相关论文: Enhancing Zero-shot Counting via Language-guided E…

Better disentanglement of speech representation is essential to improve the quality of voice conversion. Recently contrastive learning is applied to voice conversion successfully based on speaker labels. However, the performance of model…

This paper considers contrastive training for cross-modal 0-shot transfer wherein a pre-trained model in one modality is used for representation learning in another domain using pairwise data. The learnt models in the latter domain can then…

zero-shot learning is an essential part of computer vision. As a classical downstream task, zero-shot semantic segmentation has been studied because of its applicant value. One of the popular zero-shot semantic segmentation methods is based…

We propose a novel zero-shot learning method for semantic utterance classification (SUC). It learns a classifier $f: X \to Y$ for problems where none of the semantic categories $Y$ are present in the training set. The framework uncovers the…

There has been a recent spike in interest in multi-modal Language and Vision problems. On the language side, most of these models primarily focus on English since most multi-modal datasets are monolingual. We try to bridge this gap with a…

Local dialects influence people to pronounce words of the same language differently from each other. The great variability and complex characteristics of accents creates a major challenge for training a robust and accent-agnostic automatic…

Audio-language models have recently demonstrated strong zero-shot capabilities by leveraging natural-language supervision to classify audio events without labeled training data. Yet, their performance is highly sensitive to the wording of…

Large-scale pre-trained Vision-Language Models (VLMs), such as CLIP, establish the correlation between texts and images, achieving remarkable success on various downstream tasks with fine-tuning. In existing fine-tuning methods, the…

Linear embedding transformation has been shown to be effective for zero-shot cross-lingual transfer tasks and achieve surprisingly promising results. However, cross-lingual embedding space mapping is usually studied in static word-level…

While in-context learning with large language models (LLMs) has shown impressive performance, we have discovered a unique miscalibration behavior where both correct and incorrect predictions are assigned the same level of confidence. We…

Zero-shot learning (ZSL) aims to recognize instances of unseen classes solely based on the semantic descriptions of the classes. Existing algorithms usually formulate it as a semantic-visual correspondence problem, by learning mappings from…

Finetuning pretrained models on downstream generation tasks often leads to catastrophic forgetting in zero-shot conditions. In this work, we focus on summarization and tackle the problem through the lens of language-independent…

Recent advances in audio-text cross-modal contrastive learning have shown its potential towards zero-shot learning. One possibility for this is by projecting item embeddings from pre-trained backbone neural networks into a cross-modal space…

Zero-shot translation aims to translate between language pairs not seen during training in Multilingual Machine Translation (MMT) and is largely considered an open problem. A common, albeit resource-consuming, solution is to add as many…

Large language models (LLMs) are very proficient text generators. We leverage this capability of LLMs to generate task-specific data via zero-shot prompting and promote cross-lingual transfer for low-resource target languages. Given…

Through a simple multiple choice language prompt a VQA model can operate as a zero-shot image classifier, producing a classification label. Compared to typical image encoders, VQA models offer an advantage: VQA-produced image embeddings can…

In some of object recognition problems, labeled data may not be available for all categories. Zero-shot learning utilizes auxiliary information (also called signatures) describing each category in order to find a classifier that can…

Zero-Shot Learning (ZSL) is typically achieved by resorting to a class semantic embedding space to transfer the knowledge from the seen classes to unseen ones. Capturing the common semantic characteristics between the visual modality and…

A hallmark of human intelligence is the ability to learn new concepts purely from language. Several recent approaches have explored training machine learning models via natural language supervision. However, these approaches fall short in…

Targeted for real world scenarios, online continual learning aims to learn new tasks from sequentially available data under the condition that each data is observed only once by the learner. Though recent works have made remarkable…