Related papers: Learning Deep Representations of Fine-grained Visu…

In this paper we consider a version of the zero-shot learning problem where seen class source and target domain data are provided. The goal during test-time is to accurately predict the class label of an unseen target domain instance based…

Modern image classification is based upon directly predicting classes via large discriminative networks, which do not directly contain information about the intuitive visual features that may constitute a classification decision. Recently,…

Fine-grained few-shot recognition often suffers from the problem of training data scarcity for novel categories.The network tends to overfit and does not generalize well to unseen classes due to insufficient training data. Many methods have…

Identifying subordinate-level categories from images is a longstanding task in computer vision and is referred to as fine-grained visual recognition (FGVR). It has tremendous significance in real-world applications since an average…

Deep learning, a branch of artificial intelligence, is a data-driven method that uses multiple layers of interconnected units or neurons to learn intricate patterns and representations directly from raw input data. Empowered by this…

Visual Semantic Embedding (VSE) models, which map images into a rich semantic embedding space, have been a milestone in object recognition and zero-shot learning. Current approaches to VSE heavily rely on static word em-bedding techniques.…

Compositional zero-shot learning (CZSL) aims to recognize novel compositions of attributes and objects learned from seen compositions. Previous works disentangle attributes and objects by extracting shared and exclusive parts between the…

Many aesthetic models in computer vision suffer from two shortcomings: 1) the low descriptiveness and interpretability of those hand-crafted aesthetic criteria (i.e., nonindicative of region-level aesthetics), and 2) the difficulty of…

Recognizing and disentangling visual attributes from objects is a foundation to many computer vision applications. While large vision language representations like CLIP had largely resolved the task of zero-shot object recognition,…

We present a novel latent embedding model for learning a compatibility function between image and class embeddings, in the context of zero-shot classification. The proposed method augments the state-of-the-art bilinear compatibility model…

Due to the importance of zero-shot learning, i.e. classifying images where there is a lack of labeled training data, the number of proposed approaches has recently increased steadily. We argue that it is time to take a step back and to…

There are many realistic applications of activity recognition where the set of potential activity descriptions is combinatorially large. This makes end-to-end supervised training of a recognition system impractical as no training set is…

We develop a novel compositional generative model for zero- and few-shot learning to recognize fine-grained classes with a few or no training samples. Our key observation is that generating holistic features for fine-grained classes fails…

Fine-grained visual recognition is to classify objects with visually similar appearances into subcategories, which has made great progress with the development of deep CNNs. However, handling subtle differences between different…

Disentangling the encodings of neural models is a fundamental aspect for improving interpretability, semantic control and downstream task performance in Natural Language Processing. Currently, most disentanglement methods are unsupervised…

Recent mask proposal models have significantly improved the performance of zero-shot semantic segmentation. However, the use of a `background' embedding during training in these methods is problematic as the resulting model tends to…

Modern recognition systems require large amounts of supervision to achieve accuracy. Adapting to new domains requires significant data from experts, which is onerous and can become too expensive. Zero-shot learning requires an annotated set…

Generalized zero-shot learning (GZSL) is a technique to train a deep learning model to identify unseen classes using the attribute. In this paper, we put forth a new GZSL technique that improves the GZSL classification performance greatly.…

Given a training dataset composed of images and corresponding category labels, deep convolutional neural networks show a strong ability in mining discriminative parts for image classification. However, deep convolutional neural networks…

Zero-shot classification is a promising paradigm to solve an applicable problem when the training classes and test classes are disjoint. Achieving this usually needs experts to externalize their domain knowledge by manually specifying a…