Zero-Forgetting CISS via Dual-Phase Cognitive Cascades

• URL: http://arxiv.org/abs/2603.13874v1
• Date: Sat, 14 Mar 2026 10:09:32 GMT
• Title: Zero-Forgetting CISS via Dual-Phase Cognitive Cascades
• Abstract summary: Continual semantic segmentation (CSS) is a cornerstone task in computer vision that enables a large number of downstream applications, but faces the catastrophic forgetting challenge.<n>We introduce Cognitive Cascade (CogCaS), a novel dual-phase cascade formulation for CSS tasks in the CISS setting.<n>We have shown significant improvements in a variety of challenging scenarios, particularly those with long sequence of incremental tasks, when compared to exsiting state-of-the-art methods.
• Score: 10.322949655048648
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Continual semantic segmentation (CSS) is a cornerstone task in computer vision that enables a large number of downstream applications, but faces the catastrophic forgetting challenge. In conventional class-incremental semantic segmentation (CISS) frameworks using Softmax-based classification heads, catastrophic forgetting originates from Catastrophic forgetting and task affiliation probability. We formulate these problems and provide a theoretical analysis to more deeply understand the limitations in existing CISS methods, particularly Strict Parameter Isolation (SPI). To address these challenges, we follow a dual-phase intuition from human annotators, and introduce Cognitive Cascade Segmentation (CogCaS), a novel dual-phase cascade formulation for CSS tasks in the CISS setting. By decoupling the task into class-existence detection and class-specific segmentation, CogCaS enables more effective continual learning, preserving previously learned knowledge while incorporating new classes. Using two benchmark datasets PASCAL VOC 2012 and ADE20K, we have shown significant improvements in a variety of challenging scenarios, particularly those with long sequence of incremental tasks, when compared to exsiting state-of-the-art methods. Our code will be made publicly available upon paper acceptance.

Related papers

• 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)
• Low-Complexity Inference in Continual Learning via Compressed Knowledge Transfer [5.079602839359523]
  Continual learning (CL) aims to train models that can learn a sequence of tasks without forgetting previously acquired knowledge.<n>Recently, large pre-trained models have been widely adopted in CL for their ability to support both.<n>We propose two efficient frameworks tailored for class-incremental learning.
  arXiv  Detail & Related papers  (2025-05-13T08:07:40Z)
• Class-Independent Increment: An Efficient Approach for Multi-label Class-Incremental Learning [49.65841002338575]
  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.
  arXiv  Detail & Related papers  (2025-03-01T14:40:52Z)
• IPSeg: Image Posterior Mitigates Semantic Drift in Class-Incremental Segmentation [77.06177202334398]
  We identify two critical challenges in CISS that contribute to semantic drift and degrade performance.<n>First, we highlight the issue of separate optimization, where different parts of the model are optimized in distinct incremental stages.<n>Second, we identify noisy semantics arising from inappropriate pseudo-labeling, which results in sub-optimal results.
  arXiv  Detail & Related papers  (2025-02-07T12:19:37Z)
• Happy: A Debiased Learning Framework for Continual Generalized Category Discovery [54.54153155039062]
  This paper explores the underexplored task of Continual Generalized Category Discovery (C-GCD) C-GCD aims to incrementally discover new classes from unlabeled data while maintaining the ability to recognize previously learned classes. We introduce a debiased learning framework, namely Happy, characterized by Hardness-aware prototype sampling and soft entropy regularization.
  arXiv  Detail & Related papers  (2024-10-09T04:18:51Z)
• ECLIPSE: Efficient Continual Learning in Panoptic Segmentation with Visual Prompt Tuning [54.68180752416519]
  Panoptic segmentation is a cutting-edge computer vision task. We introduce a novel and efficient method for continual panoptic segmentation based on Visual Prompt Tuning, dubbed ECLIPSE. Our approach involves freezing the base model parameters and fine-tuning only a small set of prompt embeddings, addressing both catastrophic forgetting and plasticity.
  arXiv  Detail & Related papers  (2024-03-29T11:31:12Z)
• Weakly Supervised Co-training with Swapping Assignments for Semantic Segmentation [21.345548821276097]
  Class activation maps (CAMs) are commonly employed in weakly supervised semantic segmentation (WSSS) to produce pseudo-labels. We propose an end-to-end WSSS model incorporating guided CAMs, wherein our segmentation model is trained while concurrently optimizing CAMs online. CoSA is the first single-stage approach to outperform all existing multi-stage methods including those with additional supervision.
  arXiv  Detail & Related papers  (2024-02-27T21:08:23Z)
• Enhancing Few-shot CLIP with Semantic-Aware Fine-Tuning [61.902254546858465]
  Methods based on Contrastive Language-Image Pre-training have exhibited promising performance in few-shot adaptation tasks. We propose fine-tuning the parameters of the attention pooling layer during the training process to encourage the model to focus on task-specific semantics.
  arXiv  Detail & Related papers  (2023-11-08T05:18:57Z)
• Inherit with Distillation and Evolve with Contrast: Exploring Class Incremental Semantic Segmentation Without Exemplar Memory [23.730424035141155]
  We present IDEC, which consists of a Dense Knowledge Distillation on all Aspects (DADA) and an Asymmetric Region-wise Contrastive Learning (ARCL) module. We demonstrate the effectiveness of our method on multiple CISS tasks by state-of-the-art performance, including Pascal VOC 2012, ADE20K and ISPRS datasets.
  arXiv  Detail & Related papers  (2023-09-27T05:38:31Z)
• SSUL: Semantic Segmentation with Unknown Label for Exemplar-based Class-Incremental Learning [19.152041362805985]
  We consider a class-incremental semantic segmentation (CISS) problem. We propose a new method, dubbed as SSUL-M (Semantic with Unknown Label with Memory), by carefully combining several techniques tailored for semantic segmentation. We show our method achieves significantly better performance than the recent state-of-the-art baselines on the standard benchmark datasets.
  arXiv  Detail & Related papers  (2021-06-22T06:40:26Z)
• Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representations [18.655840060559168]
  This paper focuses on class incremental continual learning in semantic segmentation. New categories are made available over time while previous training data is not retained. The proposed continual learning scheme shapes the latent space to reduce forgetting whilst improving the recognition of novel classes.
  arXiv  Detail & Related papers  (2021-03-10T21:02:05Z)

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.