相关论文: Three ways to improve feature alignment for open v…

In recent years, vision-language models have made significant strides, excelling in tasks like optical character recognition and geometric problem-solving. However, several critical issues remain: 1) Proprietary models often lack…

Vision-language models enable open-world classification of objects without the need for any retraining. While this zero-shot paradigm marks a significant advance, even today's best models exhibit skewed performance when objects are…

Accurate and stable feature matching is critical for computer vision tasks, particularly in applications such as Simultaneous Localization and Mapping (SLAM). While recent learning-based feature matching methods have demonstrated promising…

Leveraging class semantic descriptions and examples of known objects, zero-shot learning makes it possible to train a recognition model for an object class whose examples are not available. In this paper, we propose a novel zero-shot…

Large-scale pre-trained models have demonstrated impressive performance in vision and language tasks within open-world scenarios. Due to the lack of comparable pre-trained models for 3D shapes, recent methods utilize language-image…

Information retrieval across different languages is an increasingly important challenge in natural language processing. Recent approaches based on multilingual pre-trained language models have achieved remarkable success, yet they often…

Zero-shot learning (ZSL) aims to recognize unseen classes without labeled training examples by leveraging class-level semantic descriptors such as attributes. A fundamental challenge in ZSL is semantic misalignment, where semantic-unrelated…

Conventional object detection models require large amounts of training data. In comparison, humans can recognize previously unseen objects by merely knowing their semantic description. To mimic similar behaviour, zero-shot object detection…

Few-shot learning aims to recognize instances from novel classes with few labeled samples, which has great value in research and application. Although there has been a lot of work in this area recently, most of the existing work is based on…

Automatic image anomaly detection is important for quality inspection in the manufacturing industry. The usual unsupervised anomaly detection approach is to train a model for each object class using a dataset of normal samples. However, a…

Open-vocabulary object detection aims to recognize objects from an open set of categories, which leverages vision-language models (VLMs) pre-trained on large-scale image-text data. The cooperative paradigm combines an object detector with a…

In this paper, we study the problem of zero-shot sketch-based image retrieval (ZS-SBIR). The prior methods tackle the problem in a two-modality setting with only category labels or even no textual information involved. However, the growing…

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…

Language models can be viewed as functions that embed text into Euclidean space, where the quality of the embedding vectors directly determines model performance, training such neural networks involves various uncertainties. This paper…

Vision-language foundation models such as CLIP have shown impressive zero-shot performance on many tasks and datasets, especially thanks to their free-text inputs. However, they struggle to handle some downstream tasks, such as fine-grained…

Recent studies have shown remarkable success in unsupervised image-to-image translation. However, if there has no access to enough images in target classes, learning a mapping from source classes to the target classes always suffers from…

Domain gaps between training data (source) and real-world environments (target) often degrade the performance of object detection models. Most existing methods aim to bridge this gap by aligning features across source and target domains but…

Semantic Image Interpretation is the task of extracting a structured semantic description from images. This requires the detection of visual relationships: triples (subject,relation,object) describing a semantic relation between a subject…

Recently, vision-language models like CLIP have advanced the state of the art in a variety of multi-modal tasks including image captioning and caption evaluation. Many approaches leverage CLIP for cross-modal retrieval to condition…

Feature selection, an effective technique for dimensionality reduction, plays an important role in many machine learning systems. Supervised knowledge can significantly improve the performance. However, faced with the rapid growth of newly…