Transfer Learning for Segmentation Problems: Choose the Right Encoder and Skip the Decoder
원문 초록
It is common practice to reuse models initially trained on different data to increase downstream task performance. Especially in the computer vision domain, ImageNet-pretrained weights have been successfully used for various tasks. In this work, we investigate the impact of transfer learning for segmentation problems, being pixel-wise classification problems that can be tackled with encoder-decoder architectures. We find that transfer learning the decoder does not help downstream segmentation tasks, while transfer learning the encoder is truly beneficial. We demonstrate that pretrained weights for a decoder may yield faster convergence, but they do not improve the overall model performance as one can obtain equivalent results with randomly initialized decoders. However, we show that it is more effective to reuse encoder weights trained on a segmentation or reconstruction task than reusing encoder weights trained on classification tasks. This finding implicates that using ImageNet-pretrained encoders for downstream segmentation problems is suboptimal. We also propose a contrastive self-supervised approach with multiple self-reconstruction tasks, which provides encoders that are suitable for transfer learning in segmentation problems in the absence of segmentation labels.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
PSAT: Pediatric Segmentation Approaches via Adult Augmentations and Transfer Learning
TASeg: Text-aware RGB-T Semantic Segmentation based on Fine-tuning Vision Foundation Models
ASQuery: A Query-based Model for Action Segmentation
MaskChanger: A Transformer-Based Model Tailoring Change Detection with Mask Classification
Semantic Segmentation Using Transfer Learning on Fisheye Images
LSegDiff: A Latent Diffusion Model for Medical Image Segmentation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.