TRoVe: Discovering Error-Inducing Static Feature Biases in Temporal Vision-Language Models
By: Maya Varma , Jean-Benoit Delbrouck , Sophie Ostmeier and more
Potential Business Impact:
Finds hidden mistakes in AI that watches videos.
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.
Similar Papers
STER-VLM: Spatio-Temporal With Enhanced Reference Vision-Language Models
CV and Pattern Recognition
Helps self-driving cars understand traffic better.
Biases Propagate in Encoder-based Vision-Language Models: A Systematic Analysis From Intrinsic Measures to Zero-shot Retrieval Outcomes
Computation and Language
Finds AI learns unfairness from its training data.
From Synthetic Scenes to Real Performance: Enhancing Spatial Reasoning in VLMs
CV and Pattern Recognition
Makes AI understand pictures better, without mistakes.