TRoVe: Discovering Error-Inducing Static Feature Biases in Temporal Vision-Language Models

• URL: http://arxiv.org/abs/2512.01048v1
• Date: Sun, 30 Nov 2025 19:36:46 GMT
• Title: TRoVe: Discovering Error-Inducing Static Feature Biases in Temporal Vision-Language Models
• Authors: Maya Varma, Jean-Benoit Delbrouck, Sophie Ostmeier, Akshay Chaudhari, Curtis Langlotz,
• Abstract summary: TRoVe is an automated approach for discovering error-inducing static feature biases.<n>We show that TRoVe can accurately identify error-inducing static feature biases in vision-language models.
• Score: 10.388673049493947
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision-language models (VLMs) have made great strides in addressing temporal understanding tasks, which involve characterizing visual changes across a sequence of images. However, recent works have suggested that when making predictions, VLMs may rely on static feature biases, such as background or object features, rather than dynamic visual changes. Static feature biases are a type of shortcut and can contribute to systematic prediction errors on downstream tasks; as a result, identifying and characterizing error-inducing static feature biases is critical prior to real-world model deployment. In this work, we introduce TRoVe, an automated approach for discovering error-inducing static feature biases learned by temporal VLMs. Given a trained VLM and an annotated validation dataset associated with a downstream classification task, TRoVe extracts candidate static features from the dataset and scores each feature by (i) the effect of the feature on classification errors as well as (ii) the extent to which the VLM relies on the feature when making predictions. In order to quantitatively evaluate TRoVe, we introduce an evaluation framework consisting of 101 trained temporal VLMs paired with ground-truth annotations for learned static feature biases. We use this framework to demonstrate that TRoVe can accurately identify error-inducing static feature biases in VLMs, achieving a 28.6% improvement over the closest baseline. Finally, we apply TRoVe to 7 off-the-shelf VLMs and 2 temporal understanding tasks, surfacing previously-unknown static feature biases and demonstrating that knowledge of learned biases can aid in improving model performance at test time. Our code is available at https://github.com/Stanford-AIMI/TRoVe.

Related papers

• CALM: A Framework for Continuous, Adaptive, and LLM-Mediated Anomaly Detection in Time-Series Streams [0.42970700836450476]
  This paper introduces CALM, a novel, end-to-end framework for real-time anomaly detection.<n> CALM is built on the Apache Beam distributed processing framework.<n>It implements a closed-loop, continuous fine-tuning mechanism that allows the anomaly detection model to adapt to evolving data patterns in near real-time.
  arXiv  Detail & Related papers  (2025-08-29T00:27:35Z)
• LLM-empowered Dynamic Prompt Routing for Vision-Language Models Tuning under Long-Tailed Distributions [3.5268162595059076]
  This paper proposes a Multi-dimensional Dynamic Prompt Routing (MDPR) framework for vision-language models (VLMs)<n>MDPR constructs a comprehensive knowledge base for classes, spanning five visual-semantic dimensions.<n>Experiments on long-tailed benchmarks, including CIFAR-LT, ImageNet-LT, and Places-LT, demonstrate that MDPR achieves comparable results with current SOTA methods.
  arXiv  Detail & Related papers  (2025-08-21T16:12:06Z)
• Debiased Prompt Tuning in Vision-Language Model without Annotations [14.811475313694041]
  Vision-Language Models (VLMs) may suffer from the problem of spurious correlations.<n>By leveraging pseudo-spurious attribute annotations, we propose a method to automatically adjust the training weights of different groups.<n>Our approach efficiently improves the worst-group accuracy on CelebA, Waterbirds, and MetaShift datasets.
  arXiv  Detail & Related papers  (2025-03-11T12:24:54Z)
• Focus On This, Not That! Steering LLMs with Adaptive Feature Specification [48.27684487597968]
  Focus Instruction Tuning (FIT) trains large language models to condition their responses by focusing on specific features whilst ignoring others, leading to different behaviours based on what features are specified.<n>We demonstrate that FIT successfully steers behaviour at inference time; (ii) increases robustness by amplifying core task signals and down-weighting spurious cues; (iii) mitigates social bias by suppressing demographic attributes; and (iv) generalises under distribution shifts and to previously unseen focus features.
  arXiv  Detail & Related papers  (2024-10-30T12:01:48Z)
• DECIDER: Leveraging Foundation Model Priors for Improved Model Failure Detection and Explanation [18.77296551727931]
  We propose DECIDER, a novel approach that leverages priors from large language models (LLMs) and vision-language models (VLMs) to detect failures in image models. DECIDER consistently achieves state-of-the-art failure detection performance, significantly outperforming baselines in terms of the overall Matthews correlation coefficient.
  arXiv  Detail & Related papers  (2024-08-01T07:08:11Z)
• Adaptive Retention & Correction: Test-Time Training for Continual Learning [114.5656325514408]
  A common problem in continual learning is the classification layer's bias towards the most recent task.<n>We name our approach Adaptive Retention & Correction (ARC)<n>ARC achieves an average performance increase of 2.7% and 2.6% on the CIFAR-100 and Imagenet-R datasets.
  arXiv  Detail & Related papers  (2024-05-23T08:43:09Z)
• D-CALM: A Dynamic Clustering-based Active Learning Approach for Mitigating Bias [13.008323851750442]
  In this paper, we propose a novel adaptive clustering-based active learning algorithm, D-CALM, that dynamically adjusts clustering and annotation efforts. Experiments on eight datasets for a diverse set of text classification tasks, including emotion, hatespeech, dialog act, and book type detection, demonstrate that our proposed algorithm significantly outperforms baseline AL approaches.
  arXiv  Detail & Related papers  (2023-05-26T15:17:43Z)
• Feature-Level Debiased Natural Language Understanding [86.8751772146264]
  Existing natural language understanding (NLU) models often rely on dataset biases to achieve high performance on specific datasets. We propose debiasing contrastive learning (DCT) to mitigate biased latent features and neglect the dynamic nature of bias. DCT outperforms state-of-the-art baselines on out-of-distribution datasets while maintaining in-distribution performance.
  arXiv  Detail & Related papers  (2022-12-11T06:16:14Z)
• Task Residual for Tuning Vision-Language Models [69.22958802711017]
  We propose a new efficient tuning approach for vision-language models (VLMs) named Task Residual Tuning (TaskRes) TaskRes explicitly decouples the prior knowledge of the pre-trained models and new knowledge regarding a target task. The proposed TaskRes is simple yet effective, which significantly outperforms previous methods on 11 benchmark datasets.
  arXiv  Detail & Related papers  (2022-11-18T15:09:03Z)
• General Greedy De-bias Learning [163.65789778416172]
  We propose a General Greedy De-bias learning framework (GGD), which greedily trains the biased models and the base model like gradient descent in functional space. GGD can learn a more robust base model under the settings of both task-specific biased models with prior knowledge and self-ensemble biased model without prior knowledge.
  arXiv  Detail & Related papers  (2021-12-20T14:47:32Z)
• SLA$^2$P: Self-supervised Anomaly Detection with Adversarial Perturbation [77.71161225100927]
  Anomaly detection is a fundamental yet challenging problem in machine learning. We propose a novel and powerful framework, dubbed as SLA$2$P, for unsupervised anomaly detection.
  arXiv  Detail & Related papers  (2021-11-25T03:53:43Z)

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.