The paradigm of large-scale pre-training followed by downstream fine-tuning has been widely employed in various object detection algorithms. In this paper, we reveal discrepancies in data, model, and task between the pre-training and fine-tuning procedure in existing practices, which implicitly limit the detector’s performance, generalization ability, and convergence speed. To this end, we propose AlignDet, a unified pre-training framework that can be adapted to various existing detectors to alleviate the discrepancies. AlignDet decouples the pre-training process into two stages, i.e., image-domain and box-domain pre-training. The image-domain pre-training optimizes the detection backbone to capture holistic visual abstraction, and box-domain pre-training learns instance-level semantics and task-aware concepts to initialize the parts out of the backbone. By incorporating the self-supervised pretrained backbones, we can pre-train all modules for various detectors in an unsupervised paradigm. As depicted in Figure 1, extensive experiments demonstrate that AlignDet can achieve significant improvements across diverse protocols, such as ${\color{Green}\text{detection algorithms}}, {\color{Blue}\text{model backbones}}, {\color{Red}\text{data settings}}$, and ${\color{SkyBlue}\text{training schedules}}$. For example, AlignDet improves FCOS by 5.3 mAP, RetinaNet by 2.1 mAP, Faster R-CNN by 3.3 mAP, and DETR by 2.3 mAP under fewer epochs.

Abstract To improve the uniformity of one‐pixel width and continuity of the thinned edges, this paper proposes an edge thinning algorithm acting on grey‐scale edge images based on 24 self‐defined single‐pixel connection patterns. First, for binary or blurred grey‐scale gradient edge images, a distance–greyscale coupling algorithm is proposed to achieve gradient enhancement in the edge width direction. Then the elimination rules of noise points and gradient calculation method are given. Secondly, the marking rules of the first three pixels of each edge are given. The next pixel to be marked must meet that the new last three pixels belong to the 24 connection modes. Whether the qualified pixels are retained depends on its grey value and the local edge gradient. The algorithm is tested on four types of images. The results show that the proposed method can guarantee uniform, smooth, and connected one‐pixel‐wide lines that lie at the centre of the initial edges. The algorithm and the existing algorithms are performed on portrait image and four scenarios of the indoor datasets. Five evaluation indicators are statistically analyzed to prove the feasibility and effectiveness of the proposed algorithm.

The goal of early action prediction is to recognize actions from partially observed videos with incomplete action executions, which is quite different from action recognition. Predicting early actions is very challenging since the partially observed videos do not contain enough action information for recognition. In this paper, we aim at improving early action prediction by proposing a novel teacherstudent learning framework. Our framework involves a teacher model for recognizing actions from full videos, a student model for predicting early actions from partial videos, and a teacher-student learning block for distilling progressive knowledge from teacher to student, crossing different tasks. Extensive experiments on three public action datasets show that the proposed progressive teacher-student learning framework can consistently improve performance of early action prediction model. We have also reported the state-of-the-art performances for early action prediction on all of these sets.

Predicting future actions from observed partial videos is very challenging as the missing future is uncertain and sometimes has multiple possibilities. To obtain a reliable future estimation, a novel encoder-decoder architecture is proposed for integrating the tasks of synthesizing future motions from observed videos and reconstructing observed motions from synthesized future motions in an unified framework, which can capture the bi-directional dynamics depicted in partial videos along the temporal (past-to-future) direction and reverse chronological (future-back-to-past) direction. We then employ a bi-directional long short-term memory (Bi-LSTM) architecture to exploit the learned bi-directional dynamics for predicting early actions. Our experiments on two benchmark action datasets show that learning bi-directional dynamics benefits the early action prediction and our system clearly outperforms the state-of-the-art methods.