Semi-supervised learning frameworks usually adopt mutual learning approaches with multiple submodels to learn from different perspectives. To avoid transferring erroneous pseudo labels between these submodels, a high threshold is usually used to filter out a large number of low-confidence predictions for unlabeled data. However, such filtering can not fully exploit unlabeled data with low prediction confidence. To overcome this problem, in this work, we propose a mutual learning framework based on pseudo-negative labels. Negative labels are those that a corresponding data item does not belong. In each iteration, one submodel generates pseudo-negative labels for each data item, and the other submodel learns from these labels. The role of the two submodels exchanges after each iteration until convergence. By reducing the prediction probability on pseudo-negative labels, the dual model can improve its prediction ability. We also propose a mechanism to select a few pseudo-negative labels to feed into submodels. In the experiments, our framework achieves state-of-the-art results on several main benchmarks. Specifically, with our framework, the error rates of the 13-layer CNN model are 9.35% and 7.94% for CIFAR-10 with 1000 and 4000 labels, respectively. In addition, for the non-augmented MNIST with only 20 labels, the error rate is 0.81% by our framework, which is much smaller than that of other approaches. Our approach also demonstrates a significant performance improvement in domain adaptation.
翻译:半监督的学习框架通常采用相互学习的方法,使用多个子模型从不同的角度学习。 为避免在这些子模型之间转移错误假假标签,通常使用一个高阈值来过滤大量对未贴标签的数据的低信任预测。 但是,这种过滤不能以低预测信心充分利用未贴标签的数据。 为了克服这一问题, 在这项工作中, 我们提议了一个基于伪负标签的相互学习框架。 负标签是不属于相应数据项目的。 在每个迭代中, 一个子模型为每个数据项目生成假冒假标签, 而其他域模型则从这些标签中学习。 两个子模型在每次迭代后交换大量低信任数据的作用。 然而, 通过降低伪负标签的预测概率, 双重模型可以提高它的预测能力。 我们还提议了一个机制, 选择几个假反虚拟标签, 用于子模型1 。 在实验中, 一个子模型为每个数据项目生成了假假假假假标签标签标签, 每个子模型生成了假冒标签, 并且另一个域模型从几个主要基准上得出了假标签, 。 具体地说, 我们的IMAR- IMAR- 13级标签的错误率比率是 。