Related papers: Binary Verification for Zero-Shot Vision

Referring Expression Comprehension (REC) is usually addressed with task-trained grounding models. We show that a zero-shot workflow, without any REC-specific training, can achieve competitive or superior performance. Our approach…

Human-in-the-loop data analysis applications necessitate greater transparency in machine learning models for experts to understand and trust their decisions. To this end, we propose a visual analytics workflow to help data scientists and…

Classification methods for binary (yes/no) tasks often produce a continuously valued score. Machine learning practitioners must perform model selection, calibration, discretization, performance assessment, tuning, and fairness assessment.…

Query expansion, pivotal in search engines, enhances the representation of user information needs with additional terms. While existing methods expand queries using retrieved or generated contextual documents, each approach has notable…

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…

The claim matching (CM) task can benefit an automated fact-checking pipeline by putting together claims that can be resolved with the same fact-check. In this work, we are the first to explore zero-shot and few-shot learning approaches to…

Visual question answering (VQA) has traditionally been treated as a single-step task where each question receives the same amount of effort, unlike natural human question-answering strategies. We explore a question decomposition strategy…

In the retrieval domain, candidates' fusion from heterogeneous retrievers is a long-standing challenge, particularly for complex, multi-modal data such as videos. While typical fusion techniques are training-free, they rely solely on rank…

Visual search offers an intuitive way for customers to explore diverse product catalogs, particularly in consumer-to-consumer (C2C) marketplaces where listings are often unstructured and visually driven. This paper presents a scalable…

Binary authorship analysis is a significant problem in many software engineering applications. In this paper, we formulate a binary authorship verification task to accurately reflect the real-world working process of software forensic…

Reinforcement learning with verifiable rewards (RLVR) has enabled large language models (LLMs) to achieve remarkable breakthroughs in reasoning tasks with objective ground-truth answers, such as mathematics and code generation. However, a…

Part of the appeal of Visual Question Answering (VQA) is its promise to answer new questions about previously unseen images. Most current methods demand training questions that illustrate every possible concept, and will therefore never…

Vision-language tasks, such as VQA, SNLI-VE, and VCR are challenging because they require the model's reasoning ability to understand the semantics of the visual world and natural language. Supervised methods working for vision-language…

We consider the problem of zero-shot one-class visual classification, extending traditional one-class classification to scenarios where only the label of the target class is available. This method aims to discriminate between positive and…

Machine Learning (ML) techniques for image classification routinely require many labelled images for training the model and while testing, we ought to use images belonging to the same domain as those used for training. In this paper, we…

Zero-shot Visual Question Answering (VQA) is a prominent vision-language task that examines both the visual and textual understanding capability of systems in the absence of training data. Recently, by converting the images into captions,…

Zero-shot reinforcement learning (RL) has emerged as a setting for developing general agents, capable of solving downstream tasks without additional training or planning at test-time. While conventional RL optimizes policies for fixed…

Large-scale pre-trained models (PTMs) show great zero-shot capabilities. In this paper, we study how to leverage them for zero-shot visual question answering (VQA). Our approach is motivated by a few observations. First, VQA questions often…

Composed image retrieval, multi-turn composed image retrieval, and composed video retrieval all share a common paradigm: composing the reference visual with modification text to retrieve the desired target. Despite this shared structure,…

Video question answering (VideoQA) is a complex task that requires diverse multi-modal data for training. Manual annotation of question and answers for videos, however, is tedious and prohibits scalability. To tackle this problem, recent…