Multi-task learning faces two challenging issues: (1) the high cost of annotating labels for all tasks and (2) balancing the training progress of various tasks with different natures. To resolve the label annotation issue, we construct a large-scale "partially annotated" multi-task dataset by combining task-specific datasets. However, the numbers of annotations for individual tasks are imbalanced, which may escalate an imbalance in training progress. To balance the training progress, we propose an achievement-based multi-task loss to modulate training speed based on the "achievement," defined as the ratio of current accuracy to single-task accuracy. Then, we formulate the multitask loss as a weighted geometric mean of individual task losses instead of a weighted sum to prevent any task from dominating the loss. In experiments, we evaluated the accuracy and training speed of the proposed multi-task loss on the large-scale multi-task dataset against recent multitask losses. The proposed loss achieved the best multi-task accuracy without incurring training time overhead. Compared to single-task models, the proposed one achieved 1.28%, 1.65%, and 1.18% accuracy improvement in object detection, semantic segmentation, and depth estimation, respectively, while reducing computations to 33.73%. Source code is available at https://github.com/samsung/Achievement-based-MTL.

This paper proposes novel noniterative mean-shift-based image segmentation that uses global and local attributes. The existing mean-shift-based methods use a fixed range bandwidth, and hence their accuracy is dependent on the range spectrum of an image. To resolve this dependency, this paper proposes to modify the range kernel in the mean-shift process to be anisotropic. The modification is conducted using a global attribute defined as the range covariance matrix of the image. Further, to alleviate oversegmentation, the proposed method merges the segments having similar local attributes more aggressively than other segments. The local attribute for each segment is defined as the sum of the variances of the chromatic components. Finally, to expedite the processing, the proposed method uses a region adjacency graph (RAG) for the merging process, thus differing from the existing linked mean-shift-based methods. In the experiments on the Berkeley segmentation data set, the use of the global and local attributes improved segmentation accuracy; the proposed method outperformed the state-of-the-art linked mean-shift-based method by showing an improvement of 2.15%, 3.16%, 3.32%, and 1.90% in probability rand index, segmentation covering, variation of information, and F-measure, respectively. Further, compared with the benchmark method, which uses the dilating and merging scheme, the proposed method improved the speed of the merging process 42 times by applying the RAG.