Detecting Systematic Weaknesses in Vision Models along Predefined Human-Understandable Dimensions

• URL: http://arxiv.org/abs/2502.12360v2
• Date: Thu, 06 Mar 2025 18:07:00 GMT
• Title: Detecting Systematic Weaknesses in Vision Models along Predefined Human-Understandable Dimensions
• Authors: Sujan Sai Gannamaneni, Rohil Prakash Rao, Michael Mock, Maram Akila, Stefan Wrobel,
• Abstract summary: Slice discovery methods (SDMs) are prominent algorithms for finding systematic weaknesses in DNNs.<n>We present an algorithm that combines foundation models for zero-shot image classification to generate semantic metadata.<n>We validate our algorithm on both synthetic and real-world datasets, demonstrating its ability to recover human-understandable systematic weaknesses.
• Score: 3.277209755418937
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Slice discovery methods (SDMs) are prominent algorithms for finding systematic weaknesses in DNNs. They identify top-k semantically coherent slices/subsets of data where a DNN-under-test has low performance. For being directly useful, slices should be aligned with human-understandable and relevant dimensions, which, for example, are defined by safety and domain experts as part of the operational design domain (ODD). While SDMs can be applied effectively on structured data, their application on image data is complicated by the lack of semantic metadata. To address these issues, we present an algorithm that combines foundation models for zero-shot image classification to generate semantic metadata with methods for combinatorial search to find systematic weaknesses in images. In contrast to existing approaches, ours identifies weak slices that are in line with pre-defined human-understandable dimensions. As the algorithm includes foundation models, its intermediate and final results may not always be exact. Therefore, we include an approach to address the impact of noisy metadata. We validate our algorithm on both synthetic and real-world datasets, demonstrating its ability to recover human-understandable systematic weaknesses. Furthermore, using our approach, we identify systematic weaknesses of multiple pre-trained and publicly available state-of-the-art computer vision DNNs.

Related papers

• Towards Robust Out-of-Distribution Generalization: Data Augmentation and Neural Architecture Search Approaches [4.577842191730992]
  We study ways toward robust OoD generalization for deep learning. We first propose a novel and effective approach to disentangle the spurious correlation between features that are not essential for recognition. We then study the problem of strengthening neural architecture search in OoD scenarios.
  arXiv  Detail & Related papers  (2024-10-25T20:50:32Z)
• AI-Aided Kalman Filters [65.35350122917914]
  The Kalman filter (KF) and its variants are among the most celebrated algorithms in signal processing. Recent developments illustrate the possibility of fusing deep neural networks (DNNs) with classic Kalman-type filtering. This article provides a tutorial-style overview of design approaches for incorporating AI in aiding KF-type algorithms.
  arXiv  Detail & Related papers  (2024-10-16T06:47:53Z)
• On Discriminative Probabilistic Modeling for Self-Supervised Representation Learning [85.75164588939185]
  We study the discriminative probabilistic modeling on a continuous domain for the data prediction task of (multimodal) self-supervised representation learning. We conduct generalization error analysis to reveal the limitation of current InfoNCE-based contrastive loss for self-supervised representation learning. We propose a novel non-parametric method for approximating the sum of conditional probability densities required by MIS.
  arXiv  Detail & Related papers  (2024-10-11T18:02:46Z)
• 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.<n>This approach faces significant challenges, including the laborious and costly requirement for additional metadata.<n>We introduce AttributionScanner, an innovative human-in-the-loop Visual Analytics (VA) system, designed for metadata-free data slice finding.<n>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)
• Assessing Systematic Weaknesses of DNNs using Counterfactuals [3.5849841840695835]
  It is non-trivial to attribute the reason for such observed low performances to the specific semantic features that describe the subset. Inspired by counterfactual explanations, we propose an effective and computationally cheap algorithm to validate the semantic attribution of existing subsets.
  arXiv  Detail & Related papers  (2023-08-03T08:41:39Z)
• Neuro-Symbolic Approaches for Context-Aware Human Activity Recognition [0.7734726150561088]
  We propose a novel approach based on a semantic loss function that infuses knowledge constraints in the Human Activity Recognition model during the training phase. Our results on scripted and in-the-wild datasets show the impact of different semantic loss functions in outperforming a purely data-driven model.
  arXiv  Detail & Related papers  (2023-06-08T09:23:09Z)
• Experimental Observations of the Topology of Convolutional Neural Network Activations [2.4235626091331737]
  Topological data analysis provides compact, noise-robust representations of complex structures. Deep neural networks (DNNs) learn millions of parameters associated with a series of transformations defined by the model architecture. In this paper, we apply cutting edge techniques from TDA with the goal of gaining insight into the interpretability of convolutional neural networks used for image classification.
  arXiv  Detail & Related papers  (2022-12-01T02:05:44Z)
• 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)
• Cluster-level pseudo-labelling for source-free cross-domain facial expression recognition [94.56304526014875]
  We propose the first Source-Free Unsupervised Domain Adaptation (SFUDA) method for Facial Expression Recognition (FER) Our method exploits self-supervised pretraining to learn good feature representations from the target data. We validate the effectiveness of our method in four adaptation setups, proving that it consistently outperforms existing SFUDA methods when applied to FER.
  arXiv  Detail & Related papers  (2022-10-11T08:24:50Z)
• Batch-Ensemble Stochastic Neural Networks for Out-of-Distribution Detection [55.028065567756066]
  Out-of-distribution (OOD) detection has recently received much attention from the machine learning community due to its importance in deploying machine learning models in real-world applications. In this paper we propose an uncertainty quantification approach by modelling the distribution of features. We incorporate an efficient ensemble mechanism, namely batch-ensemble, to construct the batch-ensemble neural networks (BE-SNNs) and overcome the feature collapse problem. We show that BE-SNNs yield superior performance on several OOD benchmarks, such as the Two-Moons dataset, the FashionMNIST vs MNIST dataset, FashionM
  arXiv  Detail & Related papers  (2022-06-26T16:00:22Z)
• DEMAND: Deep Matrix Approximately NonlinearDecomposition to Identify Meta, Canonical, and Sub-Spatial Pattern of functional Magnetic Resonance Imaging in the Human Brain [8.93274096260726]
  We propose a novel deep nonlinear matrix factorization named Deep Approximately Decomposition (DEMAND) in this work to take advantage of the shallow linear model, e.g., Sparse Dictionary Learning (SDL) and Deep Neural Networks (DNNs) DEMAND can reveal the reproducible meta, canonical, and sub-spatial features of the human brain more efficiently than other peer methodologies.
  arXiv  Detail & Related papers  (2022-05-20T15:55:01Z)
• DEALIO: Data-Efficient Adversarial Learning for Imitation from Observation [57.358212277226315]
  In imitation learning from observation IfO, a learning agent seeks to imitate a demonstrating agent using only observations of the demonstrated behavior without access to the control signals generated by the demonstrator. Recent methods based on adversarial imitation learning have led to state-of-the-art performance on IfO problems, but they typically suffer from high sample complexity due to a reliance on data-inefficient, model-free reinforcement learning algorithms. This issue makes them impractical to deploy in real-world settings, where gathering samples can incur high costs in terms of time, energy, and risk. We propose a more data-efficient IfO algorithm
  arXiv  Detail & Related papers  (2021-03-31T23:46:32Z)
• Abstraction and Symbolic Execution of Deep Neural Networks with Bayesian Approximation of Hidden Features [8.723426955657345]
  We propose a novel abstraction method which abstracts a deep neural network and a dataset into a Bayesian network. We make use of dimensionality reduction techniques to identify hidden features that have been learned by hidden layers of the DNN. We can derive a runtime monitoring approach to detect in operational time rare inputs.
  arXiv  Detail & Related papers  (2021-03-05T14:28:42Z)
• Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning [50.24174211654775]
  We present a novel contrastive self-supervised learning framework for anomaly detection on attributed networks. Our framework fully exploits the local information from network data by sampling a novel type of contrastive instance pair. A graph neural network-based contrastive learning model is proposed to learn informative embedding from high-dimensional attributes and local structure.
  arXiv  Detail & Related papers  (2021-02-27T03:17:20Z)
• Entropy Maximization and Meta Classification for Out-Of-Distribution Detection in Semantic Segmentation [7.305019142196585]
  "Out-of-distribution" (OoD) samples are crucial for many applications such as automated driving. A natural baseline approach to OoD detection is to threshold on the pixel-wise softmax entropy. We present a two-step procedure that significantly improves that approach.
  arXiv  Detail & Related papers  (2020-12-09T11:01:06Z)
• Contextual-Bandit Anomaly Detection for IoT Data in Distributed Hierarchical Edge Computing [65.78881372074983]
  IoT devices can hardly afford complex deep neural networks (DNN) models, and offloading anomaly detection tasks to the cloud incurs long delay. We propose and build a demo for an adaptive anomaly detection approach for distributed hierarchical edge computing (HEC) systems. We show that our proposed approach significantly reduces detection delay without sacrificing accuracy, as compared to offloading detection tasks to the cloud.
  arXiv  Detail & Related papers  (2020-04-15T06:13:33Z)
• Stance Detection Benchmark: How Robust Is Your Stance Detection? [65.91772010586605]
  Stance Detection (StD) aims to detect an author's stance towards a certain topic or claim. We introduce a StD benchmark that learns from ten StD datasets of various domains in a multi-dataset learning setting. Within this benchmark setup, we are able to present new state-of-the-art results on five of the datasets.
  arXiv  Detail & Related papers  (2020-01-06T13:37:51Z)

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.