Unleashing the Potential of Model Bias for Generalized Category Discovery

• URL: http://arxiv.org/abs/2412.12501v1
• Date: Tue, 17 Dec 2024 03:05:27 GMT
• Title: Unleashing the Potential of Model Bias for Generalized Category Discovery
• Authors: Wenbin An, Haonan Lin, Jiahao Nie, Feng Tian, Wenkai Shi, Yaqiang Wu, Qianying Wang, Ping Chen,
• Abstract summary: Generalized Category Discovery is a significant task that aims to identify both known and undefined novel categories. The primary challenges stem from model bias induced by pre-training on only known categories and the lack of precise supervision for novel ones. We propose a novel framework named Self-Debiasing (SDC) to address these challenges.
• Score: 9.552403124453614
• License:
• Abstract: Generalized Category Discovery is a significant and complex task that aims to identify both known and undefined novel categories from a set of unlabeled data, leveraging another labeled dataset containing only known categories. The primary challenges stem from model bias induced by pre-training on only known categories and the lack of precise supervision for novel ones, leading to category bias towards known categories and category confusion among different novel categories, which hinders models' ability to identify novel categories effectively. To address these challenges, we propose a novel framework named Self-Debiasing Calibration (SDC). Unlike prior methods that regard model bias towards known categories as an obstacle to novel category identification, SDC provides a novel insight into unleashing the potential of the bias to facilitate novel category learning. Specifically, the output of the biased model serves two key purposes. First, it provides an accurate modeling of category bias, which can be utilized to measure the degree of bias and debias the output of the current training model. Second, it offers valuable insights for distinguishing different novel categories by transferring knowledge between similar categories. Based on these insights, SDC dynamically adjusts the output logits of the current training model using the output of the biased model. This approach produces less biased logits to effectively address the issue of category bias towards known categories, and generates more accurate pseudo labels for unlabeled data, thereby mitigating category confusion for novel categories. Experiments on three benchmark datasets show that SDC outperforms SOTA methods, especially in the identification of novel categories. Our code and data are available at \url{https://github.com/Lackel/SDC}.

Related papers

• Solving the Catastrophic Forgetting Problem in Generalized Category Discovery [46.63232918739251]
  Generalized Category Discovery (GCD) aims to identify a mix of known and novel categories within unlabeled data sets. Recent state-of-the-art method SimGCD transfers the knowledge from known-class data to the learning of novel classes through debiased learning. We propose a novel learning approach, LegoGCD, which is seamlessly integrated into previous methods to enhance the discrimination of novel classes.
  arXiv  Detail & Related papers  (2025-01-09T14:31:54Z)
• Transfer and Alignment Network for Generalized Category Discovery [11.37283148391564]
  Generalized Category Discovery is a crucial real-world task. Despite the improved performance on known categories, current methods perform poorly on novel categories. We attribute the poor performance to two reasons: biased knowledge transfer between labeled and unlabeled data and noisy representation learning on the unlabeled data. We propose a Transfer and Alignment Network (TAN), which incorporates two knowledge transfer mechanisms to calibrate the biased knowledge and two feature alignment mechanisms to learn discriminative features.
  arXiv  Detail & Related papers  (2023-12-27T08:35:47Z)
• Blueprinting the Future: Automatic Item Categorization using Hierarchical Zero-Shot and Few-Shot Classifiers [6.907552533477328]
  This study unveils a novel approach employing the zero-shot and few-shot Generative Pretrained Transformer (GPT) for hierarchical item categorization. The hierarchical nature of examination blueprints is navigated seamlessly, allowing for a tiered classification of items across multiple levels. An initial simulation with artificial data demonstrates the efficacy of this method, achieving an average accuracy of 92.91% measured by the F1 score.
  arXiv  Detail & Related papers  (2023-12-06T15:51:49Z)
• Learn to Categorize or Categorize to Learn? Self-Coding for Generalized Category Discovery [49.1865089933055]
  We propose a novel, efficient and self-supervised method capable of discovering previously unknown categories at test time. A salient feature of our approach is the assignment of minimum length category codes to individual data instances. Experimental evaluations, bolstered by state-of-the-art benchmark comparisons, testify to the efficacy of our solution.
  arXiv  Detail & Related papers  (2023-10-30T17:45:32Z)
• Dynamic Conceptional Contrastive Learning for Generalized Category Discovery [76.82327473338734]
  Generalized category discovery (GCD) aims to automatically cluster partially labeled data. Unlabeled data contain instances that are not only from known categories of the labeled data but also from novel categories. One effective way for GCD is applying self-supervised learning to learn discriminate representation for unlabeled data. We propose a Dynamic Conceptional Contrastive Learning framework, which can effectively improve clustering accuracy.
  arXiv  Detail & Related papers  (2023-03-30T14:04:39Z)
• Generalized Category Discovery with Decoupled Prototypical Network [27.1635162759448]
  We present a novel model called Decoupled Prototypical Network (DPN) By formulating a bipartite matching problem for category prototypes, DPN can achieve different training targets effectively. DPN can learn more discriminative features for both known and novel categories through our proposed Semantic-aware Prototypical Learning (SPL)
  arXiv  Detail & Related papers  (2022-11-28T08:05:45Z)
• 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)
• Automatically Discovering Novel Visual Categories with Self-supervised Prototype Learning [68.63910949916209]
  This paper tackles the problem of novel category discovery (NCD), which aims to discriminate unknown categories in large-scale image collections. We propose a novel adaptive prototype learning method consisting of two main stages: prototypical representation learning and prototypical self-training. We conduct extensive experiments on four benchmark datasets and demonstrate the effectiveness and robustness of the proposed method with state-of-the-art performance.
  arXiv  Detail & Related papers  (2022-08-01T16:34:33Z)
• Novel Class Discovery without Forgetting [72.52222295216062]
  We identify and formulate a new, pragmatic problem setting of NCDwF: Novel Class Discovery without Forgetting. We propose a machine learning model to incrementally discover novel categories of instances from unlabeled data. We introduce experimental protocols based on CIFAR-10, CIFAR-100 and ImageNet-1000 to measure the trade-off between knowledge retention and novel class discovery.
  arXiv  Detail & Related papers  (2022-07-21T17:54:36Z)
• Class-incremental Novel Class Discovery [76.35226130521758]
  We study the new task of class-incremental Novel Class Discovery (class-iNCD) We propose a novel approach for class-iNCD which prevents forgetting of past information about the base classes. Our experiments, conducted on three common benchmarks, demonstrate that our method significantly outperforms state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-07-18T13:49:27Z)

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.