Pixel-Wise Feature Selection for Perceptual Edge Detection without post-processing
- URL: http://arxiv.org/abs/2501.02534v1
- Date: Sun, 05 Jan 2025 13:28:37 GMT
- Title: Pixel-Wise Feature Selection for Perceptual Edge Detection without post-processing
- Authors: Hao Shu,
- Abstract summary: This paper proposes a novel feature selection paradigm for deep networks that facilitates the differential selection of features and can be seamlessly integrated into existing ED models.
By incorporating this additional structure, the performance of conventional ED models is substantially enhanced without post-processing, while simultaneously enhancing the perceptual quality of the predictions.
- Score: 0.0
- License:
- Abstract: Although deep convolutional neutral networks (CNNs) have significantly enhanced performance in image edge detection (ED), current models remain highly dependent on post-processing techniques such as non-maximum suppression (NMS), and often fail to deliver satisfactory perceptual results, while the performance will deteriorate significantly if the allowed error toleration distance decreases. These limitations arise from the uniform fusion of features across all pixels, regardless of their specific characteristics, such as the distinction between textural and edge areas. If the features extracted by the ED models are selected more meticulously and encompass greater diversity, the resulting predictions are expected to be more accurate and perceptually meaningful. Motivated by this observation, this paper proposes a novel feature selection paradigm for deep networks that facilitates the differential selection of features and can be seamlessly integrated into existing ED models. By incorporating this additional structure, the performance of conventional ED models is substantially enhanced without post-processing, while simultaneously enhancing the perceptual quality of the predictions. Extensive experimental evaluations validate the effectiveness of the proposed model.
Related papers
- Enhanced Extractor-Selector Framework and Symmetrization Weighted Binary Cross-Entropy for Edge Detections [0.0]
Recent advancements have demonstrated the effectiveness of the extractor-selector (E-S) framework in edge detection (ED) tasks.
We propose an enhanced E-S architecture, which utilizes richer, less-loss feature representations.
We introduce a novel loss function, the Symmetrization Weight Binary Cross-Entropy (SWBCE), which simultaneously emphasizes both the recall of edge pixels and the suppression of erroneous edge predictions.
arXiv Detail & Related papers (2025-01-23T04:10:31Z) - Non-Linear Outlier Synthesis for Out-of-Distribution Detection [5.019613806273252]
We present NCIS, which enhances the quality of synthetic outliers by operating directly in the diffusion's model embedding space.
We demonstrate that these improvements yield new state-of-the-art OOD detection results on standard ImageNet100 and CIFAR100 benchmarks.
arXiv Detail & Related papers (2024-11-20T09:47:29Z) - Generative Edge Detection with Stable Diffusion [52.870631376660924]
Edge detection is typically viewed as a pixel-level classification problem mainly addressed by discriminative methods.
We propose a novel approach, named Generative Edge Detector (GED), by fully utilizing the potential of the pre-trained stable diffusion model.
We conduct extensive experiments on multiple datasets and achieve competitive performance.
arXiv Detail & Related papers (2024-10-04T01:52:23Z) - Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think [53.2706196341054]
We show that the perceived inefficiency was caused by a flaw in the inference pipeline that has so far gone unnoticed.
We perform end-to-end fine-tuning on top of the single-step model with task-specific losses and get a deterministic model that outperforms all other diffusion-based depth and normal estimation models.
arXiv Detail & Related papers (2024-09-17T16:58:52Z) - Feature Attenuation of Defective Representation Can Resolve Incomplete Masking on Anomaly Detection [1.0358639819750703]
In unsupervised anomaly detection (UAD) research, it is necessary to develop a computationally efficient and scalable solution.
We revisit the reconstruction-by-inpainting approach and rethink to improve it by analyzing strengths and weaknesses.
We propose Feature Attenuation of Defective Representation (FADeR) that only employs two layers which attenuates feature information of anomaly reconstruction.
arXiv Detail & Related papers (2024-07-05T15:44:53Z) - Uncertainty Quantification for Bird's Eye View Semantic Segmentation: Methods and Benchmarks [10.193504550494486]
This paper introduces a benchmark for predictive uncertainty quantification in BEV segmentation.
It focuses on the effectiveness of predicted uncertainty in identifying misclassified and out-of-distribution pixels, as well as calibration.
We propose the Uncertainty-Focal-Cross-Entropy loss, designed for highly imbalanced data, which consistently improves the segmentation quality and calibration.
arXiv Detail & Related papers (2024-05-31T16:32:46Z) - Neural Collapse Meets Differential Privacy: Curious Behaviors of NoisyGD with Near-perfect Representation Learning [36.954726737451224]
We consider the setting of a layer-peeled model in representation learning, which results in interesting phenomena related to learned features in deep learning and transfer learning.
We show that DP fine-tuning is less robust compared to fine-tuning without DP, particularly in the presence of perturbations.
arXiv Detail & Related papers (2024-05-14T19:18:19Z) - DetDiffusion: Synergizing Generative and Perceptive Models for Enhanced Data Generation and Perception [78.26734070960886]
Current perceptive models heavily depend on resource-intensive datasets.
We introduce perception-aware loss (P.A. loss) through segmentation, improving both quality and controllability.
Our method customizes data augmentation by extracting and utilizing perception-aware attribute (P.A. Attr) during generation.
arXiv Detail & Related papers (2024-03-20T04:58:03Z) - Variational Voxel Pseudo Image Tracking [127.46919555100543]
Uncertainty estimation is an important task for critical problems, such as robotics and autonomous driving.
We propose a Variational Neural Network-based version of a Voxel Pseudo Image Tracking (VPIT) method for 3D Single Object Tracking.
arXiv Detail & Related papers (2023-02-12T13:34:50Z) - Deep Variational Models for Collaborative Filtering-based Recommender
Systems [63.995130144110156]
Deep learning provides accurate collaborative filtering models to improve recommender system results.
Our proposed models apply the variational concept to injectity in the latent space of the deep architecture.
Results show the superiority of the proposed approach in scenarios where the variational enrichment exceeds the injected noise effect.
arXiv Detail & Related papers (2021-07-27T08:59:39Z) - Unleashing the Power of Contrastive Self-Supervised Visual Models via
Contrast-Regularized Fine-Tuning [94.35586521144117]
We investigate whether applying contrastive learning to fine-tuning would bring further benefits.
We propose Contrast-regularized tuning (Core-tuning), a novel approach for fine-tuning contrastive self-supervised visual models.
arXiv Detail & Related papers (2021-02-12T16:31:24Z)
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.