Active learning algorithms select a subset of data for annotation to maximize the model performance on a budget. One such algorithm is Expected Gradient Length, which as the name suggests uses the approximate gradient induced per example in the sampling process. While Expected Gradient Length has been successfully used for classification and regression, the formulation for regression remains intuitively driven. Hence, our theoretical contribution involves deriving this formulation, thereby supporting the experimental evidence. Subsequently, we show that expected gradient length in regression is equivalent to Bayesian uncertainty. If certain assumptions are infeasible, our algorithmic contribution (EGL++) approximates the effect of ensembles with a single deterministic network. Instead of computing multiple possible inferences per input, we leverage previously annotated samples to quantify the probability of previous labels being the true label. Such an approach allows us to extend expected gradient length to a new task: human pose estimation. We perform experimental validation on two human pose datasets (MPII and LSP/LSPET), highlighting the interpretability and competitiveness of EGL++ with different active learning algorithms for human pose estimation.
翻译:主动学习算法选择了一个数据子集, 用于在预算上尽量扩大模型性能。 其中一种算法是预期渐变长度, 其名称表明在抽样过程中使用每个示例的粗略梯度。 虽然预期渐变长度成功地用于分类和回归, 但回归的配方仍然直观驱动。 因此, 我们的理论贡献包括从这一配方中得出这一配方, 从而支持实验证据。 随后, 我们显示, 回归中的预期梯度长度相当于巴耶斯人的不确定性。 如果某些假设不可行, 我们的算法贡献( EGL++) 接近于一个单一确定性网络组合的效果。 我们不用计算每个输入的多种可能的推论, 我们利用先前加注的样本来量化先前标签为真实标签的概率。 这样的方法可以让我们将预期的梯度长度扩大到一个新的任务: 人造估计 。 我们对两个人造数据集( MPII 和 LSP/LSPETET) 进行实验性验证, 突出EGL++的可解释性和竞争力, 以及不同的人造型演算法。