Controversy exists on whether differentiable neural architecture search methods discover wiring topology effectively. To understand how wiring topology evolves, we study the underlying mechanism of several existing differentiable NAS frameworks. Our investigation is motivated by three observed searching patterns of differentiable NAS: 1) they search by growing instead of pruning; 2) wider networks are more preferred than deeper ones; 3) no edges are selected in bi-level optimization. To anatomize these phenomena, we propose a unified view on searching algorithms of existing frameworks, transferring the global optimization to local cost minimization. Based on this reformulation, we conduct empirical and theoretical analyses, revealing implicit inductive biases in the cost's assignment mechanism and evolution dynamics that cause the observed phenomena. These biases indicate strong discrimination towards certain topologies. To this end, we pose questions that future differentiable methods for neural wiring discovery need to confront, hoping to evoke a discussion and rethinking on how much bias has been enforced implicitly in existing NAS methods.
This report presents the approach used in the submission of the LVIS Challenge 2020 of team MMDet. In the submission, we propose Seesaw Loss that dynamically rebalances the penalty to each category according to a relative ratio of cumulative training instances between different categories. Furthermore, we propose HTC-Lite, a light-weight version of Hybrid Task Cascade (HTC) which replaces the semantic segmentation branch by a global context encoder. Seesaw Loss improves the strong baseline by 6.9% AP on LVIS v1 val split. With a single model, and without using external data and annotations except for standard ImageNet-1k classification dataset for backbone pre-training, our submission achieves 38.92% AP on the test-dev split of the LVIS v1 benchmark.
Shots are key narrative elements of various videos, e.g. movies, TV series, and user-generated videos that are thriving over the Internet. The types of shots greatly influence how the underlying ideas, emotions, and messages are expressed. The technique to analyze shot types is important to the understanding of videos, which has seen increasing demand in real-world applications in this era. Classifying shot type is challenging due to the additional information required beyond the video content, such as the spatial composition of a frame and camera movement. To address these issues, we propose a learning framework Subject Guidance Network (SGNet) for shot type recognition. SGNet separates the subject and background of a shot into two streams, serving as separate guidance maps for scale and movement type classification respectively. To facilitate shot type analysis and model evaluations, we build a large-scale dataset MovieShots, which contains 46K shots from 7K movie trailers with annotations of their scale and movement types. Experiments show that our framework is able to recognize these two attributes of shot accurately, outperforming all the previous methods.
The task of searching certain people in videos has seen increasing potential in real-world applications, such as video organization and editing. Most existing approaches are devised to work in an offline manner, where identities can only be inferred after an entire video is examined. This working manner precludes such methods from being applied to online services or those applications that require real-time responses. In this paper, we propose an online person search framework, which can recognize people in a video on the fly. This framework maintains a multimodal memory bank at its heart as the basis for person recognition, and updates it dynamically with a policy obtained by reinforcement learning. Our experiments on a large movie dataset show that the proposed method is effective, not only achieving remarkable improvements over online schemes but also outperforming offline methods.
State-of-the-art methods for large-scale driving-scene LiDAR semantic segmentation often project and process the point clouds in the 2D space. The projection methods includes spherical projection, bird-eye view projection, etc. Although this process makes the point cloud suitable for the 2D CNN-based networks, it inevitably alters and abandons the 3D topology and geometric relations. A straightforward solution to tackle the issue of 3D-to-2D projection is to keep the 3D representation and process the points in the 3D space. In this work, we first perform an in-depth analysis for different representations and backbones in 2D and 3D spaces, and reveal the effectiveness of 3D representations and networks on LiDAR segmentation. Then, we develop a 3D cylinder partition and a 3D cylinder convolution based framework, termed as Cylinder3D, which exploits the 3D topology relations and structures of driving-scene point clouds. Moreover, a dimension-decomposition based context modeling module is introduced to explore the high-rank context information in point clouds in a progressive manner. We evaluate the proposed model on a large-scale driving-scene dataset, i.e. SematicKITTI. Our method achieves state-of-the-art performance and outperforms existing methods by 6% in terms of mIoU.
We present a new loss function called Distribution-Balanced Loss for the multi-label recognition problems that exhibit long-tailed class distributions. Compared to conventional single-label classification problem, multi-label recognition problems are often more challenging due to two significant issues, namely the co-occurrence of labels and the dominance of negative labels (when treated as multiple binary classification problems). The Distribution-Balanced Loss tackles these issues through two key modifications to the standard binary cross-entropy loss: 1) a new way to re-balance the weights that takes into account the impact caused by label co-occurrence, and 2) a negative tolerant regularization to mitigate the over-suppression of negative labels. Experiments on both Pascal VOC and COCO show that the models trained with this new loss function achieve significant performance gains over existing methods. Code and models are available at: https://github.com/wutong16/DistributionBalancedLoss .
Recent years have seen remarkable advances in visual understanding. However, how to understand a story-based long video with artistic styles, e.g. movie, remains challenging. In this paper, we introduce MovieNet -- a holistic dataset for movie understanding. MovieNet contains 1,100 movies with a large amount of multi-modal data, e.g. trailers, photos, plot descriptions, etc. Besides, different aspects of manual annotations are provided in MovieNet, including 1.1M characters with bounding boxes and identities, 42K scene boundaries, 2.5K aligned description sentences, 65K tags of place and action, and 92K tags of cinematic style. To the best of our knowledge, MovieNet is the largest dataset with richest annotations for comprehensive movie understanding. Based on MovieNet, we set up several benchmarks for movie understanding from different angles. Extensive experiments are executed on these benchmarks to show the immeasurable value of MovieNet and the gap of current approaches towards comprehensive movie understanding. We believe that such a holistic dataset would promote the researches on story-based long video understanding and beyond. MovieNet will be published in compliance with regulations at https://movienet.github.io.
Stereophonic audio is an indispensable ingredient to enhance human auditory experience. Recent research has explored the usage of visual information as guidance to generate binaural or ambisonic audio from mono ones with stereo supervision. However, this fully supervised paradigm suffers from an inherent drawback: the recording of stereophonic audio usually requires delicate devices that are expensive for wide accessibility. To overcome this challenge, we propose to leverage the vastly available mono data to facilitate the generation of stereophonic audio. Our key observation is that the task of visually indicated audio separation also maps independent audios to their corresponding visual positions, which shares a similar objective with stereophonic audio generation. We integrate both stereo generation and source separation into a unified framework, Sep-Stereo, by considering source separation as a particular type of audio spatialization. Specifically, a novel associative pyramid network architecture is carefully designed for audio-visual feature fusion. Extensive experiments demonstrate that our framework can improve the stereophonic audio generation results while performing accurate sound separation with a shared backbone.