Related papers: Diverse and Tailored Image Generation for Zero-sho…

In this work, we investigate the problem of Model-Agnostic Zero-Shot Classification (MA-ZSC), which refers to training non-specific classification architectures (downstream models) to classify real images without using any real images…

Preparing training data for deep vision models is a labor-intensive task. To address this, generative models have emerged as an effective solution for generating synthetic data. While current generative models produce image-level category…

Zero-shot 3D object classification is crucial for real-world applications like autonomous driving, however it is often hindered by a significant domain gap between the synthetic data used for training and the sparse, noisy LiDAR scans…

Generative Models are a valuable tool for the controlled creation of high-quality image data. Controlled diffusion models like the ControlNet have allowed the creation of labeled distributions. Such synthetic datasets can augment the…

Recently, large-scale visual language pre-trained (VLP) models have demonstrated impressive performance across various downstream tasks. Motivated by these advancements, pioneering efforts have emerged in multi-label image recognition with…

Recent advancements in text-to-image generation models have dramatically enhanced the generation of photorealistic images from textual prompts, leading to an increased interest in personalized text-to-image applications, particularly in…

In this paper, we propose a novel deep learning architecture for multi-label zero-shot learning (ML-ZSL), which is able to predict multiple unseen class labels for each input instance. Inspired by the way humans utilize semantic knowledge…

We present a deep generative model for learning to predict classes not seen at training time. Unlike most existing methods for this problem, that represent each class as a point (via a semantic embedding), we represent each seen/unseen…

Recognizing objects from sparse and noisy events becomes extremely difficult when paired images and category labels do not exist. In this paper, we study label-free event-based object recognition where category labels and paired images are…

Multi-modal learning has become increasingly popular due to its ability to leverage information from different data sources (e.g., text and images) to improve the model performance. Recently, CLIP has emerged as an effective approach that…

Zero-shot text classifiers based on label descriptions embed an input text and a set of labels into the same space: measures such as cosine similarity can then be used to select the most similar label description to the input text as the…

We propose a new approach, Synthetic Optimized Layout with Instance Detection (SOLID), to pretrain object detectors with synthetic images. Our "SOLID" approach consists of two main components: (1) generating synthetic images using a…

To overcome the absence of training data for unseen classes, conventional zero-shot learning approaches mainly train their model on seen datapoints and leverage the semantic descriptions for both seen and unseen classes. Beyond exploiting…

Vision-language pre-training such as CLIP enables zero-shot transfer that can classify images according to the candidate class names. While CLIP demonstrates an impressive zero-shot performance on diverse downstream tasks, the distribution…

Fine-grained image classification, which aims to distinguish images with subtle distinctions, is a challenging task due to two main issues: lack of sufficient training data for every class and difficulty in learning discriminative features…

Addressing multi-label action recognition in videos represents a significant challenge for robotic applications in dynamic environments, especially when the robot is required to cooperate with humans in tasks that involve objects. Existing…

Robust object recognition systems usually rely on powerful feature extraction mechanisms from a large number of real images. However, in many realistic applications, collecting sufficient images for ever-growing new classes is unattainable.…

Multi-modal image-text models such as CLIP and LiT have demonstrated impressive performance on image classification benchmarks and their zero-shot generalization ability is particularly exciting. While the top-5 zero-shot accuracies of…

Recently, large-scale pre-trained Vision and Language (VL) models have set a new state-of-the-art (SOTA) in zero-shot visual classification enabling open-vocabulary recognition of potentially unlimited set of categories defined as simple…

Adopting contrastive image-text pretrained models like CLIP towards video classification has gained attention due to its cost-effectiveness and competitive performance. However, recent works in this area face a trade-off. Finetuning the…