VisFIS: Visual Feature Importance Supervision with Right-for-the-Right-Reason Objectives

• URL: http://arxiv.org/abs/2206.11212v1
• Date: Wed, 22 Jun 2022 17:02:01 GMT
• Title: VisFIS: Visual Feature Importance Supervision with Right-for-the-Right-Reason Objectives
• Authors: Zhuofan Ying, Peter Hase, Mohit Bansal
• Abstract summary: We show that model FI supervision can meaningfully improve VQA model accuracy as well as performance on several Right-for-the-Right-Reason metrics. Our best performing method, Visual Feature Importance Supervision (VisFIS), outperforms strong baselines on benchmark VQA datasets. Predictions are more accurate when explanations are plausible and faithful, and not when they are plausible but not faithful.
• Score: 84.48039784446166
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Many past works aim to improve visual reasoning in models by supervising feature importance (estimated by model explanation techniques) with human annotations such as highlights of important image regions. However, recent work has shown that performance gains from feature importance (FI) supervision for Visual Question Answering (VQA) tasks persist even with random supervision, suggesting that these methods do not meaningfully align model FI with human FI. In this paper, we show that model FI supervision can meaningfully improve VQA model accuracy as well as performance on several Right-for-the-Right-Reason (RRR) metrics by optimizing for four key model objectives: (1) accurate predictions given limited but sufficient information (Sufficiency); (2) max-entropy predictions given no important information (Uncertainty); (3) invariance of predictions to changes in unimportant features (Invariance); and (4) alignment between model FI explanations and human FI explanations (Plausibility). Our best performing method, Visual Feature Importance Supervision (VisFIS), outperforms strong baselines on benchmark VQA datasets in terms of both in-distribution and out-of-distribution accuracy. While past work suggests that the mechanism for improved accuracy is through improved explanation plausibility, we show that this relationship depends crucially on explanation faithfulness (whether explanations truly represent the model's internal reasoning). Predictions are more accurate when explanations are plausible and faithful, and not when they are plausible but not faithful. Lastly, we show that, surprisingly, RRR metrics are not predictive of out-of-distribution model accuracy when controlling for a model's in-distribution accuracy, which calls into question the value of these metrics for evaluating model reasoning. All supporting code is available at https://github.com/zfying/visfis

Related papers

• Beyond Accuracy: Ensuring Correct Predictions With Correct Rationales [10.397502254316645]
  We propose a two-phase scheme to ensure double-correct predictions. First, we curate a new dataset that offers structured rationales for visual recognition tasks. Second, we propose a rationale-informed optimization method to guide the model in disentangling and localizing visual evidence.
  arXiv  Detail & Related papers  (2024-10-31T18:33:39Z)
• Improve Vision Language Model Chain-of-thought Reasoning [86.83335752119741]
  Chain-of-thought (CoT) reasoning in vision language models (VLMs) is crucial for improving interpretability and trustworthiness. We show that training VLM on short answers does not generalize well to reasoning tasks that require more detailed responses.
  arXiv  Detail & Related papers  (2024-10-21T17:00:06Z)
• Predicting generalization performance with correctness discriminators [64.00420578048855]
  We present a novel model that establishes upper and lower bounds on the accuracy, without requiring gold labels for the unseen data. We show across a variety of tagging, parsing, and semantic parsing tasks that the gold accuracy is reliably between the predicted upper and lower bounds.
  arXiv  Detail & Related papers  (2023-11-15T22:43:42Z)
• Boosted Control Functions [10.503777692702952]
  This work aims to bridge the gap between causal effect estimation and prediction tasks. We establish a novel connection between the field of distribution from machine learning, and simultaneous equation models and control function from econometrics. Within this framework, we propose a strong notion of invariance for a predictive model and compare it with existing (weaker) versions.
  arXiv  Detail & Related papers  (2023-10-09T15:43:46Z)
• Confidence and Dispersity Speak: Characterising Prediction Matrix for Unsupervised Accuracy Estimation [51.809741427975105]
  This work aims to assess how well a model performs under distribution shifts without using labels. We use the nuclear norm that has been shown to be effective in characterizing both properties. We show that the nuclear norm is more accurate and robust in accuracy than existing methods.
  arXiv  Detail & Related papers  (2023-02-02T13:30:48Z)
• Predicting is not Understanding: Recognizing and Addressing Underspecification in Machine Learning [47.651130958272155]
  Underspecification refers to the existence of multiple models that are indistinguishable in their in-domain accuracy. We formalize the concept of underspecification and propose a method to identify and partially address it.
  arXiv  Detail & Related papers  (2022-07-06T11:20:40Z)
• Leveraging Unlabeled Data to Predict Out-of-Distribution Performance [63.740181251997306]
  Real-world machine learning deployments are characterized by mismatches between the source (training) and target (test) distributions. In this work, we investigate methods for predicting the target domain accuracy using only labeled source data and unlabeled target data. We propose Average Thresholded Confidence (ATC), a practical method that learns a threshold on the model's confidence, predicting accuracy as the fraction of unlabeled examples.
  arXiv  Detail & Related papers  (2022-01-11T23:01:12Z)
• Are Visual Explanations Useful? A Case Study in Model-in-the-Loop Prediction [49.254162397086006]
  We study explanations based on visual saliency in an image-based age prediction task. We find that presenting model predictions improves human accuracy. However, explanations of various kinds fail to significantly alter human accuracy or trust in the model.
  arXiv  Detail & Related papers  (2020-07-23T20:39:40Z)
• Unifying Model Explainability and Robustness via Machine-Checkable Concepts [33.88198813484126]
  We propose a robustness-assessment framework, at the core of which is the idea of using machine-checkable concepts. Our framework defines a large number of concepts that the explanations could be based on and performs the explanation-conformity check at test time to assess prediction robustness. Experiments on real-world datasets and human surveys show that our framework is able to enhance prediction robustness significantly.
  arXiv  Detail & Related papers  (2020-07-01T05:21:16Z)
• Towards Transparent and Explainable Attention Models [34.0557018891191]
  We first explain why current attention mechanisms in LSTM based encoders can neither provide a faithful nor a plausible explanation of the model's predictions. We propose a modified LSTM cell with a diversity-driven training objective that ensures that the hidden representations learned at different time steps are diverse. Human evaluations indicate that the attention distributions learned by our model offer a plausible explanation of the model's predictions.
  arXiv  Detail & Related papers  (2020-04-29T14:47:50Z)

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.