In contrast to regular convolutions with local receptive fields, non-local operations have widely proven an effective method for modeling long-range dependencies. Although lots of prior works have been proposed, prohibitive computation and GPU memory occupation are still the major concerns. Different from that carrying out non-local operations pixel-wise or channel-wise in a computation intensive way, we argue that we can achieve effective non-local operation using a more compact high-order statistic, which can be computed more efficiently and may convey some high-level information. In this paper, we propose an extremely compact non-local learning module (CoNL) with high-order reasoning based on a graph convolution as the core. In our CoNL, a global Hadamard pooling (GHP) as a non-local operation is used to extract a compact second-order feature vector from the input tensor. With the help of a light-weight graph convolution network (GCN), this high-order compact vector is further refined with high-level reasoning. After the GCN refinement, the compact high-order vector intuitively indicates some global semantic characteristics, and is eventually applied to enhance the input tensor through a channel scaling operation. The CoNL module is designed easily pluggable to upgrade existing networks. Extensive experiments on a wide range of tasks demonstrate the effectiveness and efficiency of our work. The proposed CoNL can achieve comparable or superior performance over previous state-of-the-art baselines on video recognition, semantic segmentation, object detection and instance segmentation tasks. For a 96 x 96 x 2048 input, our block consumes 13.6 x less in computational cost than non-local block while 7.6 x smaller in GPU memory occupation.

Videos grow to be one of the largest mediums on the Internet. E-commerce platforms like Alibaba need to process millions of video data across multimedia (e.g., visual, audio, image, and text) and on a variety of tasks (e.g., retrieval, tagging, and summary) every day. In this work, we aim to develop a once and for all pretraining technique for diverse modalities and downstream tasks. To achieve this, we make the following contributions: (1) We propose a self-supervised multi-modal co-training framework. It takes cross-modal pseudo-label consistency as the supervision and can jointly learn representations of multiple modalities. (2) We introduce several novel techniques (e.g., sliding-window subset sampling, coarse-to-fine clustering, fast spatial-temporal convolution and parallel data transmission and processing) to optimize the training process, making billion-scale stable training feasible. (3) We construct a large-scale multi-modal dataset consisting of 1.4 billion videos (~0.5 PB) and train our framework on it. The training takes only 4.6 days on an in-house 256 GPUs cluster, and it simultaneously produces pretrained video, audio, image, motion, and text networks. (4) Finetuning from our pretrained models, we obtain significant performance gains and faster convergence on diverse multimedia tasks at Alibaba. Furthermore, we also validate the learned representation on public datasets. Despite the domain gap between our commodity-centric pretraining and the action-centric evaluation data, we show superior results against state-of-the-arts.

Adaptive and flexible image editing is a desirable function of modern generative models. In this work, we present a generative model with auto-encoder architecture for per-region style manipulation. We apply a code consistency loss to enforce an explicit disentanglement between content and style latent representations, making the content and style of generated samples consistent with their corresponding content and style references. The model is also constrained by a content alignment loss to ensure the foreground editing will not interfere background contents. As a result, given interested region masks provided by users, our model supports foreground region-wise style transfer. Specially, our model receives no extra annotations such as semantic labels except for self-supervision. Extensive experiments show the effectiveness of the proposed method and exhibit the flexibility of the proposed model for various applications, including region-wise style editing, latent space interpolation, cross-domain style transfer.

Graph-based convolutional model such as non-local block has shown to be effective for strengthening the context modeling ability in convolutional neural networks (CNNs). However, its pixel-wise computational overhead is prohibitive which renders it unsuitable for high resolution imagery. In this paper, we explore the efficiency of context graph reasoning and propose a novel framework called Squeeze Reasoning. Instead of propagating information on the spatial map, we first learn to squeeze the input feature into a channel-wise global vector and perform reasoning within the single vector where the computation cost can be significantly reduced. Specifically, we build the node graph in the vector where each node represents an abstract semantic concept. The refined feature within the same semantic category results to be consistent, which is thus beneficial for downstream tasks. We show that our approach can be modularized as an end-to-end trained block and can be easily plugged into existing networks. Despite its simplicity and being lightweight, the proposed strategy allows us to establish the considerable results on different semantic segmentation datasets and shows significant improvements with respect to strong baselines on various other scene understanding tasks including object detection, instance segmentation and panoptic segmentation. Code is available at https://github.com/lxtGH/SFSegNets.

With the advance of omnidirectional panoramic technology, 360◦ imagery has become increasingly popular in the past few years. To better understand the 360◦ content, many works resort to the 360◦ object detection and various criteria have been proposed to bound the objects and compute the intersection-over-union (IoU) between bounding boxes based on the common equirectangular projection (ERP) or perspective projection (PSP). However, the existing 360◦ criteria are either inaccurate or inefficient for real-world scenarios. In this paper, we introduce a novel spherical criteria for fast and accurate 360◦ object detection, including both spherical bounding boxes and spherical IoU (SphIoU). Based on the spherical criteria, we propose a novel two-stage 360◦ detector, i.e., Reprojection R-CNN, by combining the advantages of both ERP and PSP, yielding efficient and accurate 360◦ object detection. To validate the design of spherical criteria and Reprojection R-CNN, we construct two unbiased synthetic datasets for training and evaluation. Experimental results reveal that compared with the existing criteria, the two-stage detector with spherical criteria achieves the best mAP results under the same inference speed, demonstrating that the spherical criteria can be more suitable for 360◦ object detection. Moreover, Reprojection R-CNN outperforms the previous state-of-the-art methods by over 30% on mAP with competitive speed, which confirms the efficiency and accuracy of the design.

In this paper, we focus on semantically multi-modal image synthesis (SMIS) task, namely, generating multi-modal images at the semantic level. Previous work seeks to use multiple class-specific generators, constraining its usage in datasets with a small number of classes. We instead propose a novel Group Decreasing Network (GroupDNet) that leverages group convolutions in the generator and progressively decreases the group numbers of the convolutions in the decoder. Consequently, GroupDNet is armed with much more controllability on translating semantic labels to natural images and has plausible high-quality yields for datasets with many classes. Experiments on several challenging datasets demonstrate the superiority of GroupDNet on performing the SMIS task. We also show that GroupDNet is capable of performing a wide range of interesting synthesis applications. Codes and models are available at: https://github.com/Seanseattle/SMIS.