paper-with-me

홈 › Papers

Dynamic Top-k Estimation Consolidates Disagreement between Feature Attribution Methods

2023-10-09 · Jonathan Kamp, Lisa Beinborn, Antske Fokkens

Feature attribution scores are used for explaining the prediction of a text classifier to users by highlighting a k number of tokens. In this work, we propose a way to determine the number of optimal k tokens that should be displayed from sequential properties of the attribution scores. Our approach is dynamic across sentences, method-agnostic, and deals with sentence length bias. We compare agreement between multiple methods and humans on an NLI task, using fixed k and dynamic k. We find that perturbation-based methods and Vanilla Gradient exhibit highest agreement on most method--method and method--human agreement metrics with a static k. Their advantage over other methods disappears with dynamic ks which mainly improve Integrated Gradient and GradientXInput. To our knowledge, this is the first evidence that sequential properties of attribution scores are informative for consolidating attribution signals for human interpretation.

📄 PDF Abstract BibTeX arXiv:2310.05619

Code (0)

등록된 구현이 없습니다.

Tasks

Sentence

Similar Papers 제목 키워드 기반

ConR: Contrastive Regularizer for Deep Imbalanced Regression

2023-09-13 · Mahsa Keramati, Lili Meng, R. David Evans

Imbalanced distributions are ubiquitous in real-world data. They create constraints on Deep Neural Networks to represent the minority labels and avoid bias towards majority labels. The extensive body of imbalanced approa…

Deep imbalanced regressionregression

Dual-Stream Collaborative Transformer for Image Captioning

2026-01-19 · Jun Wan, Jun Liu, Zhihui lai, Jie Zhou arxiv

Current region feature-based image captioning methods have progressed rapidly and achieved remarkable performance. However, they are still prone to generating irrelevant descriptions due to the lack of contextual informa…

Image Captioning

UfM*: Uncertainty from Motion* for DNN Depth Estimation Using Gaussians

2026-05-21 · Soumya Sudhakar, Sertac Karaman, Vivienne Sze arxiv

Reliable uncertainty estimation is critical for deploying monocular depth deep neural networks (DNNs) in safety-critical robotic systems. Conventional uncertainty methods such as ensembles and sampling-based approaches r…

Depth Estimation

Learning semantical dynamics and spatiotemporal collaboration for human pose estimation in video

2025-02-15 · Runyang Feng, Haoming Chen

Temporal modeling and spatio-temporal collaboration are pivotal techniques for video-based human pose estimation. Most state-of-the-art methods adopt optical flow or temporal difference, learning local visual content cor…

Optical Flow EstimationPose Estimation

AETTA: Label-Free Accuracy Estimation for Test-Time Adaptation

2024-04-01 · CVPR 2024 1 · Taeckyung Lee, Sorn Chottananurak, Taesik Gong, Sung-Ju Lee

Test-time adaptation (TTA) has emerged as a viable solution to adapt pre-trained models to domain shifts using unlabeled test data. However, TTA faces challenges of adaptation failures due to its reliance on blind adapta…

PredictionTest-time Adaptation