Random Walk on Pixel Manifolds for Anomaly Segmentation of Complex Driving Scenes

• URL: http://arxiv.org/abs/2404.17961v2
• Date: Sun, 15 Sep 2024 00:55:55 GMT
• Title: Random Walk on Pixel Manifolds for Anomaly Segmentation of Complex Driving Scenes
• Authors: Zelong Zeng, Kaname Tomite,
• Abstract summary: We propose a novel method called Random Walk on Pixel Manifolds (RWPM) RWPM utilizes random walks to reveal the intrinsic relationships among pixels to refine the pixel embeddings. Our experiments show that RWPM consistently improve the performance of the existing anomaly segmentation methods.
• Score: 1.3581810800092389
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In anomaly segmentation for complex driving scenes, state-of-the-art approaches utilize anomaly scoring functions to calculate anomaly scores. For these functions, accurately predicting the logits of inlier classes for each pixel is crucial for precisely inferring the anomaly score. However, in real-world driving scenarios, the diversity of scenes often results in distorted manifolds of pixel embeddings in the space. This effect is not conducive to directly using the pixel embeddings for the logit prediction during inference, a concern overlooked by existing methods. To address this problem, we propose a novel method called Random Walk on Pixel Manifolds (RWPM). RWPM utilizes random walks to reveal the intrinsic relationships among pixels to refine the pixel embeddings. The refined pixel embeddings alleviate the distortion of manifolds, improving the accuracy of anomaly scores. Our extensive experiments show that RWPM consistently improve the performance of the existing anomaly segmentation methods and achieve the best results. Code is available at: \url{https://github.com/ZelongZeng/RWPM}.

Related papers

• Smooth-edged Perturbations Improve Perturbation-based Image Explanations [1.1663475941322277]
  Perturbation-based post-hoc image explanation methods are commonly used to explain image prediction models. Due to the intractability of perturbing each pixel individually, images are typically attributed to larger segments. This work tests many combinations of mask sampling, segmentation techniques, smoothing, and attribution calculation.
  arXiv  Detail & Related papers  (2024-09-06T08:33:26Z)
• Learning to Make Keypoints Sub-Pixel Accurate [80.55676599677824]
  This work addresses the challenge of sub-pixel accuracy in detecting 2D local features. We propose a novel network that enhances any detector with sub-pixel precision by learning an offset vector for detected features.
  arXiv  Detail & Related papers  (2024-07-16T12:39:56Z)
• Restoring Images in Adverse Weather Conditions via Histogram Transformer [75.74328579778049]
  We propose an efficient Histogram Transformer (Histoformer) for restoring images affected by adverse weather. It is powered by a mechanism dubbed histogram self-attention, which sorts and segments spatial features into intensity-based bins. To boost histogram self-attention, we present a dynamic-range convolution enabling conventional convolution to conduct operation over similar pixels.
  arXiv  Detail & Related papers  (2024-07-14T11:59:22Z)
• Real-World Efficient Blind Motion Deblurring via Blur Pixel Discretization [45.20189929583484]
  We decompose the deblurring (regression) task into blur pixel discretization and discrete-to-continuous conversion tasks. Specifically, we generate the discretized image residual errors by identifying the blur pixels and then transform them to a continuous form.
  arXiv  Detail & Related papers  (2024-04-18T13:22:56Z)
• Pixel-Inconsistency Modeling for Image Manipulation Localization [63.54342601757723]
  Digital image forensics plays a crucial role in image authentication and manipulation localization. This paper presents a generalized and robust manipulation localization model through the analysis of pixel inconsistency artifacts. Experiments show that our method successfully extracts inherent pixel-inconsistency forgery fingerprints.
  arXiv  Detail & Related papers  (2023-09-30T02:54:51Z)
• UGainS: Uncertainty Guided Anomaly Instance Segmentation [80.12253291709673]
  A single unexpected object on the road can cause an accident or lead to injuries. Current approaches tackle anomaly segmentation by assigning an anomaly score to each pixel. We propose an approach that produces accurate anomaly instance masks.
  arXiv  Detail & Related papers  (2023-08-03T20:55:37Z)
• Feature Tracks are not Zero-Mean Gaussian [63.51990384359593]
  It is customary to assume that the errors in feature track positions are zero-mean Gaussian. Using a combination of calibrated camera intrinsics, ground-truth camera pose, and depth images, it is possible to compute ground-truth positions for feature tracks extracted using an image processing algorithm.
  arXiv  Detail & Related papers  (2023-03-25T00:58:30Z)
• BezierSeg: Parametric Shape Representation for Fast Object Segmentation in Medical Images [4.155973181136616]
  We propose the BezierSeg model which outputs bezier curves encompassing the region of interest. directly modelling the contour with analytic equations ensures that the segmentation is connected, continuous, and the boundary is smooth. Experiments show that the proposed method runs in real time and achieves accuracy competitive with pixel-wise segmentation models.
  arXiv  Detail & Related papers  (2021-08-02T10:10:57Z)
• Pixel-wise Anomaly Detection in Complex Driving Scenes [30.884375526254836]
  We present a pixel-wise anomaly detection framework that uses uncertainty maps to improve anomaly detection. Our approach works as a general framework around already trained segmentation networks. Top-2 performance across a range of different anomaly datasets shows the robustness of our approach to handling different anomaly instances.
  arXiv  Detail & Related papers  (2021-03-09T14:26:20Z)
• SegFix: Model-Agnostic Boundary Refinement for Segmentation [75.58050758615316]
  We present a model-agnostic post-processing scheme to improve the boundary quality for the segmentation result that is generated by any existing segmentation model. Motivated by the empirical observation that the label predictions of interior pixels are more reliable, we propose to replace the originally unreliable predictions of boundary pixels by the predictions of interior pixels.
  arXiv  Detail & Related papers  (2020-07-08T17:08:08Z)

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.