Expandable networks have demonstrated their advantages in dealing with catastrophic forgetting problem in incremental learning. Considering that different tasks may need different structures, recent methods design dynamic structures adapted to different tasks via sophisticated skills. Their routine is to search expandable structures first and then train on the new tasks, which, however, breaks tasks into multiple training stages, leading to suboptimal or overmuch computational cost. In this paper, we propose an end-to-end trainable adaptively expandable network named E2-AEN, which dynamically generates lightweight structures for new tasks without any accuracy drop in previous tasks. Specifically, the network contains a serial of powerful feature adapters for augmenting the previously learned representations to new tasks, and avoiding task interference. These adapters are controlled via an adaptive gate-based pruning strategy which decides whether the expanded structures can be pruned, making the network structure dynamically changeable according to the complexity of the new tasks. Moreover, we introduce a novel sparsity-activation regularization to encourage the model to learn discriminative features with limited parameters. E2-AEN reduces cost and can be built upon any feed-forward architectures in an end-to-end manner. Extensive experiments on both classification (i.e., CIFAR and VDD) and detection (i.e., COCO, VOC and ICCV2021 SSLAD challenge) benchmarks demonstrate the effectiveness of the proposed method, which achieves the new remarkable results.
翻译:考虑到不同任务可能需要不同的结构,最近的方法设计了适应复杂技能的不同任务的动态结构。他们的日常工作是先搜索可扩展的结构,然后对新任务进行培训,然而,这些新任务将使任务分成多个培训阶段,导致不优化或过高的计算成本。在本文件中,我们提议了一个名为E2-AEN的端到端的可训练适应性可扩展网络,这个网络动态地为新任务生成轻量级结构,而以前的任务则没有任何精确性下降。具体地说,这个网络包含一系列强大的地物调整器,用于将以前学到的表示方式扩大到新的任务,避免任务干扰。这些适应性结构通过适应性的基于门的裁剪动战略加以控制,这种战略决定扩大的结构能否被切割,使网络结构能够根据新任务的复杂性动态地改变。此外,我们引入了一个新的宽度-活动规范,鼓励模型学习具有有限参数的歧视性特征。E2-AEN将成本降低,并且可以建在任何向后进化结构上,以最终的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、最后的、