Video object detection is challenging in the presence of appearance deterioration in certain video frames. Therefore, it is a natural choice to aggregate temporal information from other frames of the same video into the current frame. However, RoI Align, as one of the most core procedures of video detectors, still remains extracting features from a single-frame feature map for proposals, making the extracted RoI features lack temporal information from videos. In this work, considering the features of the same object instance are highly similar among frames in a video, a novel Temporal RoI Align operator is proposed to extract features from other frames feature maps for current frame proposals by utilizing feature similarity. The proposed Temporal RoI Align operator can extract temporal information from the entire video for proposals. We integrate it into single-frame video detectors and other state-of-the-art video detectors, and conduct quantitative experiments to demonstrate that the proposed Temporal RoI Align operator can consistently and significantly boost the performance. Besides, the proposed Temporal RoI Align can also be applied into video instance segmentation. Codes are available at https://github.com/open-mmlab/mmtracking
Instance recognition is rapidly advanced along with the developments of various deep convolutional neural networks. Compared to the architectures of networks, the training process, which is also crucial to the success of detectors, has received relatively less attention. In this work, we carefully revisit the standard training practice of detectors, and find that the detection performance is often limited by the imbalance during the training process, which generally consists in three levels - sample level, feature level, and objective level. To mitigate the adverse effects caused thereby, we propose Libra R-CNN, a simple yet effective framework towards balanced learning for instance recognition. It integrates IoU-balanced sampling, balanced feature pyramid, and objective re-weighting, respectively for reducing the imbalance at sample, feature, and objective level. Extensive experiments conducted on MS COCO, LVIS and Pascal VOC datasets prove the effectiveness of the overall balanced design.
We present MMOCR-an open-source toolbox which provides a comprehensive pipeline for text detection and recognition, as well as their downstream tasks such as named entity recognition and key information extraction. MMOCR implements 14 state-of-the-art algorithms, which is significantly more than all the existing open-source OCR projects we are aware of to date. To facilitate future research and industrial applications of text recognition-related problems, we also provide a large number of trained models and detailed benchmarks to give insights into the performance of text detection, recognition and understanding. MMOCR is publicly released at https://github.com/open-mmlab/mmocr.
Transformers with powerful global relation modeling abilities have been introduced to fundamental computer vision tasks recently. As a typical example, the Vision Transformer (ViT) directly applies a pure transformer architecture on image classification, by simply splitting images into tokens with a fixed length, and employing transformers to learn relations between these tokens. However, such naive tokenization could destruct object structures, assign grids to uninterested regions such as background, and introduce interference signals. To mitigate the above issues, in this paper, we propose an iterative and progressive sampling strategy to locate discriminative regions. At each iteration, embeddings of the current sampling step are fed into a transformer encoder layer, and a group of sampling offsets is predicted to update the sampling locations for the next step. The progressive sampling is differentiable. When combined with the Vision Transformer, the obtained PS-ViT network can adaptively learn where to look. The proposed PS-ViT is both effective and efficient. When trained from scratch on ImageNet, PS-ViT performs 3.8% higher than the vanilla ViT in terms of top-1 accuracy with about $4\times$ fewer parameters and $10\times$ fewer FLOPs. Code is available at https://github.com/yuexy/PS-ViT.
3D object detection is an important capability needed in various practical applications such as driver assistance systems. Monocular 3D detection, as an economical solution compared to conventional settings relying on binocular vision or LiDAR, has drawn increasing attention recently but still yields unsatisfactory results. This paper first presents a systematic study on this problem and observes that the current monocular 3D detection problem can be simplified as an instance depth estimation problem: The inaccurate instance depth blocks all the other 3D attribute predictions from improving the overall detection performance. However, recent methods directly estimate the depth based on isolated instances or pixels while ignoring the geometric relations across different objects, which can be valuable constraints as the key information about depth is not directly manifest in the monocular image. Therefore, we construct geometric relation graphs across predicted objects and use the graph to facilitate depth estimation. As the preliminary depth estimation of each instance is usually inaccurate in this ill-posed setting, we incorporate a probabilistic representation to capture the uncertainty. It provides an important indicator to identify confident predictions and further guide the depth propagation. Despite the simplicity of the basic idea, our method obtains significant improvements on KITTI and nuScenes benchmarks, achieving the 1st place out of all monocular vision-only methods while still maintaining real-time efficiency. Code and models will be released at https://github.com/open-mmlab/mmdetection3d.
Among numerous videos shared on the web, well-edited ones always attract more attention. However, it is difficult for inexperienced users to make well-edited videos because it requires professional expertise and immense manual labor. To meet the demands for non-experts, we present Transcript-to-Video -- a weakly-supervised framework that uses texts as input to automatically create video sequences from an extensive collection of shots. Specifically, we propose a Content Retrieval Module and a Temporal Coherent Module to learn visual-language representations and model shot sequencing styles, respectively. For fast inference, we introduce an efficient search strategy for real-time video clip sequencing. Quantitative results and user studies demonstrate empirically that the proposed learning framework can retrieve content-relevant shots while creating plausible video sequences in terms of style. Besides, the run-time performance analysis shows that our framework can support real-world applications.
The performance of object detection, to a great extent, depends on the availability of large annotated datasets. To alleviate the annotation cost, the research community has explored a number of ways to exploit unlabeled or weakly labeled data. However, such efforts have met with limited success so far. In this work, we revisit the problem with a pragmatic standpoint, trying to explore a new balance between detection performance and annotation cost by jointly exploiting fully and weakly annotated data. Specifically, we propose a weakly- and semi-supervised object detection framework (WSSOD), which involves a two-stage learning procedure. An agent detector is first trained on a joint dataset and then used to predict pseudo bounding boxes on weakly-annotated images. The underlying assumptions in the current as well as common semi-supervised pipelines are also carefully examined under a unified EM formulation. On top of this framework, weakly-supervised loss (WSL), label attention and random pseudo-label sampling (RPS) strategies are introduced to relax these assumptions, bringing additional improvement on the efficacy of the detection pipeline. The proposed framework demonstrates remarkable performance on PASCAL-VOC and MSCOCO benchmark, achieving a high performance comparable to those obtained in fully-supervised settings, with only one third of the annotations.
Human skeleton, as a compact representation of human action, has received increasing attention in recent years. Many skeleton-based action recognition methods adopt graph convolutional networks (GCN) to extract features on top of human skeletons. Despite the positive results shown in previous works, GCN-based methods are subject to limitations in robustness, interoperability, and scalability. In this work, we propose PoseC3D, a new approach to skeleton-based action recognition, which relies on a 3D heatmap stack instead of a graph sequence as the base representation of human skeletons. Compared to GCN-based methods, PoseC3D is more effective in learning spatiotemporal features, more robust against pose estimation noises, and generalizes better in cross-dataset settings. Also, PoseC3D can handle multiple-person scenarios without additional computation cost, and its features can be easily integrated with other modalities at early fusion stages, which provides a great design space to further boost the performance. On four challenging datasets, PoseC3D consistently obtains superior performance, when used alone on skeletons and in combination with the RGB modality.
Monocular 3D object detection is an important task for autonomous driving considering its advantage of low cost. It is much more challenging compared to conventional 2D case due to its inherent ill-posed property, which is mainly reflected on the lack of depth information. Recent progress on 2D detection offers opportunities to better solving this problem. However, it is non-trivial to make a general adapted 2D detector work in this 3D task. In this technical report, we study this problem with a practice built on fully convolutional single-stage detector and propose a general framework FCOS3D. Specifically, we first transform the commonly defined 7-DoF 3D targets to image domain and decouple it as 2D and 3D attributes. Then the objects are distributed to different feature levels with the consideration of their 2D scales and assigned only according to the projected 3D-center for training procedure. Furthermore, the center-ness is redefined with a 2D Guassian distribution based on the 3D-center to fit the 3D target formulation. All of these make this framework simple yet effective, getting rid of any 2D detection or 2D-3D correspondence priors. Our solution achieves 1st place out of all the vision-only methods in the nuScenes 3D detection challenge of NeurIPS 2020. Code and models are released at https://github.com/open-mmlab/mmdetection3d.