RoNID: New Intent Discovery with Generated-Reliable Labels and Cluster-friendly Representations

• URL: http://arxiv.org/abs/2404.08977v2
• Date: Thu, 18 Apr 2024 06:54:55 GMT
• Title: RoNID: New Intent Discovery with Generated-Reliable Labels and Cluster-friendly Representations
• Authors: Shun Zhang, Chaoran Yan, Jian Yang, Changyu Ren, Jiaqi Bai, Tongliang Li, Zhoujun Li,
• Abstract summary: New Intent Discovery (NID) aims to identify novel intent groups in the open-world scenario. Current methods face issues with inaccurate pseudo-labels and poor representation learning. We propose a Robust New Intent Discovery framework optimized by an EM-style method.
• Score: 27.775731666470175
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: New Intent Discovery (NID) strives to identify known and reasonably deduce novel intent groups in the open-world scenario. But current methods face issues with inaccurate pseudo-labels and poor representation learning, creating a negative feedback loop that degrades overall model performance, including accuracy and the adjusted rand index. To address the aforementioned challenges, we propose a Robust New Intent Discovery (RoNID) framework optimized by an EM-style method, which focuses on constructing reliable pseudo-labels and obtaining cluster-friendly discriminative representations. RoNID comprises two main modules: reliable pseudo-label generation module and cluster-friendly representation learning module. Specifically, the pseudo-label generation module assigns reliable synthetic labels by solving an optimal transport problem in the E-step, which effectively provides high-quality supervised signals for the input of the cluster-friendly representation learning module. To learn cluster-friendly representation with strong intra-cluster compactness and large inter-cluster separation, the representation learning module combines intra-cluster and inter-cluster contrastive learning in the M-step to feed more discriminative features into the generation module. RoNID can be performed iteratively to ultimately yield a robust model with reliable pseudo-labels and cluster-friendly representations. Experimental results on multiple benchmarks demonstrate our method brings substantial improvements over previous state-of-the-art methods by a large margin of +1~+4 points.

Related papers

• An Information Compensation Framework for Zero-Shot Skeleton-based Action Recognition [49.45660055499103]
  Zero-shot human skeleton-based action recognition aims to construct a model that can recognize actions outside the categories seen during training. Previous research has focused on aligning sequences' visual and semantic spatial distributions. We introduce a new loss function sampling method to obtain a tight and robust representation.
  arXiv  Detail & Related papers  (2024-06-02T06:53:01Z)
• New Intent Discovery with Attracting and Dispersing Prototype [32.607743914487614]
  New Intent Discovery (NID) aims to recognize known and infer new intent categories with the help of limited labeled and large-scale unlabeled data. We propose a Robust and Adaptive Prototypical learning framework for globally distinct decision boundaries for both known and new intent categories.
  arXiv  Detail & Related papers  (2024-03-25T16:31:55Z)
• Exploring Homogeneous and Heterogeneous Consistent Label Associations for Unsupervised Visible-Infrared Person ReID [62.81466902601807]
  Unsupervised visible-infrared person re-identification (USL-VI-ReID) aims to retrieve pedestrian images of the same identity from different modalities without annotations. We introduce a Modality-Unified Label Transfer (MULT) module that simultaneously accounts for both homogeneous and heterogeneous fine-grained instance-level structures. It models both homogeneous and heterogeneous affinities, leveraging them to define the inconsistency for the pseudo-labels and then minimize it, leading to pseudo-labels that maintain alignment across modalities and consistency within intra-modality structures.
  arXiv  Detail & Related papers  (2024-02-01T15:33:17Z)
• Multi-Memory Matching for Unsupervised Visible-Infrared Person Re-Identification [30.983346937558743]
  Key challenges in USL-VI-ReID are to effectively generate pseudo-labels and establish pseudo-label correspondences. We propose a Multi-Memory Matching framework for USL-VI-ReID. Experiments on the public SYSU-MM01 and RegDB datasets demonstrate the reliability of the established cross-modality correspondences.
  arXiv  Detail & Related papers  (2024-01-12T01:24:04Z)
• Robust Representation Learning with Reliable Pseudo-labels Generation via Self-Adaptive Optimal Transport for Short Text Clustering [13.83404821252712]
  We propose a Robust Short Text Clustering model to improve robustness against imbalanced and noisy data. To improve robustness against the noise in data, we introduce both class-wise and instance-wise contrastive learning. Our empirical studies on eight short text clustering datasets demonstrate that RSTC significantly outperforms the state-of-the-art models.
  arXiv  Detail & Related papers  (2023-05-23T12:43:40Z)
• Efficient Bilateral Cross-Modality Cluster Matching for Unsupervised Visible-Infrared Person ReID [56.573905143954015]
  We propose a novel bilateral cluster matching-based learning framework to reduce the modality gap by matching cross-modality clusters. Under such a supervisory signal, a Modality-Specific and Modality-Agnostic (MSMA) contrastive learning framework is proposed to align features jointly at a cluster-level. Experiments on the public SYSU-MM01 and RegDB datasets demonstrate the effectiveness of the proposed method.
  arXiv  Detail & Related papers  (2023-05-22T03:27:46Z)
• Rethinking Clustering-Based Pseudo-Labeling for Unsupervised Meta-Learning [146.11600461034746]
  Method for unsupervised meta-learning, CACTUs, is a clustering-based approach with pseudo-labeling. This approach is model-agnostic and can be combined with supervised algorithms to learn from unlabeled data. We prove that the core reason for this is lack of a clustering-friendly property in the embedding space.
  arXiv  Detail & Related papers  (2022-09-27T19:04:36Z)
• Mind Your Clever Neighbours: Unsupervised Person Re-identification via Adaptive Clustering Relationship Modeling [19.532602887109668]
  Unsupervised person re-identification (Re-ID) attracts increasing attention due to its potential to resolve the scalability problem of supervised Re-ID models. Most existing unsupervised methods adopt an iterative clustering mechanism, where the network was trained based on pseudo labels generated by unsupervised clustering. To generate high-quality pseudo-labels and mitigate the impact of clustering errors, we propose a novel clustering relationship modeling framework for unsupervised person Re-ID.
  arXiv  Detail & Related papers  (2021-12-03T10:55:07Z)
• Deep Attention-guided Graph Clustering with Dual Self-supervision [49.040136530379094]
  We propose a novel method, namely deep attention-guided graph clustering with dual self-supervision (DAGC) We develop a dual self-supervision solution consisting of a soft self-supervision strategy with a triplet Kullback-Leibler divergence loss and a hard self-supervision strategy with a pseudo supervision loss. Our method consistently outperforms state-of-the-art methods on six benchmark datasets.
  arXiv  Detail & Related papers  (2021-11-10T06:53:03Z)
• Neighborhood Contrastive Learning for Novel Class Discovery [79.14767688903028]
  We build a new framework, named Neighborhood Contrastive Learning, to learn discriminative representations that are important to clustering performance. We experimentally demonstrate that these two ingredients significantly contribute to clustering performance and lead our model to outperform state-of-the-art methods by a large margin.
  arXiv  Detail & Related papers  (2021-06-20T17:34:55Z)
• ANL: Anti-Noise Learning for Cross-Domain Person Re-Identification [25.035093667770052]
  We propose an Anti-Noise Learning (ANL) approach, which contains two modules. FDA module is designed to gather the id-related samples and disperse id-unrelated samples, through the camera-wise contrastive learning and adversarial adaptation. Reliable Sample Selection ( RSS) module utilizes an Auxiliary Model to correct noisy labels and select reliable samples for the Main Model.
  arXiv  Detail & Related papers  (2020-12-27T02:38:45Z)

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.