On Evaluation of Vision Datasets and Models using Human Competency Frameworks

• URL: http://arxiv.org/abs/2409.04041v1
• Date: Fri, 6 Sep 2024 06:20:11 GMT
• Title: On Evaluation of Vision Datasets and Models using Human Competency Frameworks
• Authors: Rahul Ramachandran, Tejal Kulkarni, Charchit Sharma, Deepak Vijaykeerthy, Vineeth N Balasubramanian,
• Abstract summary: Item Response Theory (IRT) is a framework that infers interpretable latent parameters for an ensemble of models and each dataset item. We assess model calibration, select informative data subsets, and demonstrate the usefulness of its latent parameters for analyzing and comparing models and datasets in computer vision.
• Score: 20.802372291783488
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Evaluating models and datasets in computer vision remains a challenging task, with most leaderboards relying solely on accuracy. While accuracy is a popular metric for model evaluation, it provides only a coarse assessment by considering a single model's score on all dataset items. This paper explores Item Response Theory (IRT), a framework that infers interpretable latent parameters for an ensemble of models and each dataset item, enabling richer evaluation and analysis beyond the single accuracy number. Leveraging IRT, we assess model calibration, select informative data subsets, and demonstrate the usefulness of its latent parameters for analyzing and comparing models and datasets in computer vision.

Related papers

• LiveXiv -- A Multi-Modal Live Benchmark Based on Arxiv Papers Content [62.816876067499415]
  We propose LiveXiv: a scalable evolving live benchmark based on scientific ArXiv papers. LiveXiv accesses domain-specific manuscripts at any given timestamp and proposes to automatically generate visual question-answer pairs. We benchmark multiple open and proprietary Large Multi-modal Models (LMMs) on the first version of our benchmark, showing its challenging nature and exposing the models true abilities.
  arXiv  Detail & Related papers  (2024-10-14T17:51:23Z)
• PUB: Plot Understanding Benchmark and Dataset for Evaluating Large Language Models on Synthetic Visual Data Interpretation [2.1184929769291294]
  This paper presents a novel synthetic dataset designed to evaluate the proficiency of large language models in interpreting data visualizations. Our dataset is generated using controlled parameters to ensure comprehensive coverage of potential real-world scenarios. We employ multimodal text prompts with questions related to visual data in images to benchmark several state-of-the-art models.
  arXiv  Detail & Related papers  (2024-09-04T11:19:17Z)
• A Framework for Efficient Model Evaluation through Stratification, Sampling, and Estimation [17.351089059392674]
  We propose a framework for model evaluation that includes stratification, sampling, and estimation components. We show that stratification via k-means clustering based on accurate predictions of model performance yields efficient estimators. We also find that model-assisted estimators, which leverage predictions of model accuracy on the unlabeled portion of the dataset, are generally more efficient than the traditional estimates.
  arXiv  Detail & Related papers  (2024-06-11T14:49:04Z)
• AttributionScanner: A Visual Analytics System for Model Validation with Metadata-Free Slice Finding [29.07617945233152]
  Data slice finding is an emerging technique for validating machine learning (ML) models by identifying and analyzing subgroups in a dataset that exhibit poor performance. This approach faces significant challenges, including the laborious and costly requirement for additional metadata. We introduce AttributionScanner, an innovative human-in-the-loop Visual Analytics (VA) system, designed for metadata-free data slice finding. Our system identifies interpretable data slices that involve common model behaviors and visualizes these patterns through an Attribution Mosaic design.
  arXiv  Detail & Related papers  (2024-01-12T09:17:32Z)
• On the Evaluation and Refinement of Vision-Language Instruction Tuning Datasets [71.54954966652286]
  We try to evaluate the Vision-Language Instruction-Tuning (VLIT) datasets. We build a new dataset, REVO-LION, by collecting samples with higher SQ from each dataset. Remarkably, even with only half of the complete data, the model trained on REVO-LION can achieve the performance comparable to simply adding all VLIT datasets up.
  arXiv  Detail & Related papers  (2023-10-10T13:01:38Z)
• Revisiting the Evaluation of Image Synthesis with GANs [55.72247435112475]
  This study presents an empirical investigation into the evaluation of synthesis performance, with generative adversarial networks (GANs) as a representative of generative models. In particular, we make in-depth analyses of various factors, including how to represent a data point in the representation space, how to calculate a fair distance using selected samples, and how many instances to use from each set.
  arXiv  Detail & Related papers  (2023-04-04T17:54:32Z)
• Discover, Explanation, Improvement: An Automatic Slice Detection Framework for Natural Language Processing [72.14557106085284]
  slice detection models (SDM) automatically identify underperforming groups of datapoints. This paper proposes a benchmark named "Discover, Explain, improve (DEIM)" for classification NLP tasks. Our evaluation shows that Edisa can accurately select error-prone datapoints with informative semantic features.
  arXiv  Detail & Related papers  (2022-11-08T19:00:00Z)
• Comparing Test Sets with Item Response Theory [53.755064720563]
  We evaluate 29 datasets using predictions from 18 pretrained Transformer models on individual test examples. We find that Quoref, HellaSwag, and MC-TACO are best suited for distinguishing among state-of-the-art models. We also observe span selection task format, which is used for QA datasets like QAMR or SQuAD2.0, is effective in differentiating between strong and weak models.
  arXiv  Detail & Related papers  (2021-06-01T22:33:53Z)
• BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models [41.45240621979654]
  We introduce BEIR, a heterogeneous benchmark for information retrieval. We study the effectiveness of nine state-of-the-art retrieval models in a zero-shot evaluation setup. Dense-retrieval models are computationally more efficient but often underperform other approaches.
  arXiv  Detail & Related papers  (2021-04-17T23:29:55Z)
• How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Models [95.8037674226622]
  We introduce a 3-dimensional evaluation metric that characterizes the fidelity, diversity and generalization performance of any generative model in a domain-agnostic fashion. Our metric unifies statistical divergence measures with precision-recall analysis, enabling sample- and distribution-level diagnoses of model fidelity and diversity.
  arXiv  Detail & Related papers  (2021-02-17T18:25:30Z)

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.