RGB-D Salient Object Detection Based on Discriminative Cross-modal Transfer Learning
원문 초록
In this work, we propose to utilize Convolutional Neural Networks to boost the performance of depth-induced salient object detection by capturing the high-level representative features for depth modality. We formulate the depth-induced saliency detection as a CNN-based cross-modal transfer problem to bridge the gap between the "data-hungry" nature of CNNs and the unavailability of sufficient labeled training data in depth modality. In the proposed approach, we leverage the auxiliary data from the source modality effectively by training the RGB saliency detection network to obtain the task-specific pre-understanding layers for the target modality. Meanwhile, we exploit the depth-specific information by pre-training a modality classification network that encourages modal-specific representations during the optimizing course. Thus, it could make the feature representations of the RGB and depth modalities as discriminative as possible. These two modules are pre-trained independently and then stitched to initialize and optimize the eventual depth-induced saliency detection model. Experiments demonstrate the effectiveness of the proposed novel pre-training strategy as well as the significant and consistent improvements of the proposed approach over other state-of-the-art methods.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Lightweight RGB-D Salient Object Detection from a Speed-Accuracy Tradeoff Perspective
Seg-R1: Segmentation Can Be Surprisingly Simple with Reinforcement Learning
FLIM-based Salient Object Detection Networks with Adaptive Decoders
Visual Consensus Prompting for Co-Salient Object Detection
Feature Hallucination for Self-supervised Action Recognition
Flyweight FLIM Networks for Salient Object Detection in Biomedical Images
토론
이 논문과 연결된 포럼 글이 아직 없습니다.