Uncertainty-aware Contrastive Distillation for Incremental Semantic Segmentation

Abstract

A fundamental and challenging problem in deep learning is catastrophic forgetting, i.e. the tendency of neural networks to fail to preserve the knowledge acquired from old tasks when learning new tasks. This problem has been widely investigated in the research community and several Incremental Learning (IL) approaches have been proposed in the past years. While earlier works in computer vision have mostly focused on image classification and object detection, more recently some IL approaches for semantic segmentation have been introduced. These previous works showed that, despite its simplicity, knowledge distillation can be effectively employed to alleviate catastrophic forgetting. In this paper, we follow this research direction and, inspired by recent literature on contrastive learning, we propose a novel distillation framework, Uncertainty-aware Contrastive Distillation (\method). In a nutshell, \method~is operated by introducing a novel distillation loss that takes into account all the images in a mini-batch, enforcing similarity between features associated to all the pixels from the same classes, and pulling apart those corresponding to pixels from different classes. In order to mitigate catastrophic forgetting, we contrast features of the new model with features extracted by a frozen model learned at the previous incremental step. Our experimental results demonstrate the advantage of the proposed distillation technique, which can be used in synergy with previous IL approaches, and leads to state-of-art performance on three commonly adopted benchmarks for incremental semantic segmentation. The code is available at \url{https://github.com/ygjwd12345/UCD}.

arXiv commentTPAMI

References in corpus (13)

• Distilling the Knowledge in a Neural Network
• Overcoming catastrophic forgetting in neural networks
• Rethinking Atrous Convolution for Semantic Image Segmentation
• A Simple Framework for Contrastive Learning of Visual Representations
• Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
• Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence
• Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation
• Contrastive Learning of Medical Visual Representations from Paired Images and Text
• Incremental Learning for Semantic Segmentation of Large-Scale Remote Sensing Data
• Adversarial Self-Supervised Contrastive Learning
• Learn the new, keep the old: Extending pretrained models with new anatomy and images
• Extending Pretrained Segmentation Networks with Additional Anatomical Structures
• Multi-Task Incremental Learning for Object Detection

Cited by in corpus (5)

• Class-Incremental Learning: A Survey
• A Survey on Continual Semantic Segmentation: Theory, Challenge, Method and Application
• Inherit with Distillation and Evolve with Contrast: Exploring Class Incremental Semantic Segmentation Without Exemplar Memory
• Learning at a Glance: Towards Interpretable Data-limited Continual Semantic Segmentation via Semantic-Invariance Modelling
• PARMESAN: Parameter-Free Memory Search and Transduction for Dense Prediction Tasks