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

• URL: http://arxiv.org/abs/2406.11061v2
• Date: Fri, 16 May 2025 12:01:46 GMT
• Title: A-I-RAVEN and I-RAVEN-Mesh: Two New Benchmarks for Abstract Visual Reasoning
• Authors: Mikołaj Małkiński, Jacek Mańdziuk,
• Abstract summary: We study generalization and knowledge reuse capabilities of deep neural networks in the domain of abstract visual reasoning.<n>We introduce Attributeless-I-RAVEN (A-I-RAVEN), a benchmark with 10 generalization regimes that allow to test generalization of abstract rules applied to held-out attributes.<n>We construct I-RAVEN-Mesh, a dataset that enriches RPMs with a novel component structure comprising line-based patterns.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 AVR abilities. Two knowledge transfer scenarios referring to the I-RAVEN dataset are investigated. Firstly, inspired by generalization assessment capabilities of the PGM dataset and popularity of I-RAVEN, we introduce Attributeless-I-RAVEN (A-I-RAVEN), a benchmark with 10 generalization regimes that allow to systematically test generalization of abstract rules applied to held-out attributes at various levels of complexity (primary and extended regimes). In contrast to PGM, A-I-RAVEN features compositionality, a variety of figure configurations, and does not require substantial computational resources. Secondly, we construct I-RAVEN-Mesh, a dataset that enriches RPMs with a novel component structure comprising line-based patterns, facilitating assessment of progressive knowledge acquisition in transfer learning setting. We evaluate 13 strong models from the AVR literature on the introduced datasets, revealing their specific shortcomings in generalization and knowledge transfer.

Related papers

• Advancing Generalization Across a Variety of Abstract Visual Reasoning Tasks [0.0]
  We present the Pathways of Normalized Group Convolution model (PoNG)<n>PoNG is a novel neural architecture that features group convolution, normalization, and a parallel design.<n>Experiments demonstrate strong capabilities of the proposed model, which in several settings outperforms the existing literature methods.
  arXiv  Detail & Related papers  (2025-05-19T17:32:07Z)
• FORCE: Feature-Oriented Representation with Clustering and Explanation [0.0]
  We propose a SHAP based supervised deep learning framework FORCE. It relies on two-stage usage of SHAP values in the neural network architecture. We show that FORCE led to dramatic improvements in overall performance as compared to networks that did not incorporate the latent feature and attention framework.
  arXiv  Detail & Related papers  (2025-04-07T22:05:50Z)
• Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains [92.36624674516553]
  Reinforcement learning with verifiable rewards (RLVR) has demonstrated significant success in enhancing mathematical reasoning and coding performance of large language models (LLMs) We investigate the effectiveness and scalability of RLVR across diverse real-world domains including medicine, chemistry, psychology, economics, and education. We utilize a generative scoring technique that yields soft, model-based reward signals to overcome limitations posed by binary verifications.
  arXiv  Detail & Related papers  (2025-03-31T08:22:49Z)
• Unseen from Seen: Rewriting Observation-Instruction Using Foundation Models for Augmenting Vision-Language Navigation [67.31811007549489]
  We propose a Rewriting-driven AugMentation (RAM) paradigm for Vision-Language Navigation (VLN) Benefiting from our rewriting mechanism, new observation-instruction can be obtained in both simulator-free and labor-saving manners to promote generalization. Experiments on both the discrete environments (R2R, REVERIE, and R4R) and continuous environments (R2R-CE) show the superior performance and impressive generalization ability of our method.
  arXiv  Detail & Related papers  (2025-03-23T13:18:17Z)
• Retrieval Augmented Generation and Understanding in Vision: A Survey and New Outlook [85.43403500874889]
  Retrieval-augmented generation (RAG) has emerged as a pivotal technique in artificial intelligence (AI) Recent advancements in RAG for embodied AI, with a particular focus on applications in planning, task execution, multimodal perception, interaction, and specialized domains.
  arXiv  Detail & Related papers  (2025-03-23T10:33:28Z)
• A Survey on Knowledge-Oriented Retrieval-Augmented Generation [45.65542434522205]
  Retrieval-Augmented Generation (RAG) has gained significant attention in recent years. RAG combines large-scale retrieval systems with generative models. We discuss the key characteristics of RAG, such as its ability to augment generative models with dynamic external knowledge.
  arXiv  Detail & Related papers  (2025-03-11T01:59:35Z)
• Composed Multi-modal Retrieval: A Survey of Approaches and Applications [81.54640206021757]
  Composed Multi-modal Retrieval (CMR) emerges as a pivotal next-generation technology.<n>CMR enables users to query images or videos by integrating a reference visual input with textual modifications.<n>This paper provides a comprehensive survey of CMR, covering its fundamental challenges, technical advancements, and applications.
  arXiv  Detail & Related papers  (2025-03-03T09:18:43Z)
• A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trends [67.43992456058541]
  Image restoration (IR) refers to the process of improving visual quality of images while removing degradation, such as noise, blur, weather effects, and so on. Traditional IR methods typically target specific types of degradation, which limits their effectiveness in real-world scenarios with complex distortions. The all-in-one image restoration (AiOIR) paradigm has emerged, offering a unified framework that adeptly addresses multiple degradation types.
  arXiv  Detail & Related papers  (2024-10-19T11:11:09Z)
• On the Element-Wise Representation and Reasoning in Zero-Shot Image Recognition: A Systematic Survey [82.49623756124357]
  Zero-shot image recognition (ZSIR) aims at empowering models to recognize and reason in unseen domains. This paper presents a broad review of recent advances in element-wise ZSIR. We first attempt to integrate the three basic ZSIR tasks of object recognition, compositional recognition, and foundation model-based open-world recognition into a unified element-wise perspective.
  arXiv  Detail & Related papers  (2024-08-09T05:49:21Z)
• RS-GPT4V: A Unified Multimodal Instruction-Following Dataset for Remote Sensing Image Understanding [4.266920365127677]
  Under the new LaGD paradigm, the old datasets are no longer suitable for fire-new tasks. We designed a high-quality, diversified, and unified multimodal instruction-following dataset for RSI understanding. The empirical results show that the fine-tuned MLLMs by RS-GPT4V can describe fine-grained information.
  arXiv  Detail & Related papers  (2024-06-18T10:34:28Z)
• Robust Saliency-Aware Distillation for Few-shot Fine-grained Visual Recognition [57.08108545219043]
  Recognizing novel sub-categories with scarce samples is an essential and challenging research topic in computer vision. Existing literature addresses this challenge by employing local-based representation approaches. This article proposes a novel model, Robust Saliency-aware Distillation (RSaD), for few-shot fine-grained visual recognition.
  arXiv  Detail & Related papers  (2023-05-12T00:13:17Z)
• Generalization Properties of Retrieval-based Models [50.35325326050263]
  Retrieval-based machine learning methods have enjoyed success on a wide range of problems. Despite growing literature showcasing the promise of these models, the theoretical underpinning for such models remains underexplored. We present a formal treatment of retrieval-based models to characterize their generalization ability.
  arXiv  Detail & Related papers  (2022-10-06T00:33:01Z)
• Evaluating the Generalization Ability of Super-Resolution Networks [45.867729539843]
  We propose a Generalization Assessment Index for SR networks, namely SRGA. SRGA exploits the statistical characteristics of the internal features of deep networks to measure the generalization ability. We benchmark existing SR models on the generalization ability.
  arXiv  Detail & Related papers  (2022-05-14T09:33:20Z)
• Entity-Conditioned Question Generation for Robust Attention Distribution in Neural Information Retrieval [51.53892300802014]
  We show that supervised neural information retrieval models are prone to learning sparse attention patterns over passage tokens. Using a novel targeted synthetic data generation method, we teach neural IR to attend more uniformly and robustly to all entities in a given passage.
  arXiv  Detail & Related papers  (2022-04-24T22:36:48Z)
• Towards Open-World Feature Extrapolation: An Inductive Graph Learning Approach [80.8446673089281]
  We propose a new learning paradigm with graph representation and learning. Our framework contains two modules: 1) a backbone network (e.g., feedforward neural nets) as a lower model takes features as input and outputs predicted labels; 2) a graph neural network as an upper model learns to extrapolate embeddings for new features via message passing over a feature-data graph built from observed data.
  arXiv  Detail & Related papers  (2021-10-09T09:02:45Z)
• Pointer Value Retrieval: A new benchmark for understanding the limits of neural network generalization [40.21297628440919]
  We introduce a novel benchmark, Pointer Value Retrieval (PVR) tasks, that explore the limits of neural network generalization. PVR tasks can consist of visual as well as symbolic inputs, each with varying levels of difficulty. We demonstrate that this task structure provides a rich testbed for understanding generalization.
  arXiv  Detail & Related papers  (2021-07-27T03:50:31Z)
• Few-Shot Named Entity Recognition: A Comprehensive Study [92.40991050806544]
  We investigate three schemes to improve the model generalization ability for few-shot settings. We perform empirical comparisons on 10 public NER datasets with various proportions of labeled data. We create new state-of-the-art results on both few-shot and training-free settings.
  arXiv  Detail & Related papers  (2020-12-29T23:43:16Z)
• Explaining Deep Learning Models for Structured Data using Layer-Wise Relevance Propagation [0.0]
  Layer-wise Relevance (LRP), an established explainability technique developed for deep models in computer vision, provides intuitive human-readable heat maps of input images. We show how LRPis more effective than traditional explainability concepts of Local Interpretable Model-agnostic Ex-planations (LIME) and Shapley Additive Explanations (SHAP) for explainability.
  arXiv  Detail & Related papers  (2020-11-26T18:34:21Z)
• CDEvalSumm: An Empirical Study of Cross-Dataset Evaluation for Neural Summarization Systems [121.78477833009671]
  We investigate the performance of different summarization models under a cross-dataset setting. A comprehensive study of 11 representative summarization systems on 5 datasets from different domains reveals the effect of model architectures and generation ways.
  arXiv  Detail & Related papers  (2020-10-11T02:19:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.