Geometric Generalization Based Zero-Shot Learning Dataset Infinite World: Simple Yet Powerful

2018-07-10 · Rajesh Chidambaram, Michael Kampffmeyer, Willie Neiswanger, Xiaodan Liang, Thomas Lachmann, Eric Xing

Raven's Progressive Matrices are one of the widely used tests in evaluating the human test taker's fluid intelligence. Analogously, this paper introduces geometric generalization based zero-shot learning tests to measure the rapid learning ability and the internal consistency of deep generative models. Our empirical research analysis on state-of-the-art generative models discern their ability to generalize concepts across classes. In the process, we introduce Infinite World, an evaluable, scalable, multi-modal, light-weight dataset and Zero-Shot Intelligence Metric ZSI. The proposed tests condenses human-level spatial and numerical reasoning tasks to its simplistic geometric forms. The dataset is scalable to a theoretical limit of infinity, in numerical features of the generated geometric figures, image size and in quantity. We systematically analyze state-of-the-art model's internal consistency, identify their bottlenecks and propose a pro-active optimization method for few-shot and zero-shot learning.

📄 PDF Abstract BibTeX arXiv:1807.03711

Code (0)

등록된 구현이 없습니다.

Tasks

Zero-Shot Learning

Unifying Few- and Zero-Shot Egocentric Action Recognition

2020-05-27 · Scott Tyler R., Shvartsman Michael, Ridgeway Karl

Although there has been significant research in egocentric action recognition, most methods and tasks, including EPIC-KITCHENS, suppose a fixed set of action classes. Fixed-set classification is useful for benchmarking m…

Action Recognition Benchmarking Classification General Classification+5

Text-guided Synthetic Geometric Augmentation for Zero-shot 3D Understanding

2025-01-16 · Kohei Torimi, Ryosuke Yamada, Daichi Otsuka, Kensho Hara 외

Zero-shot recognition models require extensive training data for generalization. However, in zero-shot 3D classification, collecting 3D data and captions is costly and laborintensive, posing a significant barrier compare…

3D Classification Zero-shot 3D classification Zero-Shot Learning

Difference Vector Equalization for Robust Fine-tuning of Vision-Language Models

2025-11-13 · Satoshi Suzuki, Shin'ya Yamaguchi, Shoichiro Takeda, Taiga Yamane 외 arxiv

Contrastive pre-trained vision-language models, such as CLIP, demonstrate strong generalization abilities in zero-shot classification by leveraging embeddings extracted from image and text encoders. This paper aims to ro…

Contrastive Learning

Zero-shot Generalizable Graph Anomaly Detection with Mixture of Riemannian Experts

2026-02-06 · Xinyu Zhao, Qingyun Sun, Jiayi Luo, Xingcheng Fu 외 arxiv

Graph Anomaly Detection (GAD) aims to identify irregular patterns in graph data, and recent works have explored zero-shot generalist GAD to enable generalization to unseen graph datasets. However, existing zero-shot GAD …

Graph Anomaly Detection Domain Generalization

LM-Infinite: Zero-Shot Extreme Length Generalization for Large Language Models

2023-08-30 · Chi Han, Qifan Wang, Hao Peng, Wenhan Xiong 외

Today's large language models (LLMs) typically train on short text segments (e.g., <4K tokens) due to the quadratic complexity of their Transformer architectures. As a result, their performance suffers drastically on inp…

2k 4k Articles Text Generation