Investigating the Impact of Various Loss Functions and Learnable Wiener Filter for Laparoscopic Image Desmoking

• URL: http://arxiv.org/abs/2509.09849v1
• Date: Thu, 11 Sep 2025 20:58:52 GMT
• Title: Investigating the Impact of Various Loss Functions and Learnable Wiener Filter for Laparoscopic Image Desmoking
• Authors: Chengyu Yang, Chengjun Liu,
• Abstract summary: The aim of this study is to rigorously assess the effectiveness and necessity of individual components within the recently proposed ULW framework for laparoscopic image desmoking.<n>The framework combines a U-Net based backbone with a compound loss function that comprises mean squared error (MSE), structural similarity index (SSIM) loss, and perceptual loss.
• Score: 5.1261951744603715
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: To rigorously assess the effectiveness and necessity of individual components within the recently proposed ULW framework for laparoscopic image desmoking, this paper presents a comprehensive ablation study. The ULW approach combines a U-Net based backbone with a compound loss function that comprises mean squared error (MSE), structural similarity index (SSIM) loss, and perceptual loss. The framework also incorporates a differentiable, learnable Wiener filter module. In this study, each component is systematically ablated to evaluate its specific contribution to the overall performance of the whole framework. The analysis includes: (1) removal of the learnable Wiener filter, (2) selective use of individual loss terms from the composite loss function. All variants are benchmarked on a publicly available paired laparoscopic images dataset using quantitative metrics (SSIM, PSNR, MSE and CIEDE-2000) alongside qualitative visual comparisons.

Related papers

• Suppressing VLM Hallucinations with Spectral Representation Filtering [49.52703800684483]
  Vision-language models (VLMs) frequently produce hallucinations in the form of descriptions of objects, attributes, or relations that do not exist in the image.<n>We introduce Spectral Representation Filtering (SRF), a lightweight, training-free method to suppress such hallucinations by analyzing and correcting the covariance structure of the model's representations.
  arXiv  Detail & Related papers  (2025-11-15T13:49:27Z)
• Laparoscopic Image Desmoking Using the U-Net with New Loss Function and Integrated Differentiable Wiener Filter [5.747172898125006]
  Laparoscopic surgeries often suffer from reduced visual clarity due to the presence of surgical smoke originated by surgical instruments.<n>In order to remove the surgical smoke, a novel U-Net deep learning with new loss function and integrated differentiable Wiener filter (ULW) method is presented.<n> Experimental results show that the proposed ULW method excels in both visual clarity and metric-based evaluation.
  arXiv  Detail & Related papers  (2025-05-27T18:07:06Z)
• NCL-CIR: Noise-aware Contrastive Learning for Composed Image Retrieval [16.460121977322224]
  Composed Image Retrieval (CIR) seeks to find a target image using a multi-modal query, which combines an image with modification text to pinpoint the target.<n> pairs are often partially or completely mismatched due to issues like inaccurate modification texts, low-quality target images, and annotation errors.<n>We propose the Noise-aware Contrastive Learning for CIR (NCL-CIR) comprising two key components: the Weight Compensation Block (WCB) and the Noise-pair Filter Block (NFB).
  arXiv  Detail & Related papers  (2025-04-06T03:27:23Z)
• Speckle Noise Analysis for Synthetic Aperture Radar (SAR) Space Data [0.0]
  The study presents a comparative analysis of six distinct speckle noise reduction techniques. The performance of each technique was evaluated using a comprehensive set of metrics, including Peak Signal-to-Noise Ratio (PSNR), Mean Squared Error (MSE), Structural Similarity Index (SSIM), Equivalent Number of Looks (ENL), and Speckle Suppression Index (SSI)
  arXiv  Detail & Related papers  (2024-08-16T14:33:02Z)
• Toward a Better Understanding of Loss Functions for Collaborative Filtering [13.581193492311805]
  Collaborative filtering (CF) is a pivotal technique in modern recommender systems. Recent work shows that simply reformulating the loss functions can achieve significant performance gains. We propose a novel loss function that improves the design of alignment and uniformity.
  arXiv  Detail & Related papers  (2023-08-11T12:04:36Z)
• Class Anchor Margin Loss for Content-Based Image Retrieval [97.81742911657497]
  We propose a novel repeller-attractor loss that falls in the metric learning paradigm, yet directly optimize for the L2 metric without the need of generating pairs. We evaluate the proposed objective in the context of few-shot and full-set training on the CBIR task, by using both convolutional and transformer architectures.
  arXiv  Detail & Related papers  (2023-06-01T12:53:10Z)
• Impact of loss function in Deep Learning methods for accurate retinal vessel segmentation [1.1470070927586016]
  We compare Binary Cross Entropy, Dice, Tversky, and Combo loss using the deep learning architectures (i.e. U-Net, Attention U-Net, and Nested UNet) with the DRIVE dataset. The results showed that there is a significant difference in the selection of loss function.
  arXiv  Detail & Related papers  (2022-06-01T14:47:18Z)
• Shared Independent Component Analysis for Multi-Subject Neuroimaging [107.29179765643042]
  We introduce Shared Independent Component Analysis (ShICA) that models each view as a linear transform of shared independent components contaminated by additive Gaussian noise. We show that this model is identifiable if the components are either non-Gaussian or have enough diversity in noise variances. We provide empirical evidence on fMRI and MEG datasets that ShICA yields more accurate estimation of the components than alternatives.
  arXiv  Detail & Related papers  (2021-10-26T08:54:41Z)
• Quantification of pulmonary involvement in COVID-19 pneumonia by means of a cascade oftwo U-nets: training and assessment on multipledatasets using different annotation criteria [83.83783947027392]
  This study aims at exploiting Artificial intelligence (AI) for the identification, segmentation and quantification of COVID-19 pulmonary lesions. We developed an automated analysis pipeline, the LungQuant system, based on a cascade of two U-nets. The accuracy in predicting the CT-Severity Score (CT-SS) of the LungQuant system has been also evaluated.
  arXiv  Detail & Related papers  (2021-05-06T10:21:28Z)
• Out-of-distribution Generalization via Partial Feature Decorrelation [72.96261704851683]
  We present a novel Partial Feature Decorrelation Learning (PFDL) algorithm, which jointly optimize a feature decomposition network and the target image classification model. The experiments on real-world datasets demonstrate that our method can improve the backbone model's accuracy on OOD image classification datasets.
  arXiv  Detail & Related papers  (2020-07-30T05:48:48Z)
• Understanding Adversarial Examples from the Mutual Influence of Images and Perturbations [83.60161052867534]
  We analyze adversarial examples by disentangling the clean images and adversarial perturbations, and analyze their influence on each other. Our results suggest a new perspective towards the relationship between images and universal perturbations. We are the first to achieve the challenging task of a targeted universal attack without utilizing original training data.
  arXiv  Detail & Related papers  (2020-07-13T05:00:09Z)

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.