Related papers: Generalizers: New Metaobjects for Generalized Disp…

Image style transfer occupies an important place in both computer graphics and computer vision. However, most current methods require reference to stylized images and cannot individually stylize specific objects. To overcome this…

Substantial efforts have been made on improving the generalization abilities of deep neural networks (DNNs) in order to obtain better performances without introducing more parameters. On the other hand, meta-learning approaches exhibit…

Existing domain adaptation (DA) and generalization (DG) methods in object detection enforce feature alignment in the visual space but face challenges like object appearance variability and scene complexity, which make it difficult to…

While a wide range of different, sometimes heterogeneous test coverage criteria have been proposed, there exists no generic formalism to describe them, and available test automation tools usually support only a small subset of them. We…

Human intelligence is characterized not only by the capacity to learn complex skills, but the ability to rapidly adapt and acquire new skills within an ever-changing environment. In this work we study how the learning of modular solutions…

Generalization in robotics is one of the most important problems. New generalization approaches use internet databases in order to solve new tasks. Modern search engines can return a large amount of information according to a query within…

We study object recognition under the constraint that each object class is only represented by very few observations. Semi-supervised learning, transfer learning, and few-shot recognition all concern with achieving fast generalization with…

Modern large language models (LLMs) are capable of interpreting input strings as instructions, or prompts, and carry out tasks based on them. Unlike traditional learners, LLMs cannot use back-propagation to obtain feedback, and condition…

Single Domain Generalization (SDG) tackles the problem of training a model on a single source domain so that it generalizes to any unseen target domain. While this has been well studied for image classification, the literature on SDG object…

This paper presents a new context-free parsing algorithm based on a bidirectional strictly horizontal strategy which incorporates strong top-down predictions (derivations and adjacencies). From a functional point of view, the parser is able…

The growing number of Earth observation satellites has led to increasingly diverse remote sensing data, with varying spatial, spectral, and temporal configurations. Most existing models rely on fixed input formats and modality-specific…

Multi-task learning promises better model generalization on a target task by jointly optimizing it with an auxiliary task. However, the current practice requires additional labeling efforts for the auxiliary task, while not guaranteeing…

Length Generalization is the essential capacity of autonomous agents to perform tasks in longer contexts than those encountered during training. To systematically study this feat, we test how well models can approximate the next token…

The rapid development of large language models (LLMs) has led to the widespread deployment of LLM agents across diverse industries, including customer service, content generation, data analysis, and even healthcare. However, as more LLM…

Large Language Models (LLMs) have achieved remarkable success across a wide range of natural language tasks, and recent efforts have sought to extend their capabilities to multimodal domains and resource-constrained environments. However,…

Extrapolation -- the ability to make inferences that go beyond the scope of one's experiences -- is a hallmark of human intelligence. By contrast, the generalization exhibited by contemporary neural network algorithms is largely limited to…

Conventional research attributes the improvements of generalization ability of deep neural networks either to powerful optimizers or the new network design. Different from them, in this paper, we aim to link the generalization ability of a…

Deep learning has led to a dramatic leap on Single Image Super-Resolution (SISR) performances in recent years. %Despite the substantial advancement% While most existing work assumes a simple and fixed degradation model (e.g., bicubic…

We introduce a simple method that employs pre-trained CLIP encoders to enhance model generalization in the ALFRED task. In contrast to previous literature where CLIP replaces the visual encoder, we suggest using CLIP as an additional module…

Anchoring is a recent, architecture-agnostic principle for training deep neural networks that has been shown to significantly improve uncertainty estimation, calibration, and extrapolation capabilities. In this paper, we systematically…