Enhancing Semantic Segmentation with Adaptive Focal Loss: A Novel Approach

• URL: http://arxiv.org/abs/2407.09828v1
• Date: Sat, 13 Jul 2024 09:41:20 GMT
• Title: Enhancing Semantic Segmentation with Adaptive Focal Loss: A Novel Approach
• Abstract summary: We introduce an Adaptive Focal Loss function designed to mitigate class imbalance by down-weighting the loss for easy examples. We evaluate the performance of the A-FL using ResNet50-encoded U-Net architecture on the Picai 2022 and BraTS 2018 datasets. This work highlights A-FL's potential to improve deep learning models for segmenting clinically significant regions in medical images.
• Score: 21.134077729826107
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep learning has achieved outstanding accuracy in medical image segmentation, particularly for objects like organs or tumors with smooth boundaries or large sizes. Whereas, it encounters significant difficulties with objects that have zigzag boundaries or are small in size, leading to a notable decrease in segmentation effectiveness. In this context, using a loss function that incorporates smoothness and volume information into a model's predictions offers a promising solution to these shortcomings. In this work, we introduce an Adaptive Focal Loss (A-FL) function designed to mitigate class imbalance by down-weighting the loss for easy examples that results in up-weighting the loss for hard examples and giving greater emphasis to challenging examples, such as small and irregularly shaped objects. The proposed A-FL involves dynamically adjusting a focusing parameter based on an object's surface smoothness, size information, and adjusting the class balancing parameter based on the ratio of targeted area to total area in an image. We evaluated the performance of the A-FL using ResNet50-encoded U-Net architecture on the Picai 2022 and BraTS 2018 datasets. On the Picai 2022 dataset, the A-FL achieved an Intersection over Union (IoU) of 0.696 and a Dice Similarity Coefficient (DSC) of 0.769, outperforming the regular Focal Loss (FL) by 5.5% and 5.4% respectively. It also surpassed the best baseline Dice-Focal by 2.0% and 1.2%. On the BraTS 2018 dataset, A-FL achieved an IoU of 0.883 and a DSC of 0.931. The comparative studies show that the proposed A-FL function surpasses conventional methods, including Dice Loss, Focal Loss, and their hybrid variants, in IoU, DSC, Sensitivity, and Specificity metrics. This work highlights A-FL's potential to improve deep learning models for segmenting clinically significant regions in medical images, leading to more precise and reliable diagnostic tools.

Related papers

• HADS-Net:A Hybrid Attention-Augmented Dual-Stream Network with Physics-Informed Augmentation for Breast Ultrasound Image Classification [0.04999814847776097]
  HADS-Net is a Hybrid Attention-Augmented Dual-Stream Network.<n>It exploits global texture and local boundary cues through two parallel pathways.<n>It achieves 96.58% accuracy, macro ROC-AUC of 0.9978, macro F1 of 0.9654, and per-class F1-scores of 0.970, 0.951, and 0.976 for benign, malignant, and normal.
  arXiv  Detail & Related papers  (2026-05-19T22:16:24Z)
• HEART-PFL: Stable Personalized Federated Learning under Heterogeneity with Hierarchical Directional Alignment and Adversarial Knowledge Transfer [28.18683870049843]
  HEART-PFL is a dual-sided framework that performs depth-aware Hierarchical Directional Alignment.<n>It stabilizes global updates through Adversarial Knowledge Transfer (AKT) with symmetric KL distillation on clean and adversarial proxy data.<n>Using lightweight adapters with only 1.46M trainable parameters, HEART-PFL achieves state-of-the-art personalized accuracy.
  arXiv  Detail & Related papers  (2026-03-25T11:35:07Z)
• The MICCAI Federated Tumor Segmentation (FeTS) Challenge 2024: Efficient and Robust Aggregation Methods for Federated Learning [9.202327404631289]
  We present the design and results of the MICCAI Federated Tumor (FeTS) Challenge 2024.<n>It focuses on federated learning for glioma sub-region segmentation in multi-parametric MRI.<n>A PID-controller-based method achieved the top overall ranking.
  arXiv  Detail & Related papers  (2025-12-05T22:59:57Z)
• LFRA-Net: A Lightweight Focal and Region-Aware Attention Network for Retinal Vessel Segmentatio [4.5211402678313135]
  LFRA-Net is a lightweight network optimized for precise and effective retinal vascular segmentation.<n>It enhances feature representation and regional focus by efficiently capturing local and global dependencies.<n>LFRA-Net provides an ideal ratio between segmentation accuracy and computational cost compared to existing deep learning methods.
  arXiv  Detail & Related papers  (2025-09-15T11:47:51Z)
• DCFFSNet: Deep Connectivity Feature Fusion Separation Network for Medical Image Segmentation [14.06374058427024]
  We propose DCFFSNet (Dual-Connectivity Feature Fusion-Separation Network) for medical image segmentation.<n>It quantifies the strength between connectivity features and other features and builds a deep connectivity feature fusion-separation architecture.<n>It effectively resolves segmentation fragmentation and achieves smooth edge transitions.
  arXiv  Detail & Related papers  (2025-07-24T13:46:50Z)
• Ultra-Resolution Adaptation with Ease [62.56434979517156]
  We propose a set of key guidelines for ultra-resolution adaptation termed emphURAE. We show that tuning minor components of the weight matrices outperforms widely-used low-rank adapters when synthetic data are unavailable. Experiments validate that URAE achieves comparable 2K-generation performance to state-of-the-art closed-source models like FLUX1.1 [Pro] Ultra with only 3K samples and 2K iterations.
  arXiv  Detail & Related papers  (2025-03-20T16:44:43Z)
• SPFFNet: Strip Perception and Feature Fusion Spatial Pyramid Pooling for Fabric Defect Detection [0.0]
  We propose an improved fabric defect detection model based on YOLOv11. We introduce a Strip Perception Module (SPM) that improves feature capture through multi-scale convolution. We also propose a novel focal enhanced complete intersection over union (FECIoU) metric with adaptive weights.
  arXiv  Detail & Related papers  (2025-02-03T15:33:11Z)
• Federated Learning with Partially Labeled Data: A Conditional Distillation Approach [6.539281169155941]
  We propose ConDistFL, a novel FL framework incorporating conditional distillation to address medical image segmentation challenges. ConDistFL enables effective learning from partially labeled datasets, significantly improving segmentation accuracy across distributed and non-uniform datasets. In addition to its superior segmentation performance, ConDistFL maintains computational and communication efficiency, ensuring its scalability for real-world applications.
  arXiv  Detail & Related papers  (2024-12-25T08:40:03Z)
• FedGS: Federated Gradient Scaling for Heterogeneous Medical Image Segmentation [0.4499833362998489]
  We propose FedGS, a novel FL aggregation method, to improve segmentation performance on small, under-represented targets. FedGS demonstrates superior performance over FedAvg, particularly for small lesions, across PolypGen and LiTS datasets.
  arXiv  Detail & Related papers  (2024-08-21T15:26:21Z)
• Federated Learning under Partially Class-Disjoint Data via Manifold Reshaping [64.58402571292723]
  We propose a manifold reshaping approach called FedMR to calibrate the feature space of local training. We conduct extensive experiments on a range of datasets to demonstrate that our FedMR achieves much higher accuracy and better communication efficiency.
  arXiv  Detail & Related papers  (2024-05-29T10:56:13Z)
• MergeSFL: Split Federated Learning with Feature Merging and Batch Size Regulation [27.159538773609917]
  Federated learning (FL) is a technique for edge AI to mine valuable knowledge in edge computing (EC) systems. We propose a novel SFL framework, termed MergeSFL, by incorporating feature merging and batch size regulation in SFL. We show that MergeSFL can improve the final model accuracy by 5.82% to 26.22%, with a speedup by about 1.74x to 4.14x, compared to the baselines.
  arXiv  Detail & Related papers  (2023-11-22T12:25:02Z)
• DFedADMM: Dual Constraints Controlled Model Inconsistency for Decentralized Federated Learning [52.83811558753284]
  Decentralized learning (DFL) discards the central server and establishes a decentralized communication network. Existing DFL methods still suffer from two major challenges: local inconsistency and local overfitting.
  arXiv  Detail & Related papers  (2023-08-16T11:22:36Z)
• 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)
• Hierarchical Personalized Federated Learning Over Massive Mobile Edge Computing Networks [95.39148209543175]
  We propose hierarchical PFL (HPFL), an algorithm for deploying PFL over massive MEC networks. HPFL combines the objectives of training loss minimization and round latency minimization while jointly determining the optimal bandwidth allocation.
  arXiv  Detail & Related papers  (2023-03-19T06:00:05Z)
• An Adaptive Plug-and-Play Network for Few-Shot Learning [12.023266104119289]
  Few-shot learning requires a model to classify new samples after learning from only a few samples. Deep networks and complex metrics tend to induce overfitting, making it difficult to further improve the performance. We propose plug-and-play model-adaptive resizer (MAR) and adaptive similarity metric (ASM) without any other losses.
  arXiv  Detail & Related papers  (2023-02-18T13:25:04Z)
• Towards Fairer and More Efficient Federated Learning via Multidimensional Personalized Edge Models [36.84027517814128]
  Federated learning (FL) trains massive and geographically distributed edge data while maintaining privacy. We propose a Customized Federated Learning (CFL) system to eliminate FL heterogeneity from multiple dimensions. CFL tailors personalized models from the specially designed global model for each client jointly guided by an online trained model-search helper and a novel aggregation algorithm.
  arXiv  Detail & Related papers  (2023-02-09T06:55:19Z)
• DilateFormer: Multi-Scale Dilated Transformer for Visual Recognition [62.95223898214866]
  We explore effective Vision Transformers to pursue a preferable trade-off between the computational complexity and size of the attended receptive field. With a pyramid architecture, we construct a Multi-Scale Dilated Transformer (DilateFormer) by stacking MSDA blocks at low-level stages and global multi-head self-attention blocks at high-level stages. Our experiment results show that our DilateFormer achieves state-of-the-art performance on various vision tasks.
  arXiv  Detail & Related papers  (2023-02-03T14:59:31Z)
• Robust Split Federated Learning for U-shaped Medical Image Networks [16.046153872932653]
  We propose Robust Split Federated Learning (RoS-FL) for U-shaped medical image networks. RoS-FL is a novel hybrid learning paradigm of Federated Learning (FL) and Split Learning (SL)
  arXiv  Detail & Related papers  (2022-12-13T05:26:31Z)
• 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)
• Multi-Scale Context-Guided Lumbar Spine Disease Identification with Coarse-to-fine Localization and Classification [22.62393344071125]
  This work introduces a multi-scale context-guided network with coarse-to-fine localization and classification, named CCF-Net, for lumbar spine disease identification. The experimental results show that the coarse-to-fine design presents the potential to achieve high performance with fewer parameters and data requirements.
  arXiv  Detail & Related papers  (2022-03-16T05:51:16Z)
• Orthogonal Projection Loss [59.61277381836491]
  We develop a novel loss function termed Orthogonal Projection Loss' (OPL) OPL directly enforces inter-class separation alongside intra-class clustering in the feature space. OPL offers unique advantages as it does not require careful negative mining and is not sensitive to the batch size.
  arXiv  Detail & Related papers  (2021-03-25T17:58:00Z)
• DONet: Dual Objective Networks for Skin Lesion Segmentation [77.9806410198298]
  We propose a simple yet effective framework, named Dual Objective Networks (DONet), to improve the skin lesion segmentation. Our DONet adopts two symmetric decoders to produce different predictions for approaching different objectives. To address the challenge of large variety of lesion scales and shapes in dermoscopic images, we additionally propose a recurrent context encoding module (RCEM)
  arXiv  Detail & Related papers  (2020-08-19T06:02:46Z)
• Deep F-measure Maximization for End-to-End Speech Understanding [52.36496114728355]
  We propose a differentiable approximation to the F-measure and train the network with this objective using standard backpropagation. We perform experiments on two standard fairness datasets, Adult, Communities and Crime, and also on speech-to-intent detection on the ATIS dataset and speech-to-image concept classification on the Speech-COCO dataset. In all four of these tasks, F-measure results in improved micro-F1 scores, with absolute improvements of up to 8% absolute, as compared to models trained with the cross-entropy loss function.
  arXiv  Detail & Related papers  (2020-08-08T03:02:27Z)
• Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection [85.53263670166304]
  One-stage detector basically formulates object detection as dense classification and localization. Recent trend for one-stage detectors is to introduce an individual prediction branch to estimate the quality of localization. This paper delves into the representations of the above three fundamental elements: quality estimation, classification and localization.
  arXiv  Detail & Related papers  (2020-06-08T07:24:33Z)
• Enhancing Geometric Factors in Model Learning and Inference for Object Detection and Instance Segmentation [91.12575065731883]
  We propose Complete-IoU (CIoU) loss and Cluster-NMS for enhancing geometric factors in both bounding box regression and Non-Maximum Suppression (NMS) The training of deep models using CIoU loss results in consistent AP and AR improvements in comparison to widely adopted $ell_n$-norm loss and IoU-based loss. Cluster-NMS is very efficient due to its pure GPU implementation, and geometric factors can be incorporated to improve both AP and AR.
  arXiv  Detail & Related papers  (2020-05-07T16:00:27Z)
• Calibrating Deep Neural Networks using Focal Loss [77.92765139898906]
  Miscalibration is a mismatch between a model's confidence and its correctness. We show that focal loss allows us to learn models that are already very well calibrated. We show that our approach achieves state-of-the-art calibration without compromising on accuracy in almost all cases.
  arXiv  Detail & Related papers  (2020-02-21T17:35:50Z)

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.