Boosting Generalizability towards Zero-Shot Cross-Dataset Single-Image Indoor Depth by Meta-Initialization

• URL: http://arxiv.org/abs/2409.02486v1
• Date: Wed, 4 Sep 2024 07:25:50 GMT
• Title: Boosting Generalizability towards Zero-Shot Cross-Dataset Single-Image Indoor Depth by Meta-Initialization
• Authors: Cho-Ying Wu, Yiqi Zhong, Junying Wang, Ulrich Neumann,
• Abstract summary: We use gradient-based meta-learning to gain higher generalizability on zero-shot cross-dataset inference. We propose zero-shot cross-dataset protocols and validate higher generalizability induced by our meta-initialization.
• Score: 17.822554284161868
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Indoor robots rely on depth to perform tasks like navigation or obstacle detection, and single-image depth estimation is widely used to assist perception. Most indoor single-image depth prediction focuses less on model generalizability to unseen datasets, concerned with in-the-wild robustness for system deployment. This work leverages gradient-based meta-learning to gain higher generalizability on zero-shot cross-dataset inference. Unlike the most-studied meta-learning of image classification associated with explicit class labels, no explicit task boundaries exist for continuous depth values tied to highly varying indoor environments regarding object arrangement and scene composition. We propose fine-grained task that treats each RGB-D mini-batch as a task in our meta-learning formulation. We first show that our method on limited data induces a much better prior (max 27.8% in RMSE). Then, finetuning on meta-learned initialization consistently outperforms baselines without the meta approach. Aiming at generalization, we propose zero-shot cross-dataset protocols and validate higher generalizability induced by our meta-initialization, as a simple and useful plugin to many existing depth estimation methods. The work at the intersection of depth and meta-learning potentially drives both research to step closer to practical robotic and machine perception usage.

Related papers

• Weakly-supervised Contrastive Learning for Unsupervised Object Discovery [52.696041556640516]
  Unsupervised object discovery is promising due to its ability to discover objects in a generic manner. We design a semantic-guided self-supervised learning model to extract high-level semantic features from images. We introduce Principal Component Analysis (PCA) to localize object regions.
  arXiv  Detail & Related papers  (2023-07-07T04:03:48Z)
• Meta Omnium: A Benchmark for General-Purpose Learning-to-Learn [15.0841751679151]
  We introduce Meta Omnium, a dataset-of-datasets spanning multiple vision tasks. We analyze their ability to generalize across tasks and to transfer knowledge between them.
  arXiv  Detail & Related papers  (2023-05-12T17:25:19Z)
• Meta-Optimization for Higher Model Generalizability in Single-Image Depth Prediction [19.469860191876876]
  We leverage gradient-based meta-learning for higher generalizability on zero-shot cross-dataset inference. Unlike the most-studied image classification in meta-learning, depth is pixel-level continuous range values. We propose fine-grained task that treats each RGB-D pair as a task in our meta-optimization.
  arXiv  Detail & Related papers  (2023-05-12T06:17:13Z)
• SemHint-MD: Learning from Noisy Semantic Labels for Self-Supervised Monocular Depth Estimation [19.229255297016635]
  Self-supervised depth estimation can be trapped in a local minimum due to the gradient-locality issue of the photometric loss. We present a framework to enhance depth by leveraging semantic segmentation to guide the network to jump out of the local minimum.
  arXiv  Detail & Related papers  (2023-03-31T17:20:27Z)
• LESS: Label-Efficient Semantic Segmentation for LiDAR Point Clouds [62.49198183539889]
  We propose a label-efficient semantic segmentation pipeline for outdoor scenes with LiDAR point clouds. Our method co-designs an efficient labeling process with semi/weakly supervised learning. Our proposed method is even highly competitive compared to the fully supervised counterpart with 100% labels.
  arXiv  Detail & Related papers  (2022-10-14T19:13:36Z)
• Improving Meta-Learning Generalization with Activation-Based Early-Stopping [12.299371455015239]
  Meta-Learning algorithms for few-shot learning aim to train neural networks capable of generalizing to novel tasks using only a few examples. Early-stopping is critical for performance, halting model training when it reaches optimal generalization to the new task distribution. This is problematic in few-shot transfer learning settings, where the meta-test set comes from a different target dataset.
  arXiv  Detail & Related papers  (2022-08-03T22:55:45Z)
• Improving Generalization in Meta-learning via Task Augmentation [69.83677015207527]
  We propose two task augmentation methods, including MetaMix and Channel Shuffle. Both MetaMix and Channel Shuffle outperform state-of-the-art results by a large margin across many datasets.
  arXiv  Detail & Related papers  (2020-07-26T01:50:42Z)
• Incremental Object Detection via Meta-Learning [77.55310507917012]
  We propose a meta-learning approach that learns to reshape model gradients, such that information across incremental tasks is optimally shared. In comparison to existing meta-learning methods, our approach is task-agnostic, allows incremental addition of new-classes and scales to high-capacity models for object detection.
  arXiv  Detail & Related papers  (2020-03-17T13:40:00Z)
• Incremental Meta-Learning via Indirect Discriminant Alignment [118.61152684795178]
  We develop a notion of incremental learning during the meta-training phase of meta-learning. Our approach performs favorably at test time as compared to training a model with the full meta-training set.
  arXiv  Detail & Related papers  (2020-02-11T01:39:12Z)
• Single Image Depth Estimation Trained via Depth from Defocus Cues [105.67073923825842]
  Estimating depth from a single RGB image is a fundamental task in computer vision. In this work, we rely, instead of different views, on depth from focus cues. We present results that are on par with supervised methods on KITTI and Make3D datasets and outperform unsupervised learning approaches.
  arXiv  Detail & Related papers  (2020-01-14T20:22:54Z)

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.