demonstrated strong zero-shot performance across diverse downstream text-image tasks. Existing CLIP methods typically optimize a contrastive objective using negative samples drawn from each…

A prevailing approach for learning visuomotor policies is to employ reinforcement learning to map high-dimensional visual observations directly to action commands. However, the combination of high-dimensional visual inputs and agile…

Predicting the neural response to natural images in the visual cortex requires extracting relevant features from the images and relating those feature to the observed responses. In this work, we optimize the feature extraction in order to…

Generalized zero-shot learning aims to recognize both seen and unseen classes with the help of semantic information that is shared among different classes. It inevitably requires consistent visual-semantic alignment. Existing approaches…

Self-supervised contrastive learning models, such as CLIP, have set new benchmarks for vision-language models in many downstream tasks. However, their dependency on rigid one-to-one mappings overlooks the complex and often multifaceted…

Few-Shot learning aims to train and optimize a model that can adapt to unseen visual classes with only a few labeled examples. The existing few-shot learning (FSL) methods, heavily rely only on visual data, thus fail to capture the semantic…

Pretrained large-scale vision-language models like CLIP have exhibited strong generalization over unseen tasks. Yet imperceptible adversarial perturbations can significantly reduce CLIP's performance on new tasks. In this work, we identify…

Meta-learning enables learning systems to adapt quickly to new tasks, similar to humans. Different meta-learning approaches all work under/with the mini-batch episodic training framework. Such framework naturally gives the information about…

In this paper, we propose a novel framework for speech-image retrieval. We utilize speech-image contrastive (SIC) learning tasks to align speech and image representations at a coarse level and speech-image matching (SIM) learning tasks to…

This paper proposes Comprehensive Pathology Language Image Pre-training (CPLIP), a new unsupervised technique designed to enhance the alignment of images and text in histopathology for tasks such as classification and segmentation. This…

Foundation models have had a significant impact across various AI applications, enabling use cases that were previously impossible. Contrastive Visual Language Models (VLMs), in particular, have outperformed other techniques in many tasks.…

Vision-Language Models like CLIP create aligned embedding spaces for text and images, making it possible for anyone to build a visual classifier by simply naming the classes they want to distinguish. However, a model that works well in one…