arXiv Analytics

Sign in

arXiv:2404.08540 [cs.CV]AbstractReferencesReviewsResources

On the Robustness of Language Guidance for Low-Level Vision Tasks: Findings from Depth Estimation

Agneet Chatterjee, Tejas Gokhale, Chitta Baral, Yezhou Yang

Published 2024-04-12Version 1

Recent advances in monocular depth estimation have been made by incorporating natural language as additional guidance. Although yielding impressive results, the impact of the language prior, particularly in terms of generalization and robustness, remains unexplored. In this paper, we address this gap by quantifying the impact of this prior and introduce methods to benchmark its effectiveness across various settings. We generate "low-level" sentences that convey object-centric, three-dimensional spatial relationships, incorporate them as additional language priors and evaluate their downstream impact on depth estimation. Our key finding is that current language-guided depth estimators perform optimally only with scene-level descriptions and counter-intuitively fare worse with low level descriptions. Despite leveraging additional data, these methods are not robust to directed adversarial attacks and decline in performance with an increase in distribution shift. Finally, to provide a foundation for future research, we identify points of failures and offer insights to better understand these shortcomings. With an increasing number of methods using language for depth estimation, our findings highlight the opportunities and pitfalls that require careful consideration for effective deployment in real-world settings

Comments: Accepted to CVPR 2024. Project webpage: https://agneetchatterjee.com/robustness_depth_lang/
Categories: cs.CV
Related articles: Most relevant | Search more
arXiv:1111.1014 [cs.CV] (Published 2011-11-03)
Sparsity and Robustness in Face Recognition
arXiv:1604.07480 [cs.CV] (Published 2016-04-25)
Joint Semantic Segmentation and Depth Estimation with Deep Convolutional Networks
arXiv:2410.11610 [cs.CV] (Published 2024-10-15)
Depth Estimation From Monocular Images With Enhanced Encoder-Decoder Architecture