Knowledge Decomposition and Replay: A Novel Cross-modal Image-Text Retrieval Continual Learning Method
Rui Yang, Shuang Wang, Huan Zhang, Siyuan Xu, Yanhe Guo, Xiutiao Ye, Biao Hou, Licheng Jiao
Abstract
To enable machines to mimic human cognitive abilities and alleviate the catastrophic forgetting problem in cross-modal image-text retrieval (CMITR), this paper proposes a novel continual learning method, Knowledge Decomposition and Replay (KDR), which emulates the process of knowledge decomposition and replay exhibited by humans in complex and changing environments. KDR has two components: a feature Decomposition-based CMITR Model (DCM) and a cross-task Generic Knowledge Replay strategy (GKR). DCM decomposes text and image features into task-specific and generic knowledge features, mimicking the human cognitive process of knowledge decomposition. Specifically, it employs a generic knowledge features extraction module for all tasks and a task-specific module for each task with a few trainable fully connected layers. Similarly, GKR emulates the human behavior of knowledge replay by utilizing the image-text similarity matrix output from the old task model with inputting the previous samples to induce the learning of the image-text similarity matrix output from the current task model with inputting the previous samples, using knowledge distillation technology. To demonstrate the effect of KDR, we adapted a continual learning dataset Seq-COCO from MSCOCO. Extensive experiments on Seq-COCO showed that KDR reduces catastrophic forgetting and consolidates general knowledge, improving the model's learning ability in CMITR.