Related papers: HyCIR: Boosting Zero-Shot Composed Image Retrieval…
The objective of Content-Based Image Retrieval (CBIR) methods is essentially to extract, from large (image) databases, a specified number of images similar in visual and semantic content to a so-called query image. To bridge the semantic…
A fundamental challenge faced by existing Fine-Grained Sketch-Based Image Retrieval (FG-SBIR) models is the data scarcity -- model performances are largely bottlenecked by the lack of sketch-photo pairs. Whilst the number of photos can be…
In the blind single image super-resolution (SISR) task, existing works have been successful in restoring image-level unknown degradations. However, when a single video frame becomes the input, these works usually fail to address…
Sketch-based image retrieval (SBIR) relies on free-hand sketches to retrieve natural photos within the same class. However, its practical application is limited by its inability to retrieve classes absent from the training set. To address…
Traditional computer vision models are trained to predict a fixed set of predefined categories. Recently, natural language has been shown to be a broader and richer source of supervision that provides finer descriptions to visual concepts…
Image-Text Retrieval (ITR) is challenging in bridging visual and lingual modalities. Contrastive learning has been adopted by most prior arts. Except for limited amount of negative image-text pairs, the capability of constrastive learning…
Content-Based Image Retrieval (CBIR) locates, retrieves and displays images alike to one given as a query, using a set of features. It demands accessible data in medical archives and from medical equipment, to infer meaning after some…
Image classification, which classifies images by pre-defined categories, has been the dominant approach to visual representation learning over the last decade. Visual learning through image-text alignment, however, has emerged to show…
Composed Image Retrieval (CIR) enables image retrieval by combining multiple query modalities, but existing benchmarks predominantly focus on general-domain imagery and rely on reference images with short textual modifications. As a result,…
The task of single image super-resolution (SISR) aims at reconstructing a high-resolution (HR) image from a low-resolution (LR) image. Although significant progress has been made by deep learning models, they are trained on synthetic paired…
Vision-language models, such as CLIP, have shown impressive generalization capacities when using appropriate text descriptions. While optimizing prompts on downstream labeled data has proven effective in improving performance, these methods…
Zero-shot learning (ZSL) aims to recognize unseen classes by leveraging semantic information from seen classes, but most existing methods assume accurate class labels for training instances. However, in real-world scenarios, noise and…
Despite significant progress toward super resolving more realistic images by deeper convolutional neural networks (CNNs), reconstructing fine and natural textures still remains a challenging problem. Recent works on single image super…
In this paper, we introduce an approach to overcome the low accuracy of the Content-Based Image Retrieval (CBIR) (when using the global features). To increase the accuracy, we use Harris-Laplace detector to identify the interest regions of…
Although large language models can be prompted for both zero- and few-shot learning, performance drops significantly when no demonstrations are available. In this paper, we introduce Z-ICL, a new zero-shot method that closes the gap by…
We address the challenges inherent in sketch-based image retrieval (SBIR) across various settings, including zero-shot SBIR, generalized zero-shot SBIR, and fine-grained zero-shot SBIR, by leveraging the vision-language foundation model…
Composed image retrieval searches for a target image based on a multi-modal user query comprised of a reference image and modification text describing the desired changes. Existing approaches to solving this challenging task learn a mapping…
Traditional Information Retrieval (IR) research has focussed on a single user interaction modality, where a user searches to satisfy an information need. Recent advances in web technologies and computer hardware have enabled multiple users…
3D reconstruction of high-resolution target remains a challenge task due to the large memory required from the large input image size. Recently developed learning based algorithms provide promising reconstruction performance than…
Zero-shot detection (ZSD), i.e., detection on classes not seen during training, is essential for real world detection use-cases, but remains a difficult task. Recent research attempts ZSD with detection models that output embeddings instead…