Related papers: Visual Zero-Shot E-Commerce Product Attribute Valu…
New categories can be discovered by transforming semantic features into synthesized visual features without corresponding training samples in zero-shot image classification. Although significant progress has been made in generating…
Transductive zero-shot learning with vision-language models leverages image-image similarities within the dataset to achieve better classification accuracy compared to the inductive setting. However, there is little work that explores the…
Multimodal pre-trained models, such as CLIP, are popular for zero-shot classification due to their open-vocabulary flexibility and high performance. However, vision-language models, which compute similarity scores between images and class…
Object proposal generation is an important and fundamental task in computer vision. In this paper, we propose ProposalCLIP, a method towards unsupervised open-category object proposal generation. Unlike previous works which require a large…
Recently, zero-shot anomaly detection (ZSAD) has emerged as a pivotal paradigm for industrial inspection and medical diagnostics, detecting defects in novel objects without requiring any target-dataset samples during training. Existing…
Compositional zero-shot learning (CZSL) aims to learn the concepts of attributes and objects in seen compositions and to recognize their unseen compositions. Most Contrastive Language-Image Pre-training (CLIP)-based CZSL methods focus on…
Our objective is the automatic generation of Audio Descriptions (ADs) for edited video material, such as movies and TV series. To achieve this, we propose a two-stage framework that leverages "shots" as the fundamental units of video…
Generalized Zero-shot Semantic Segmentation aims to segment both seen and unseen categories only under the supervision of the seen ones. To tackle this, existing methods adopt the large-scale Vision Language Models (VLMs) which obtain…
Vision-language pre-training methods, e.g., CLIP, demonstrate an impressive zero-shot performance on visual categorizations with the class proxy from the text embedding of the class name. However, the modality gap between the text and…
We study the problem of compositional zero-shot learning for object-attribute recognition. Prior works use visual features extracted with a backbone network, pre-trained for object classification and thus do not capture the subtly distinct…
Zero-shot anomaly detection (ZSAD) identifies anomalies without needing training samples from the target dataset, essential for scenarios with privacy concerns or limited data. Vision-language models like CLIP show potential in ZSAD but…
In this paper, we propose a new setting for generating product descriptions from images, augmented by marketing keywords. It leverages the combined power of visual and textual information to create descriptions that are more tailored to the…
Same-style products retrieval plays an important role in e-commerce platforms, aiming to identify the same products which may have different text descriptions or images. It can be used for similar products retrieval from different suppliers…
The emergence of CLIP has opened the way for open-world image perception. The zero-shot classification capabilities of the model are impressive but are harder to use for dense tasks such as image segmentation. Several methods have proposed…
Visual anomaly detection has been widely used in industrial inspection and medical diagnosis. Existing methods typically demand substantial training samples, limiting their utility in zero-/few-shot scenarios. While recent efforts have…
Zero-shot anomaly detection (ZSAD) requires detection models trained using auxiliary data to detect anomalies without any training sample in a target dataset. It is a crucial task when training data is not accessible due to various…
Recently, pre-trained vision-language models have been increasingly used to tackle the challenging zero-shot segmentation task. Typical solutions follow the paradigm of first generating mask proposals and then adopting CLIP to classify…
State-of-the-art methods for zero-shot visual recognition formulate learning as a joint embedding problem of images and side information. In these formulations the current best complement to visual features are attributes: manually encoded…
Generalized zero-shot learning (GZSL) is a technique to train a deep learning model to identify unseen classes using the image attribute. In this paper, we put forth a new GZSL approach exploiting Vision Transformer (ViT) to maximize the…
Recent approaches have shown that training deep neural networks directly on large-scale image-text pair collections enables zero-shot transfer on various recognition tasks. One central issue is how this can be generalized to object…