paper-with-me

홈 › Papers

A Closer Look at Generalisation in RAVEN

2020-08-01 · ECCV 2020 8 · Steven Spratley, Krista Ehinger, Tim Miller

Humans have a remarkable capacity to draw parallels between concepts, generalising their experience to new domains. This skill is essential to solving the visual problems featured in the RAVEN and PGM datasets, yet, previous papers have scarcely tested how well models generalise across tasks. Additionally, we encounter a critical issue that allows existing models to inadvertently 'cheat' problems in RAVEN. We therefore propose a simple workaround to resolve this issue, and focus the conversation on generalisation performance, as this was severely affected in the process. We revise the existing evaluation, and introduce two relational models, Rel-Base and Rel-AIR, that significantly improve this performance. To our knowledge, Rel-AIR is the first method to employ unsupervised scene decomposition in solving abstract visual reasoning problems, and along with Rel-Base, sets states-of-the-art for image-only reasoning and generalisation across both RAVEN and PGM.

📄 PDF Abstract BibTeX

Code (1)

SvenShade/Rel-AIR 공식 구현 pytorch

Tasks

Visual Reasoning

Methods 이 논문이 사용한 방법론

PGM A regularization criterion that, differently from dropout and its variants, is deterministic rather than random. It grounds on the…

Similar Papers 제목 키워드 기반

Are nuclear masks all you need for improved out-of-domain generalisation? A closer look at cancer classification in histopathology

2024-11-14 · Dhananjay Tomar, Alexander Binder, Andreas Kleppe

Domain generalisation in computational histopathology is challenging because the images are substantially affected by differences among hospitals due to factors like fixation and staining of tissue and imaging equipment.…

AllCancer ClassificationData AugmentationNuclear Segmentation

RAVEN: A Regime-Aware Variable-context Expert Network for Financial Time Series Forecasting

2026-06-23 · Cheng He, Zhenyu Guan, Xijie Liang, Defu Lian 외 arxiv

Financial time series forecasting presents structural challenges absent from standard benchmarks. Log-returns are non-stationary, exhibit exceptionally low signal-to-noise (SNR) ratios, and are governed by regime-depende…

Time Series Forecasting

Blackbird's language matrices (BLMs): a new benchmark to investigate disentangled generalisation in neural networks

2022-05-22 · Paola Merlo, Aixiu An, Maria A. Rodriguez

Current successes of machine learning architectures are based on computationally expensive algorithms and prohibitively large amounts of data. We need to develop tasks and data to train networks to reach more complex and…

A-I-RAVEN and I-RAVEN-Mesh: Two New Benchmarks for Abstract Visual Reasoning

2024-06-16 · Mikołaj Małkiński, Jacek Mańdziuk

We study generalization and knowledge reuse capabilities of deep neural networks in the domain of abstract visual reasoning (AVR), employing Raven's Progressive Matrices (RPMs), a recognized benchmark task for assessing …

Transfer LearningVisual Reasoning

Functional Specification of the RAVENS Neuroprocessor

2023-07-27 · Adam Z. Foshie, James S. Plank, Garrett S. Rose, Catherine D. Schuman

RAVENS is a neuroprocessor that has been developed by the TENNLab research group at the University of Tennessee. Its main focus has been as a vehicle for chip design with memristive elements; however it has also been the…