Deep Learning From Crowdsourced Labels: Coupled Cross-entropy Minimization, Identifiability, and Regularization

• URL: http://arxiv.org/abs/2306.03288v1
• Date: Mon, 5 Jun 2023 22:21:26 GMT
• Title: Deep Learning From Crowdsourced Labels: Coupled Cross-entropy Minimization, Identifiability, and Regularization
• Authors: Shahana Ibrahim, Tri Nguyen, Xiao Fu
• Abstract summary: A deep learning-based end-to-end (E2E) system uses noisy crowdsourced labels from multiple annotators. Many E2E systems co-train the neural classifier with multiple annotator-specific label confusion'' layers. This work presents performance guarantees of the CCEM criterion and two regularized variants of the CCEM.
• Score: 21.32957828106532
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Using noisy crowdsourced labels from multiple annotators, a deep learning-based end-to-end (E2E) system aims to learn the label correction mechanism and the neural classifier simultaneously. To this end, many E2E systems concatenate the neural classifier with multiple annotator-specific ``label confusion'' layers and co-train the two parts in a parameter-coupled manner. The formulated coupled cross-entropy minimization (CCEM)-type criteria are intuitive and work well in practice. Nonetheless, theoretical understanding of the CCEM criterion has been limited. The contribution of this work is twofold: First, performance guarantees of the CCEM criterion are presented. Our analysis reveals for the first time that the CCEM can indeed correctly identify the annotators' confusion characteristics and the desired ``ground-truth'' neural classifier under realistic conditions, e.g., when only incomplete annotator labeling and finite samples are available. Second, based on the insights learned from our analysis, two regularized variants of the CCEM are proposed. The regularization terms provably enhance the identifiability of the target model parameters in various more challenging cases. A series of synthetic and real data experiments are presented to showcase the effectiveness of our approach.

Related papers

• Adaptive Gradient Calibration for Single-Positive Multi-Label Learning in Remote Sensing Image Scene Classification [20.29420915336209]
  Multi-label classification (MLC) offers a more comprehensive semantic understanding of Remote Sensing (RS) imagery.<n>Single-positive multi-label learning (SPML) has emerged, where each image is annotated with only one relevant label, and the model is expected to recover the full set of labels.<n>We propose Adaptive Gradient (AdaGC) as a novel and generalizable SPML framework tailored to RS imagery.
  arXiv  Detail & Related papers  (2025-10-09T14:26:09Z)
• Hierarchical Self-Supervised Representation Learning for Depression Detection from Speech [51.14752758616364]
  Speech-based depression detection (SDD) is a promising, non-invasive alternative to traditional clinical assessments.<n>We propose HAREN-CTC, a novel architecture that integrates multi-layer SSL features using cross-attention within a multitask learning framework.<n>The model achieves state-of-the-art macro F1-scores of 0.81 on DAIC-WOZ and 0.82 on MODMA, outperforming prior methods across both evaluation scenarios.
  arXiv  Detail & Related papers  (2025-10-05T09:32:12Z)
• CoPS: Conditional Prompt Synthesis for Zero-Shot Anomaly Detection [6.1568149026052374]
  Conditional Prompt Synthesis (CoPS) is a novel framework that synthesizes dynamic prompts conditioned on visual features to enhance ZSAD performance.<n>CoPS surpasses state-of-the-art methods by 2.5% AUROC in both classification and segmentation across 13 industrial and medical datasets.
  arXiv  Detail & Related papers  (2025-08-05T13:47:45Z)
• Zero-Shot Anomaly Detection with Dual-Branch Prompt Learning [17.263625932911534]
  Zero-shot anomaly detection (ZSAD) enables identifying and localizing defects in unseen categories.<n>Existing ZSAD methods, whether using fixed or learned prompts, struggle under domain shifts because their training data are derived from limited training domains.<n>We introduce PILOT, a framework designed to overcome these challenges through two key innovations.
  arXiv  Detail & Related papers  (2025-08-01T17:00:12Z)
• Generalized Class Discovery in Instance Segmentation [7.400926717561454]
  We propose an instance-wise temperature assignment (ITA) method for contrastive learning and class-wise reliability criteria for pseudo-labels. We evaluate our proposed method by conducting experiments on two settings: COCO$_half$ + LVIS and LVIS + Visual Genome.
  arXiv  Detail & Related papers  (2025-02-12T06:26:05Z)
• Ultrasound Nodule Segmentation Using Asymmetric Learning with Simple Clinical Annotation [25.459627476201646]
  We suggest using simple aspect ratio annotations directly from ultrasound clinical diagnoses for automated nodule segmentation. An asymmetric learning framework is developed by extending the aspect ratio annotations with two types of pseudo labels. Experiments on two clinically collected ultrasound datasets (thyroid and breast) demonstrate the superior performance of our proposed method.
  arXiv  Detail & Related papers  (2024-04-23T09:07:04Z)
• Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection [98.66771688028426]
  We propose a Ambiguity-Resistant Semi-supervised Learning (ARSL) for one-stage detectors. Joint-Confidence Estimation (JCE) is proposed to quantifies the classification and localization quality of pseudo labels. ARSL effectively mitigates the ambiguities and achieves state-of-the-art SSOD performance on MS COCO and PASCAL VOC.
  arXiv  Detail & Related papers  (2023-03-27T07:46:58Z)
• A Theoretical Understanding of Shallow Vision Transformers: Learning, Generalization, and Sample Complexity [71.11795737362459]
  ViTs with self-attention modules have recently achieved great empirical success in many tasks. However, theoretical learning generalization analysis is mostly noisy and elusive. This paper provides the first theoretical analysis of a shallow ViT for a classification task.
  arXiv  Detail & Related papers  (2023-02-12T22:12:35Z)
• Learning Classifiers of Prototypes and Reciprocal Points for Universal Domain Adaptation [79.62038105814658]
  Universal Domain aims to transfer the knowledge between datasets by handling two shifts: domain-shift and categoryshift. Main challenge is correctly distinguishing the unknown target samples while adapting the distribution of known class knowledge from source to target. Most existing methods approach this problem by first training the target adapted known and then relying on the single threshold to distinguish unknown target samples.
  arXiv  Detail & Related papers  (2022-12-16T09:01:57Z)
• On Robust Learning from Noisy Labels: A Permutation Layer Approach [53.798757734297986]
  This paper introduces a permutation layer learning approach termed PermLL to dynamically calibrate the training process of a deep neural network (DNN) We provide two variants of PermLL in this paper: one applies the permutation layer to the model's prediction, while the other applies it directly to the given noisy label. We validate PermLL experimentally and show that it achieves state-of-the-art performance on both real and synthetic datasets.
  arXiv  Detail & Related papers  (2022-11-29T03:01:48Z)
• Parametric Classification for Generalized Category Discovery: A Baseline Study [70.73212959385387]
  Generalized Category Discovery (GCD) aims to discover novel categories in unlabelled datasets using knowledge learned from labelled samples. We investigate the failure of parametric classifiers, verify the effectiveness of previous design choices when high-quality supervision is available, and identify unreliable pseudo-labels as a key problem. We propose a simple yet effective parametric classification method that benefits from entropy regularisation, achieves state-of-the-art performance on multiple GCD benchmarks and shows strong robustness to unknown class numbers.
  arXiv  Detail & Related papers  (2022-11-21T18:47:11Z)
• The Overlooked Classifier in Human-Object Interaction Recognition [82.20671129356037]
  We encode the semantic correlation among classes into the classification head by initializing the weights with language embeddings of HOIs. We propose a new loss named LSE-Sign to enhance multi-label learning on a long-tailed dataset. Our simple yet effective method enables detection-free HOI classification, outperforming the state-of-the-arts that require object detection and human pose by a clear margin.
  arXiv  Detail & Related papers  (2022-03-10T23:35:00Z)
• Robust Neural Network Classification via Double Regularization [2.41710192205034]
  We propose a novel double regularization of the neural network training loss that combines a penalty on the complexity of the classification model and an optimal reweighting of training observations. We demonstrate DRFit, for neural net classification of (i) MNIST and (ii) CIFAR-10, in both cases with simulated mislabeling.
  arXiv  Detail & Related papers  (2021-12-15T13:19:20Z)
• Robust Classification of High-Dimensional Spectroscopy Data Using Deep Learning and Data Synthesis [0.5801044612920815]
  A novel application of a locally-connected neural network (NN) for the binary classification of spectroscopy data is proposed. A two-step classification process is presented as an alternative to the binary and one-class classification paradigms.
  arXiv  Detail & Related papers  (2020-03-26T11:33:52Z)

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.