相关论文: Geometric Generalization Based Zero-Shot Learning …

Global average pooling (GAP) is a popular component in deep metric learning (DML) for aggregating features. Its effectiveness is often attributed to treating each feature vector as a distinct semantic entity and GAP as a combination of…

Extreme-mass-ratio-inspiral observations from future space-based gravitational-wave detectors such as LISA will enable strong-field tests of general relativity with unprecedented precision, but at prohibitive computational cost if existing…

Zero-shot learning (ZSL) aims to recognize objects from novel unseen classes without any training data. Recently, structure-transfer based methods are proposed to implement ZSL by transferring structural knowledge from the semantic…

Can the latent spaces of modern generative neural rendering models serve as representations for 3D-aware discriminative visual understanding tasks? We use retrieval as a proxy for measuring the metric learning properties of the latent…

Highly Autonomous Driving (HAD) systems rely on deep neural networks for the visual perception of the driving environment. Such networks are trained on large manually annotated databases. In this work, a semi-parametric approach to one-shot…

Zero-shot quantization is a promising approach for developing lightweight deep neural networks when data is inaccessible owing to various reasons, including cost and issues related to privacy. By exploiting the learned parameters ($\mu$ and…

We propose a zero-shot approach to image harmonization, aiming to overcome the reliance on large amounts of synthetic composite images in existing methods. These methods, while showing promising results, involve significant training…

Zero-shot inference is a powerful paradigm that enables the use of large pretrained models for downstream classification tasks without further training. However, these models are vulnerable to inherited biases that can impact their…

3D reconstruction from a single image is a long-standing problem in computer vision. Learning-based methods address its inherent scale ambiguity by leveraging increasingly large labeled and unlabeled datasets, to produce geometric priors…

We derive a novel information-theoretic analysis of the generalization property of meta-learning algorithms. Concretely, our analysis proposes a generic understanding of both the conventional learning-to-learn framework and the modern…

Raven's Progressive Matrices (RPMs) is an established benchmark to examine the ability to perform high-level abstract visual reasoning (AVR). Despite the current success of algorithms that solve this task, humans can generalize beyond a…

Humans have the capability, aided by the expressive compositionality of their language, to learn quickly by demonstration. They are able to describe unseen task-performing procedures and generalize their execution to other contexts. In this…

Raven's Progressive Matrices is a family of classical intelligence tests that have been widely used in both research and clinical settings. There have been many exciting efforts in AI communities to computationally model various aspects of…

The recent advance in deep generative models outlines a promising perspective in the realm of Zero-Shot Learning (ZSL). Most generative ZSL methods use category semantic attributes plus a Gaussian noise to generate visual features. After…

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…

A world model is an internal model that simulates how the world evolves. Given past observations and actions, it predicts the future physical state of both the embodied agent and its environment. Accurate world models are essential for…

We study universal zero-shot segmentation in this work to achieve panoptic, instance, and semantic segmentation for novel categories without any training samples. Such zero-shot segmentation ability relies on inter-class relationships in…

We present a generic and flexible Reinforcement Learning (RL) based meta-learning framework for the problem of few-shot learning. During training, it learns the best optimization algorithm to produce a learner (ranker/classifier, etc) by…

Exploiting symmetry inherent in data can significantly improve the sample efficiency of a learning procedure and the generalization of learned models. When data clearly reveals underlying symmetry, leveraging this symmetry can naturally…

World models have recently emerged as a promising approach to reinforcement learning (RL), achieving state-of-the-art performance across a wide range of visual control tasks. This work aims to obtain a deep understanding of the robustness…