Partial multi-label image classification (PMLIC) learns from typical weak supervision, where each image is labeled with a set of candidate labels, only some of which are correct. We find that noisy labels generate conflicting gradient signals that disrupt the learning of latent true labels, causing the model to prefer learning clean negative labels that provide consistent supervisory signals, thereby hindering disambiguation. Meanwhile, noisy labels cause the model to activate misattributed pixel regions, which interfere with feature pattern extraction, leading to inaccurate label correlation. In this paper, we propose a PMLIC framework that constructs a correlation-induced negative suppression disambiguation loss (CoNeS). First, we exploit the property that networks tend to learn clean labels first by extracting class activation maps to identify and screen misattributed pixel regions. Meanwhile, we aggregate noise-disturbed feature patterns into more expressive representations via k-means clustering and construct accurate label correlations to aid disambiguation. In addition, we design the negative suppression disambiguation loss to focus the model on disambiguation by introducing a weight distribution to suppress the contribution of negative labels. This weighting distribution can be adaptively inferred by a closed-form solution. Extensive experiments demonstrate that the CoNeS framework achieves significant advantages over current state-of-the-art methods. Specifically, it achieves average mAP improvements of 1.26%, 2.74%, 0.85%, and 0.33% on the VOC 2007, MS-COCO, VG-256, and CUB-200 datasets at different resolutions and noise rates. Code has been made available at https://github.com/zhongjingyu1/CoNeS.

The anchor-based clustering method is currently a predominant technique for handling large-scale data. However, in multiview data, existing anchor-based methods face a key challenge: balancing individual anchor graph distinctiveness with final consistency. To address this challenge, we propose a large-scale multiview clustering (MVC) method via joint learning of anchor representation and multigraph alignment (ARMGA). Specifically, ARMGA introduces a unified framework that facilitates the concurrent learning of single-view anchor representations and virtual graph-based multigraph alignment. The approach aims to preserve the adaptability of anchor learning across different views, while ensuring the ultimate consistency of the merged anchor graph. Furthermore, ARMGA employs Schatten- $\boldsymbol {p}$ norm on the tensor formed by the adaptive anchor representation, originating from multigraph alignment, to reinforce cross-view consistency. This technique effectively leverages complementary information preserved across views to bolster the overall structure and consensus information. Ultimately, to attenuate the noise impact on the anchor representation matrix, ARMGA capitalizes on the cosine angle information from the low-rank representation as coefficients within the relationship matrix and efficiently reduces computational complexity through deductions. On nine datasets, ARMGA has exhibited a notable improvement in clustering performance indicators by 2%-10% over other algorithms, while also maintaining lower time complexity.

Multilabel feature selection solves the dimension distress of high-dimensional multilabel data by selecting the optimal subset of features. Noisy and incomplete labels of raw multilabel data hinder the acquisition of label-guided information. In existing approaches, mapping the label space to a low-dimensional latent space by semantic decomposition to mitigate label noise is considered an effective strategy. However, the decomposed latent label space contains redundant label information, which misleads the capture of potential label relevance. To eliminate the effect of redundant information on the extraction of latent label correlations, a novel method named SLOFS via shared latent sublabel structure and simultaneous orthogonal basis clustering for multilabel feature selection is proposed. First, a latent orthogonal base structure shared (LOBSS) term is engineered to guide the construction of a redundancy-free latent sublabel space via the separated latent clustering center structure. The LOBSS term simultaneously retains latent sublabel information and latent clustering center structure. Moreover, the structure and relevance information of nonredundant latent sublabels are fully explored. The introduction of graph regularization ensures structural consistency in the data space and latent sublabels, thus helping the feature selection process. SLOFS employs a dynamic sublabel graph to obtain a high-quality sublabel space and uses regularization to constrain label correlations on dynamic sublabel projections. Finally, an effective convergence provable optimization scheme is proposed to solve the SLOFS method. The experimental studies on the 18 datasets demonstrate that the presented method performs consistently better than previous feature selection methods.

Partial multi-label learning (PML) is defined as the construction of robust multi-label classification models from a training set where all instances are correlated with a corresponding group of candidate labels that are only partially accurate. Existing PML approaches have attempted to elicit reliable labels by parsing the guideline information of candidate labels. However, the other side information in the labels that describes what the sample does not contain is largely ignored. Moreover, existing PML approaches only focus on distinguishing the noise information and lack the effective use of noise information. To this end, a partial multi-label learning disambiguation approach guided by negative labels and noise information is proposed. Specifically, a negative label information-inducing paradigm is established based on the constructed negative label encoding matrix. Meanwhile, the negative correlation information guides an iterative label propagation process to induce ground-truth labels with high credibility. In addition, the truth and noise labels are formalized in a unified framework by constructing a regularizer. Moreover, the multi-label predictor is induced by discriminating regularization and disambiguation of label-specific features using the identified noise feature information. Extensive experiments on existing and constructed datasets have demonstrated that the negative label information bootstrapping strategy can be more effective in finding truth labels hidden in candidate labels. Moreover, noisy feature information-induced multi-label prediction outperforms state-of-the-art approaches.