Multi-task feature learning aims to identity the shared features among tasks to improve generalization. It has been shown that by minimizing non-convex learning models, a better solution than the convex alternatives can be obtained. Therefore, a non-convex model based on the capped-ℓ 1 , ℓ 1 regularization was proposed in [1], and a corresponding efficient multi-stage multi-task feature learning algorithm (MSMTFL) was presented. However, this algorithm harnesses a prescribed fixed threshold in the definition of the capped-ℓ 1 , ℓ 1 regularization and the lack of adaptivity might result in suboptimal performance. In this paper we propose to employ an adaptive threshold in the capped-ℓ 1 , ℓ 1 regularized formulation, where the corresponding variant of MSMTFL will incorporate an additional component to adaptively determine the threshold value. This variant is expected to achieve a better feature selection performance over the original MSMTFL algorithm. In particular, the embedded adaptive threshold component comes from our previously proposed iterative support detection (ISD) method [2]. Empirical studies on both synthetic and real-world data sets demonstrate the effectiveness of this new variant over the original MSMTFL.