E-DU: Deep neural network for multimodal medical image segmentation based on semantic gap compensation

Ecosystem Health of the Beiyun River Basin (Beijing, China) as Evaluated by the Analytic Hierarchy Process Method

“…As depicted in Fig. 3, the first category, known as data-replay methods, involves storing a portion of past training data as exemplar memory such as [26], [27], [28], [29], [30], [31], [32], [33], [34], [35], [36]. The second category, termed datafree methods, includes methods like [37], [38], [39], [40], [41], [42], [43], [44], [45], [46], [47], [48], [49].…”

“…Here we would like to discuss the advantage and necessity of continual learning based on specified models during the period of emerging large models. Although recent [26], [34], [35], [50], [51] Generative-replay Generative-data Generative-feature without storing real data, customized data replay heavy reliance on generative quality, high space complexity [28], [29], [32], [36], [52] Self-supervised Contrastive-learning Pseudo-labeling Foundation-model Driven strong adaptability, exemplar-memory free high training cost, hard to convergence [27], [41], [48], [53], [54] Regularization-based [39], [40], [43], [44], [55] Dynamic-architecture Parameter Allocation Architecture Decomposition Modular Network high model flexibility, high adaptability to diverse data network parameters gradually increases, high space complexity [30], [46], [56], [57], [58] large-model forms [59], [60] achieve fair zero-shot learning ability, they often lack the ability to classify targets with semantic understanding like humans. Another significant concern is cost.…”

“…Zhu et al [34] design a multi-factor decision-making policy enhanced by a reward set for sample selection. Considering exploration in reducing storage burdens, Wang et al [35] propose a pseudo-replay mechanism within a mini-batch to mitigate storage and privacy issues of exemplar data.…”