Class-Independent Increment: An Efficient Approach for Multi-label Class-Incremental Learning

• URL: http://arxiv.org/abs/2503.00515v1
• Date: Sat, 01 Mar 2025 14:40:52 GMT
• Title: Class-Independent Increment: An Efficient Approach for Multi-label Class-Incremental Learning
• Authors: Songlin Dong, Yuhang He, Zhengdong Zhou, Haoyu Luo, Xing Wei, Alex C. Kot, Yihong Gong,
• Abstract summary: This paper focuses on the challenging yet practical multi-label class-incremental learning (MLCIL) problem.<n>We propose a novel class-independent incremental network (CINet) to extract multiple class-level embeddings for multi-label samples.<n>It learns and preserves the knowledge of different classes by constructing class-specific tokens.
• Score: 49.65841002338575
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Current research on class-incremental learning primarily focuses on single-label classification tasks. However, real-world applications often involve multi-label scenarios, such as image retrieval and medical imaging. Therefore, this paper focuses on the challenging yet practical multi-label class-incremental learning (MLCIL) problem. In addition to the challenge of catastrophic forgetting, MLCIL encounters issues related to feature confusion, encompassing inter-session and intra-feature confusion. To address these problems, we propose a novel MLCIL approach called class-independent increment (CLIN). Specifically, in contrast to existing methods that extract image-level features, we propose a class-independent incremental network (CINet) to extract multiple class-level embeddings for multi-label samples. It learns and preserves the knowledge of different classes by constructing class-specific tokens. On this basis, we develop two novel loss functions, optimizing the learning of class-specific tokens and class-level embeddings, respectively. These losses aim to distinguish between new and old classes, further alleviating the problem of feature confusion. Extensive experiments on MS-COCO and PASCAL VOC datasets demonstrate the effectiveness of our method for improving recognition performance and mitigating forgetting on various MLCIL tasks.

Related papers

• Towards Generalized Multi-stage Clustering: Multi-view Self-distillation [10.368796552760571]
  Existing multi-stage clustering methods independently learn the salient features from multiple views and then perform the clustering task. This paper proposes a novel multi-stage deep MVC framework where multi-view self-distillation (DistilMVC) is introduced to distill dark knowledge of label distribution.
  arXiv  Detail & Related papers  (2023-10-29T03:35:34Z)
• Incremental Object Detection with CLIP [36.478530086163744]
  We propose a visual-language model such as CLIP to generate text feature embeddings for different class sets. We then employ super-classes to replace the unavailable novel classes in the early learning stage to simulate the incremental scenario. We incorporate the finely recognized detection boxes as pseudo-annotations into the training process, thereby further improving the detection performance.
  arXiv  Detail & Related papers  (2023-10-13T01:59:39Z)
• Knowledge Restore and Transfer for Multi-label Class-Incremental Learning [34.378828633726854]
  We propose a knowledge restore and transfer (KRT) framework for multi-label class-incremental learning (MLCIL) KRT includes a dynamic pseudo-label (DPL) module to restore the old class knowledge and an incremental cross-attention(ICA) module to save session-specific knowledge and transfer old class knowledge to the new model sufficiently. Experimental results on MS-COCO and PASCAL VOC datasets demonstrate the effectiveness of our method for improving recognition performance and mitigating forgetting.
  arXiv  Detail & Related papers  (2023-02-26T15:34:05Z)
• PatchMix Augmentation to Identify Causal Features in Few-shot Learning [55.64873998196191]
  Few-shot learning aims to transfer knowledge learned from base with sufficient categories labelled data to novel categories with scarce known information. We propose a novel data augmentation strategy dubbed as PatchMix that can break this spurious dependency. We show that such an augmentation mechanism, different from existing ones, is able to identify the causal features.
  arXiv  Detail & Related papers  (2022-11-29T08:41:29Z)
• A Multi-label Continual Learning Framework to Scale Deep Learning Approaches for Packaging Equipment Monitoring [57.5099555438223]
  We study multi-label classification in the continual scenario for the first time. We propose an efficient approach that has a logarithmic complexity with regard to the number of tasks. We validate our approach on a real-world multi-label Forecasting problem from the packaging industry.
  arXiv  Detail & Related papers  (2022-08-08T15:58:39Z)
• Class-Incremental Lifelong Learning in Multi-Label Classification [3.711485819097916]
  This paper studies Lifelong Multi-Label (LML) classification, which builds an online class-incremental classifier in a sequential multi-label classification data stream. To solve the problem, the study proposes an Augmented Graph Convolutional Network (AGCN) with a built Augmented Correlation Matrix (ACM) across sequential partial-label tasks.
  arXiv  Detail & Related papers  (2022-07-16T05:14:07Z)
• Generative Multi-Label Zero-Shot Learning [136.17594611722285]
  Multi-label zero-shot learning strives to classify images into multiple unseen categories for which no data is available during training. Our work is the first to tackle the problem of multi-label feature in the (generalized) zero-shot setting. Our cross-level fusion-based generative approach outperforms the state-of-the-art on all three datasets.
  arXiv  Detail & Related papers  (2021-01-27T18:56:46Z)
• A Few-Shot Sequential Approach for Object Counting [63.82757025821265]
  We introduce a class attention mechanism that sequentially attends to objects in the image and extracts their relevant features. The proposed technique is trained on point-level annotations and uses a novel loss function that disentangles class-dependent and class-agnostic aspects of the model. We present our results on a variety of object-counting/detection datasets, including FSOD and MS COCO.
  arXiv  Detail & Related papers  (2020-07-03T18:23:39Z)
• Many-Class Few-Shot Learning on Multi-Granularity Class Hierarchy [57.68486382473194]
  We study many-class few-shot (MCFS) problem in both supervised learning and meta-learning settings. In this paper, we leverage the class hierarchy as a prior knowledge to train a coarse-to-fine classifier. The model, "memory-augmented hierarchical-classification network (MahiNet)", performs coarse-to-fine classification where each coarse class can cover multiple fine classes.
  arXiv  Detail & Related papers  (2020-06-28T01:11:34Z)

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.