Related papers: Towards Zero-Shot Camera Trap Image Categorization

The contemporary phenomenon of deepfakes, utilizing GAN or diffusion models for face swapping, presents a substantial and evolving threat in digital media, identity verification, and a multitude of other systems. The majority of existing…

Object recognition systems usually require fully complete manually labeled training data to train the classifier. In this paper, we study the problem of object recognition where the training samples are missing during the classifier…

Open-world object detection, as a more general and challenging goal, aims to recognize and localize objects described by arbitrary category names. The recent work GLIP formulates this problem as a grounding problem by concatenating all…

This paper considers zero-shot Anomaly Detection (AD), performing AD without reference images of the test objects. We propose a framework called CLIP-AD to leverage the zero-shot capabilities of the large vision-language model CLIP.…

Few-shot object detection, which focuses on detecting novel objects with few labels, is an emerging challenge in the community. Recent studies show that adapting a pre-trained model or modified loss function can improve performance. In this…

Few-shot image classification is a challenging task in the field of machine learning, involving the identification of new categories using a limited number of labeled samples. In recent years, methods based on local descriptors have made…

Hashing algorithms have been widely used in large-scale image retrieval tasks, especially for seen class data. Zero-shot hashing algorithms have been proposed to handle unseen class data. The key technique in these algorithms involves…

The recent advances in representation learning inspire us to take on the challenging problem of unsupervised image classification tasks in a principled way. We propose ContraCluster, an unsupervised image classification method that combines…

In Composed Image Retrieval (CIR), a user combines a query image with text to describe their intended target. Existing methods rely on supervised learning of CIR models using labeled triplets consisting of the query image, text…

Zero-shot video captioning requires that a model generate high-quality captions without human-annotated video-text pairs for training. State-of-the-art approaches to the problem leverage CLIP to extract visual-relevant textual prompts to…

We address the challenge of building task-agnostic classifiers using only text descriptions, demonstrating a unified approach to image classification, 3D point cloud classification, and action recognition from scenes. Unlike approaches that…

The rapid advancement of generative models, particularly diffusion-based methods, has significantly improved the realism of synthetic images. As new generative models continuously emerge, detecting generated images remains a critical…

Contemporary deep learning techniques have made image recognition a reasonably reliable technology. However training effective photo classifiers typically takes numerous examples which limits image recognition's scalability and…

Zero-shot inference, where pre-trained models perform tasks without specific training data, is an exciting emergent ability of large models like CLIP. Although there has been considerable exploration into enhancing zero-shot abilities in…

Few-shot or one-shot learning of classifiers requires a significant inductive bias towards the type of task to be learned. One way to acquire this is by meta-learning on tasks similar to the target task. In this paper, we propose UMTRA, an…

This report introduces a solution to the Topic 1 Zero-shot Image Captioning of 2024 NICE : New frontiers for zero-shot Image Captioning Evaluation. In contrast to NICE 2023 datasets, this challenge involves new annotations by humans with…

Photo search, the task of retrieving images based on textual queries, has witnessed significant advancements with the introduction of CLIP (Contrastive Language-Image Pretraining) model. CLIP leverages a vision-language pre training…

Accurate characterization of carbon nanotube morphologies in electron microscopy images is vital for exposure assessment and toxicological studies, yet current workflows rely on slow, subjective manual segmentation. This work presents a…

The goal of few-shot classification is to classify new categories with few labeled examples within each class. Nowadays, the excellent performance in handling few-shot classification problems is shown by metric-based meta-learning methods.…

While multimodal contrastive learning methods (e.g., CLIP) can achieve impressive zero-shot classification performance, recent research has revealed that these methods are vulnerable to backdoor attacks. To defend against backdoor attacks…