Related papers: A causal view of compositional zero-shot recogniti…
Zero-shot learning (ZSL) is a framework to classify images belonging to unseen classes based on solely semantic information about these unseen classes. In this paper, we propose a new ZSL algorithm using coupled dictionary learning. The…
Few-shot learning (FSL) aims at recognizing novel classes given only few training samples, which still remains a great challenge for deep learning. However, humans can easily recognize novel classes with only few samples. A key component of…
The existing zero-shot detection approaches project visual features to the semantic domain for seen objects, hoping to map unseen objects to their corresponding semantics during inference. However, since the unseen objects are never…
From the beginning of zero-shot learning research, visual attributes have been shown to play an important role. In order to better transfer attribute-based knowledge from known to unknown classes, we argue that an image representation with…
Intelligent systems possess a crucial characteristic of breaking complicated problems into smaller reusable components or parts and adjusting to new tasks using these part representations. However, current part-learners encounter…
Compositional generalization refers to correctly interpret novel combinations of known primitives, which remains a major challenge. Existing approaches often rely on supervised fine-tuning, which encourages models to imitate target outputs.…
Zero-shot action recognition requires a strong ability to generalize from pre-training and seen classes to novel unseen classes. Similarly, continual learning aims to develop models that can generalize effectively and learn new tasks…
A common problem with most zero and few-shot learning approaches is they suffer from bias towards seen classes resulting in sub-optimal performance. Existing efforts aim to utilize unlabeled images from unseen classes (i.e transductive…
Collecting training images for all visual categories is not only expensive but also impractical. Zero-shot learning (ZSL), especially using attributes, offers a pragmatic solution to this problem. However, at test time most attribute-based…
Zero-shot learning (ZSL) which aims to recognize unseen object classes by only training on seen object classes, has increasingly been of great interest in Machine Learning, and has registered with some successes. Most existing ZSL methods…
Zero-shot learning (ZSL) aims at understanding unseen categories with no training examples from class-level descriptions. To improve the discriminative power of zero-shot learning, we model the visual learning process of unseen categories…
Machine learning models rely on various assumptions to attain high accuracy. One of the preliminary assumptions of these models is the independent and identical distribution, which suggests that the train and test data are sampled from the…
In the domain generalization literature, a common objective is to learn representations independent of the domain after conditioning on the class label. We show that this objective is not sufficient: there exist counter-examples where a…
Zero-shot learning is a learning regime that recognizes unseen classes by generalizing the visual-semantic relationship learned from the seen classes. To obtain an effective ZSL model, one may resort to curating training samples from…
We propose a novel approach to improve a visual-semantic embedding model by incorporating concept representations captured from an external structured knowledge base. We investigate its performance on image classification under both…
In this paper, we address zero-shot learning (ZSL), the problem of recognizing categories for which no labeled visual data are available during training. We focus on the transductive setting, in which unlabelled visual data from unseen…
The impressive performance of deep convolutional neural networks in single-view 3D reconstruction suggests that these models perform non-trivial reasoning about the 3D structure of the output space. Recent work has challenged this belief,…
We study domain-adaptive image synthesis, the problem of teaching pretrained image generative models a new style or concept from as few as one image to synthesize novel images, to better understand the compositional image synthesis. We…
This paper studies visual search using structured queries. The structure is in the form of a 2D composition that encodes the position and the category of the objects. The transformation of the position and the category of the objects leads…
The ability to learn new visual concepts from limited examples is a hallmark of human cognition. While traditional category learning models represent each example as an unstructured feature vector, compositional concept learning is thought…