PAT: Pixel-wise Adaptive Training for Long-tailed Segmentation

• URL: http://arxiv.org/abs/2404.05393v4
• Date: Sun, 20 Oct 2024 16:20:16 GMT
• Title: PAT: Pixel-wise Adaptive Training for Long-tailed Segmentation
• Abstract summary: We propose an innovative Pixel-wise Adaptive Training (PAT) technique tailored for long-tailed segmentation. PAT has two key features: 1) class-wise gradient magnitude homogenization, and 2) pixel-wise class-specific loss adaptation (PCLA) PAT exhibits significant performance improvements, surpassing the current state-of-the-art by 2.2% in the NyU dataset.
• Score: 4.384837621499638
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Beyond class frequency, we recognize the impact of class-wise relationships among various class-specific predictions and the imbalance in label masks on long-tailed segmentation learning. To address these challenges, we propose an innovative Pixel-wise Adaptive Training (PAT) technique tailored for long-tailed segmentation. PAT has two key features: 1) class-wise gradient magnitude homogenization, and 2) pixel-wise class-specific loss adaptation (PCLA). First, the class-wise gradient magnitude homogenization helps alleviate the imbalance among label masks by ensuring equal consideration of the class-wise impact on model updates. Second, PCLA tackles the detrimental impact of both rare classes within the long-tailed distribution and inaccurate predictions from previous training stages by encouraging learning classes with low prediction confidence and guarding against forgetting classes with high confidence. This combined approach fosters robust learning while preventing the model from forgetting previously learned knowledge. PAT exhibits significant performance improvements, surpassing the current state-of-the-art by 2.2% in the NyU dataset. Moreover, it enhances overall pixel-wise accuracy by 2.85% and intersection over union value by 2.07%, with a particularly notable declination of 0.39% in detecting rare classes compared to Balance Logits Variation, as demonstrated on the three popular datasets, i.e., OxfordPetIII, CityScape, and NYU.

Related papers

• MoTiC: Momentum Tightness and Contrast for Few-Shot Class-Incremental Learning [20.22260611239967]
  Few-Shot Class-Incremental Learning (FSCIL) must contend with the dual challenge of learning new classes from scarce samples while preserving old class knowledge.<n>New-class prototypes suffer significant estimation bias due to extreme data scarcity, whereas base-class prototypes benefit from sufficient data.<n>We show that aligning the new-class priors with old-class statistics via Bayesian analysis reduces variance and improves prototype accuracy.
  arXiv  Detail & Related papers  (2025-09-24T00:41:40Z)
• ART: Adaptive Resampling-based Training for Imbalanced Classification [0.0]
  This paper proposes an Adaptive Resampling-based Training (ART) method for handling class imbalance.<n>ART periodically updates the distribution of the training data based on the class-wise performance of the model.<n>Results on diverse benchmarks demonstrate that ART consistently outperforms both resampling-based and algorithm-level methods.
  arXiv  Detail & Related papers  (2025-08-31T18:20:55Z)
• ViRN: Variational Inference and Distribution Trilateration for Long-Tailed Continual Representation Learning [6.253882111488726]
  ViRN is a novel framework that integrates variational inference with distributional trilateration for robust long-tailed learning.<n> evaluated on six long-tailed classification benchmarks, including speech (e.g., rare acoustic events, accents) and image tasks.<n> achieves a 10.24% average accuracy gain over state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-07-23T10:04:30Z)
• Bayesian Learning-driven Prototypical Contrastive Loss for Class-Incremental Learning [42.14439854721613]
  We propose a prototypical network with a Bayesian learning-driven contrastive loss (BLCL) tailored specifically for class-incremental learning scenarios. Our approach dynamically adapts the balance between the cross-entropy and contrastive loss functions with a Bayesian learning technique.
  arXiv  Detail & Related papers  (2024-05-17T19:49:02Z)
• Better (pseudo-)labels for semi-supervised instance segmentation [21.703173564795353]
  We introduce a dual-strategy to enhance the teacher model's training process, substantially improving the performance on few-shot learning. We observe marked improvements over a state-of-the-art supervised baseline performance on the LVIS dataset, with an increase of 2.8% in average precision (AP) and 10.3% gain in AP for rare classes.
  arXiv  Detail & Related papers  (2024-03-18T11:23:02Z)
• Class-Imbalanced Semi-Supervised Learning for Large-Scale Point Cloud Semantic Segmentation via Decoupling Optimization [64.36097398869774]
  Semi-supervised learning (SSL) has been an active research topic for large-scale 3D scene understanding. The existing SSL-based methods suffer from severe training bias due to class imbalance and long-tail distributions of the point cloud data. We introduce a new decoupling optimization framework, which disentangles feature representation learning and classifier in an alternative optimization manner to shift the bias decision boundary effectively.
  arXiv  Detail & Related papers  (2024-01-13T04:16:40Z)
• Uncertainty-aware Sampling for Long-tailed Semi-supervised Learning [89.98353600316285]
  We introduce uncertainty into the modeling process for pseudo-label sampling, taking into account that the model performance on the tailed classes varies over different training stages. This approach allows the model to perceive the uncertainty of pseudo-labels at different training stages, thereby adaptively adjusting the selection thresholds for different classes. Compared to other methods such as the baseline method FixMatch, UDTS achieves an increase in accuracy of at least approximately 5.26%, 1.75%, 9.96%, and 1.28% on the natural scene image datasets.
  arXiv  Detail & Related papers  (2024-01-09T08:59:39Z)
• Understanding the Detrimental Class-level Effects of Data Augmentation [63.1733767714073]
  achieving optimal average accuracy comes at the cost of significantly hurting individual class accuracy by as much as 20% on ImageNet. We present a framework for understanding how DA interacts with class-level learning dynamics. We show that simple class-conditional augmentation strategies improve performance on the negatively affected classes.
  arXiv  Detail & Related papers  (2023-12-07T18:37:43Z)
• Class Balanced Dynamic Acquisition for Domain Adaptive Semantic Segmentation using Active Learning [3.175227858236288]
  Domain adaptive active learning is leading the charge in label-efficient training of neural networks. For semantic segmentation, state-of-the-art models jointly use two criteria of uncertainty and diversity to select training labels. We show that such methods currently suffer from a class imbalance issue which degrades their performance for larger active learning budgets.
  arXiv  Detail & Related papers  (2023-11-23T18:35:26Z)
• Uncertainty-guided Boundary Learning for Imbalanced Social Event Detection [64.4350027428928]
  We propose a novel uncertainty-guided class imbalance learning framework for imbalanced social event detection tasks. Our model significantly improves social event representation and classification tasks in almost all classes, especially those uncertain ones.
  arXiv  Detail & Related papers  (2023-10-30T03:32:04Z)
• Exploring Classification Equilibrium in Long-Tailed Object Detection [29.069986049436157]
  We propose to use the mean classification score to indicate the classification accuracy for each category during training. We balance the classification via an Equilibrium Loss (EBL) and a Memory-augmented Feature Sampling (MFS) method. It improves the detection performance of tail classes by 15.6 AP, and outperforms the most recent long-tailed object detectors by more than 1 AP.
  arXiv  Detail & Related papers  (2021-08-17T08:39:04Z)
• Semi-supervised Contrastive Learning with Similarity Co-calibration [72.38187308270135]
  We propose a novel training strategy, termed as Semi-supervised Contrastive Learning (SsCL) SsCL combines the well-known contrastive loss in self-supervised learning with the cross entropy loss in semi-supervised learning. We show that SsCL produces more discriminative representation and is beneficial to few shot learning.
  arXiv  Detail & Related papers  (2021-05-16T09:13:56Z)
• Robust Pre-Training by Adversarial Contrastive Learning [120.33706897927391]
  Recent work has shown that, when integrated with adversarial training, self-supervised pre-training can lead to state-of-the-art robustness. We improve robustness-aware self-supervised pre-training by learning representations consistent under both data augmentations and adversarial perturbations.
  arXiv  Detail & Related papers  (2020-10-26T04:44:43Z)

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.