相关论文: Can this Model Also Recognize Dogs? Zero-Shot Mode…

Object recognition systems usually require fully complete manually labeled training data to train the classifier. In this paper, we study the problem of object recognition where the training samples are missing during the classifier…

The number of publicly available models is rapidly increasing, yet most remain undocumented. Users looking for suitable models for their tasks must first determine what each model does. Training machine learning models to infer missing…

We propose the new problem of choosing which dense retrieval model to use when searching on a new collection for which no labels are available, i.e. in a zero-shot setting. Many dense retrieval models are readily available. Each model…

Zero-shot Learners are models capable of predicting unseen classes. In this work, we propose a Zero-shot Learning approach for text categorization. Our method involves training model on a large corpus of sentences to learn the relationship…

The problem of organizing and finding images in a user's directory has become increasingly challenging due to the rapid growth in the number of images captured on personal devices. This paper presents a solution that utilizes zero shot…

While billions of non-English speaking users rely on search engines every day, the problem of ad-hoc information retrieval is rarely studied for non-English languages. This is primarily due to a lack of data set that are suitable to train…

When it comes to deploying deep vision models, the behavior of these systems must be explicable to ensure confidence in their reliability and fairness. A common approach to evaluate deep learning models is to build a labeled test set with…

Large pre-trained models can dramatically reduce the amount of task-specific data required to solve a problem, but they often fail to capture domain-specific nuances out of the box. The Web likely contains the information necessary to excel…

Collecting training images for all visual categories is not only expensive but also impractical. Zero-shot learning (ZSL), especially using attributes, offers a pragmatic solution to this problem. However, at test time most attribute-based…

Zero-shot learning (ZSL) can be defined by correctly solving a task where no training data is available, based on previous acquired knowledge from different, but related tasks. So far, this area has mostly drawn the attention from computer…

Automated road sign recognition is a critical task for intelligent transportation systems, but traditional deep learning methods struggle with the sheer number of sign classes and the impracticality of creating exhaustive labeled datasets.…

Most existing algorithms for cross-modal Information Retrieval are based on a supervised train-test setup, where a model learns to align the mode of the query (e.g., text) to the mode of the documents (e.g., images) from a given training…

Effective cross-modal retrieval is essential for applications like information retrieval and recommendation systems, particularly in specialized domains such as manufacturing, where product information often consists of visual samples…

We propose a novel zero-shot approach for keypoint detection on 3D shapes. Point-level reasoning on visual data is challenging as it requires precise localization capability, posing problems even for powerful models like DINO or CLIP.…

The pre-trained language model (eg, BERT) based deep retrieval models achieved superior performance over lexical retrieval models (eg, BM25) in many passage retrieval tasks. However, limited work has been done to generalize a deep retrieval…

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…

Stance detection is an important component of understanding hidden influences in everyday life. Since there are thousands of potential topics to take a stance on, most with little to no training data, we focus on zero-shot stance detection:…

Masked language models like BERT can perform text classification in a zero-shot fashion by reformulating downstream tasks as text infilling. However, this approach is highly sensitive to the template used to prompt the model, yet…

Log-based anomaly detection is an important task in ensuring the stability and reliability of software systems. One of the key problems in this task is the lack of labeled logs. Existing works usually leverage large-scale labeled logs from…

Large reasoning models exhibit long chain-of-thought reasoning with complex strategies such as backtracking and self-verification. Yet, these capabilities typically require resource-intensive post-training. We investigate whether such…