相关论文: Follow-Up Differential Descriptions: Language Mode…

Clearly explaining a rationale for a classification decision to an end-user can be as important as the decision itself. Existing approaches for deep visual recognition are generally opaque and do not output any justification text;…

Contrastive Language-Image Pretraining (CLIP) performs zero-shot image classification by mapping images and textual class representation into a shared embedding space, then retrieving the class closest to the image. This work provides a new…

Contrastive Language-Image Pre-training (CLIP) has recently shown great promise in pixel-level zero-shot learning tasks. However, existing approaches utilizing CLIP's text and patch embeddings to generate semantic masks often misidentify…

Focusing on discriminative zero-shot learning, in this work we introduce a novel mechanism that dynamically augments during training the set of seen classes to produce additional fictitious classes. These fictitious classes diminish the…

Image captioning aims at generating descriptive and meaningful textual descriptions of images, enabling a broad range of vision-language applications. Prior works have demonstrated that harnessing the power of Contrastive Image Language…

Few-shot segmentation remains challenging due to the limitations of its labeling information for unseen classes. Most previous approaches rely on extracting high-level feature maps from the frozen visual encoder to compute the pixel-wise…

In computer vision, Image Difference Captioning (IDC) is crucial for accurately describing variations between closely related images. Traditional IDC methods often rely on specialist models, which restrict their applicability across varied…

Clustering-based approach has proved effective in dealing with unsupervised domain adaptive person re-identification (ReID) tasks. However, existing works along this approach still suffer from noisy pseudo labels and the unreliable…

Audio-text models trained via contrastive learning offer a practical approach to perform audio classification through natural language prompts, such as "this is a sound of" followed by category names. In this work, we explore alternative…

Adapting vision-language models to remote sensing imagery presents a fundamental challenge: both the visual and linguistic distributions of satellite data lie far outside natural image pretraining corpora. Despite this, prompting remains…

We propose DiffCLIP, a novel vision-language model that extends the differential attention mechanism to CLIP architectures. Differential attention was originally developed for large language models to amplify relevant context while…

Self-supervised models trained with a contrastive loss such as CLIP have shown to be very powerful in zero-shot classification settings. However, to be used as a zero-shot classifier these models require the user to provide new captions…

This paper introduces a novel framework for zero-shot learning (ZSL), i.e., to recognize new categories that are unseen during training, by using a multi-model and multi-alignment integration method. Specifically, we propose three…

Few-shot segmentation has garnered significant attention. Many recent approaches attempt to introduce the Segment Anything Model (SAM) to handle this task. With the strong generalization ability and rich object-specific extraction ability…

In this study, we define and tackle zero shot "real" classification by description, a novel task that evaluates the ability of Vision-Language Models (VLMs) like CLIP to classify objects based solely on descriptive attributes, excluding…

There has been significant recent progress in training differentially private (DP) models which achieve accuracy that approaches the best non-private models. These DP models are typically pretrained on large public datasets and then…

We study the impact of using rich and diverse textual descriptions of classes for zero-shot learning (ZSL) on ImageNet. We create a new dataset ImageNet-Wiki that matches each ImageNet class to its corresponding Wikipedia article. We show…

Large-scale contrastive vision-language pre-trained models provide the zero-shot model achieving competitive performance across a range of image classification tasks without requiring training on downstream data. Recent works have confirmed…

Transfer learning enables the sharing of common knowledge among models for a variety of downstream tasks, but traditional methods suffer in limited training data settings and produce narrow models incapable of effectively generalizing under…

Spurious correlations are brittle associations between certain attributes of inputs and target variables, such as the correlation between an image background and an object class. Deep image classifiers often leverage them for predictions,…