ECCV 2020 论文列表

A vast number of well-trained deep networks have been released by developers online for plug-and-play use. These networks specialize in different tasks and in many cases, the data and annotations used to train them are not publicly available. In this paper, we study how to reuse such heterogeneous pre-trained models as teachers, and build a versatile and compact student model, without accessing human annotations. To this end, we propose a self-coordinate knowledge amalgamation network (SOKA-Net) for learning the multi-talent student model. This is achieved via a dual-step adaptive competitive-cooperation training approach, where the knowledge of the heterogeneous teachers are in the first step amalgamated to guide the shared parameter learning of the student network, and followed by a gradient-based competition-balancing strategy to learn the multi-head prediction network as well as the loss weightings of the distinct tasks in the second step. The two steps, which we term as the collaboration and competition step respectively, are performed alternatively until the balance of the competition is reached for the ultimate collaboration. Experimental results demonstrate that, the learned student not only comes with a smaller size but all achieves performances on par with or even superior to those of the teachers."

Modeling relations is crucial to understand videos for action and behavior recognition. Current relation models mainly reason about relations of invisibly implicit cues, while important relations of visually explicit cues are rarely considered, and the collaboration between them is usually ignored. In this paper, we propose a novel relation model that discovers relations of both implicit and explicit cues as well as their collaboration in videos. Our model concerns Collaborative Ternary Relations (CoTeRe), where the ternary relation involves channel (C, for implicit), temporal (T, for implicit), and spatial (S, for explicit) relation (R). We devise a flexible and effective CTSR module to collaborate ternary relations for 3D-CNNs, and then construct CoTeRe-Nets for action recognition. Extensive experiments on both ablation study and performance evaluation demonstrate that our CTSR module is significantly effective with approximate 3% gains and our CoTeRe-Nets outperform state-of-the-art approaches on three popular benchmarks. Boosts analysis and relations visualization also validate that relations of both implicit and explicit cues are discovered with efficacy by our method. Our code is available at https://github.com/zhenglab/cotere-net ."

Advances in deep learning techniques have allowed recent work to reconstruct the shape of a single object given only one RBG image as input. Building on common encoder-decoder architectures for this task, we propose three extensions: (1) ray-traced skip connections that propagate local 2D information to the output 3D volume in a physically correct manner; (2) a hybrid 3D volume representation that enables building translation equivariant models, while at the same time encoding fine object details without an excessive memory footprint; (3) a reconstruction loss tailored to capture overall object geometry. Furthermore, we adapt our model to address the harder task of reconstructing multiple objects from a single image. We reconstruct all objects jointly in one pass, producing a coherent reconstruction, where all objects live in a single consistent 3D coordinate frame relative to the camera and they do not intersect in 3D space. We also handle occlusions and resolve them by hallucinating the missing object parts in the 3D volume. We validate the impact of our contributions experimentally both on synthetic data from ShapeNet as well as real images from Pix3D. Our method improves over the state-of-the-art single-object methods on both datasets. Finally, we evaluate performance quantitatively on multiple object reconstruction with synthetic scenes assembled from ShapeNet objects. "

Within medical imaging, organ/pathology segmentation models trained on current publicly available and fully-annotated datasets usually do not well-represent the heterogeneous modalities, phases, pathologies, and clinical scenarios encountered in real environments. On the other hand, there are tremendous amounts of unlabelled patient imaging scans stored by many modern clinical centers. In this work, we present a novel segmentation strategy, co-heterogenous andadaptive segmentation (CHASe), which only requires a small labeled cohort of single phase data to adapt to any unlabeled cohort of heterogenous multi-phase data with possibly new clinical scenarios and pathologies. To do this, we develop a versatile framework that fuses appearance-based semi-supervision, mask-based adversarial domain adaptation, and pseudo-labeling. We also introduce co-heterogeneous training, which is a novel integration of co-training and hetero-modality learning. We evaluate CHASe using a clinically comprehensive and challenging dataset of multi-phase computed tomography (CT) imaging studies (1147 patients and 4577 3D volumes), with a test set of 100 patients. Compared to previous state-of-the-art baselines, CHASe can further improve pathological liver mask Dice-Sørensen coefficients by ranges of 4.2% to 9.4%, depending on the phase combinations, e.g., from 84.6% to 94.0% on non-contrast CTs."

Because of the ambiguous definition of anomaly and the complexity of real data, anomaly detection in videos is one of the most challenging problems in intelligent video surveillance. Since the abnormal events are usually different from normal events in appearance and/or in motion behavior, we address this issue by designing a novel convolution autoencoder architecture to separately capture spatial and temporal informative representation. The spatial part reconstructs the last individual frame (LIF), and the temporal part generates the RGB difference between the rest of video frames and the LIF, where the fast obtained RGB difference cue can learn useful motion features. Two sub-modules independently learn the regularity from appearance and motion feature space, the abnormal events which are irregular in appearance or in motion behavior lead to a large reconstruction error. Besides, we design a deep k-means cluster constraint to force both the appearance encoder and the motion encoder to extract common factors of variation within the dataset by penalizing the distance of each data representation to cluster centers. Experiments on some publicly available datasets demonstrate the effectiveness of our method which detects abnormal events in videos with competitive performance."

Despite great progress in supervised semantic segmentation, a large performance drop is usually observed when deploying the model in the wild. Domain adaptation methods tackle the issue by aligning the source domain and the target domain. However, most existing methods attempt to perform the alignment from a holistic view, ignoring the underlying class-level data structure in the target domain. To fully exploit the supervision in the source domain, we propose a fine-grained adversarial learning strategy for class-level feature alignment while preserving the internal structure of semantics across domains. We adopt a fine-grained domain discriminator that not only plays as a domain distinguisher, but also differentiates domains at class level. The traditional binary domain labels are also generalized to domain encodings as the supervision signal to guide a fine-grained feature alignment. An analysis with Class Center Distance (CCD) validates that our fine-grained adversarial strategy achieves better class-level alignment compared to other state-of-the-art methods. Our method is easy to implement and its effectiveness is evaluated on three classical domain adaptation tasks, i.e., GTA5 $ o$ Cityscapes, SYNTHIA $ o$ Cityscapes, Cityscapes $ o$ Cross-City. Large performance gains show that our method outperforms other global feature alignment based and class-wise alignment based counterparts. The code is publicly available at https://github.com/JDAI-CV/FADA."

Recent works have made great progress in semantic segmentation by exploiting contextual information in a local or global manner with dilated convolutions, pyramid pooling or self-attention mechanism. In order to avoid potential misleading contextual information aggregation in previous work, we propose a class-wise dynamic graph convolution(CDGC) module to adaptively propagate information. The graph reasoning is performed among pixels in the same class. Based on the proposed CDGC module, we further introduce the Class-wise Dynamic Graph Convolution Network(CDGCNet), which consists of two main parts including the CDGC module and a basic segmentation network, forming a coarse-to-fine paradigm. Specifically, the CDGC module takes the coarse segmentation result as class mask to extract node features for graph construction and performs dynamic graph convolutions on the constructed graph to learn the feature aggregation and weight allocation. Then the refined feature and the original feature are fused to get the final prediction. We conduct extensive experiments on three popular semantic segmentation benchmarks including Cityscapes, PASCAL VOC 2012 and COCO Stuff, and achieve state-of-the-art performance on all three benchmarks. "

We introduce a practical Domain Adaptation (DA) paradigm called Class-Incremental Domain Adaptation (CIDA). Existing DA methods tackle domain-shift but are unsuitable for learning novel target-domain classes. Meanwhile, class-incremental (CI) methods enable learning of new classes in absence of source training data, but fail under a domain-shift without labeled supervision. In this work, we effectively identify the limitations of these approaches in the CIDA paradigm. Motivated by theoretical and empirical observations, we propose an effective method, inspired by prototypical networks, that enables classification of target samples into both shared and novel (one-shot) target classes, even under a domain-shift. Our approach yields superior performance as compared to both DA and CI methods in the CIDA paradigm."

AutoAugment has been a powerful algorithm that improves the accuracy of many vision tasks, yet it is sensitive to the operator space as well as hyper-parameters, and an improper setting may degenerate network optimization. This paper delves deep into the working mechanism, and reveals that AutoAugment may remove part of discriminative information from the training image and so insisting on the ground-truth label is no longer the best option. To relieve the inaccuracy of supervision, we make use of knowledge distillation that refers to the output of a teacher model to guide network training. Experiments are performed in standard image classification benchmarks, and demonstrate the effectiveness of our approach in suppressing noise of data augmentation and stabilizing training. Upon the cooperation of knowledge distillation and AutoAugment, we claim the new state-of-the-art on ImageNet classification with a top-1 accuracy of 85.7%."

In this paper, we propose a general and efficient pre-training paradigm, Montage pre-training, for object detection. Montage pre-training needs only the target detection dataset while taking only 1/4 computational resources compared to the widely adopted ImageNet pre-training. To build such an efficient paradigm, we reduce the potential redundancy by carefully extracting useful samples from the original images, assembling samples in a Montage manner as input, and using an ERF-adaptive dense classification strategy for model pre-training. These designs include not only a new input pattern to improve the spatial utilization but also a novel learning objective to expand the effective receptive field of the pre-trained model. The efficiency and effectiveness of Montage pre-training are validated by extensive experiments on the MS-COCO dataset, where the results indicate that the models using Montage pre-training are able to achieve on-par or even better detection performances compared with the ImageNet pre-training.

Story visualization aims at generating a sequence of images to narrate each sentence in a multi-sentence story. Different from video generation that focuses on maintaining the continuity of generated images (frames), story visualization emphasizes preserving the global consistency of characters and scenes across different story pictures, which is very challenging since story sentences only provide sparse signals for generating images. Therefore, we propose a new framework named Character-Preserving Coherent Story Visualization (CP-CSV) to tackle the challenges. CP-CSV effectively learns to visualize the story by three critical modules: story and context encoder (story and sentence representation learning), figure-ground segmentation (auxiliary task to provide information for preserving character and story consistency), and figure-ground aware generation (image sequence generation by incorporating figure-ground information). Moreover, we propose a metric named Fr\'{e}chet Story Distance (FSD) to evaluate the performance of story visualization. Extensive experiments demonstrate that CP-CSV maintains the details of character information and achieves high consistency among different frames, while FSD better measures the performance of story visualization."

A scene text spotter is composed of text detection and recognition modules. Many studies have been conducted to unify these modules into an end-to-end trainable model to achieve better performance. A typical architecture places detection and recognition modules into separate branches, and a RoI pooling is commonly used to let the branches share a visual feature. However, there still exists a chance of establishing a more complimentary connection between the modules when adopting recognizer that uses attention-based decoder and detector that represents spatial information of the character regions. This is possible since the two modules share a common sub-task which is to find the location of the character regions. Based on the insight, we construct a tightly coupled single pipeline model. This architecture is formed by utilizing detection outputs in the recognizer and propagating the recognition loss through the detection stage. The use of character score map helps the recognizer attend better to the character center points, and the recognition loss propagation to the detector module enhances the localization of the character regions. Also, a strengthened sharing stage allows feature rectification and boundary localization of arbitrary-shaped text regions. Extensive experiments demonstrate state-of-the-art performance in publicly available straight and curved benchmark dataset."

We address character grounding and re-identification in multiple story-based videos like movies and associated text descriptions. In order to solve these related tasks in a mutually rewarding way, we propose a model named Character in Story Identification Network (CiSIN). Our method builds two semantically informative representations via joint training of multiple objectives for character grounding, video/text re-identification and gender prediction: Visual Track Embedding from videos and Textual Character Embedding from text context. These two representations are learned to retain rich semantic multimodal information that enables even simple MLPs to achieve the state-of-the-art performance on the target tasks. More specifically, our CiSIN model achieves the best performance in the Fill-in the Characters task of LSMDC 2019 challenges. Moreover, it outperforms previous state-of-the-art models in M-VAD Names dataset as a benchmark of multimodal character grounding and re-identification."

Important applications such as mobile computing require reducing the computational costs of neural network inference. Ideally, applications would specify their preferred tradeoff between accuracy and speed, and the network would optimize this end-to-end, using classification error to remove parts of the network. Increasing speed can be done either during training – e.g., pruning filters – or during inference – e.g., conditionally executing a subset of the layers. We propose a single end-to-end framework that can improve inference efficiency in both settings. We use a combination of batch activation loss and classification loss, and Gumbel reparameterization to learn network structure. We train end-to-end, and the same technique supports pruning as well as conditional computation. We obtain promising experimental results for ImageNet classification with ResNet (45-52% less computation)."

RGB and thermal source data suffer from both shared and specific challenges, and how to explore and exploit them plays a critical role to represent the target appearance in RGBT tracking. In this paper, we propose a novel challenge-aware neural network to handle the modality-shared challenges (e.g., fast motion, scale variation and occlusion) and the modality-specific ones (e.g., illumination variation and thermal crossover) for RGBT tracking. In particular, we design several parameter-shared branches in each layer to model the target appearance under the modality-shared challenges, and several parameter-independent branches under the modality-specific ones. Based on the observation that the modality-specific cues of different modalities usually contains the complementary advantages, we propose a guidance module to transfer discriminative features from one modality to another one, which could enhance the discriminative ability of some weak modality. Moreover, all branches are aggregated together in an adaptive manner and parallel embedded in the backbone network to efficiently form more discriminative target representations. These challenge-aware branches are able to model the target appearance under certain challenges so that the target representations can be learnt by a few parameters even in the situation of insufficient training data. From the experimental results we will show that our method operates at a real-time speed while performing well against the state-of-the-art methods on three benchmark datasets."

Existing Multiple-Object Tracking (MOT) methods either follow the tracking-by-detection paradigm to conduct object detection, feature extraction and data association separately, or have two of the three subtasks integrated to form a partially end-to-end solution. Going beyond these sub-optimal frameworks, we propose a simple online model named Chained-Tracker (CTracker), which naturally integrates all the three subtasks into an end-to-end solution (the first as far as we know). It chains paired bounding boxes regression results estimated from overlapping nodes, of which each node covers two adjacent frames. The paired regression is made attentive by object-attention (brought by a detection module) and identity-attention (ensured by an ID verification module). The two major novelties: chained structure and paired attentive regression, make CTracker simple, fast and effective, setting new MOTA records on MOT16 and MOT17 challenge datasets (67.6 and 66.6, respectively), without relying on any extra training data. The source code of CTracker can be found at: github.com/pjl1995/CTracker."

The existing methods for video object detection mainly depend on two-stage image object detectors. The fact that two-stage detectors are generally slow makes it difficult to apply in real-time scenarios. Moreover, adapting directly existing methods to a one-stage detector is inefficient or infeasible. In this work, we introduce a method based on a one-stage detector called CenterNet. We propagate the previous reliable long-term detection in the form of heatmap to boost results of upcoming image. Our method achieves the online real-time performance on ImageNet VID dataset with 76.7% mAP at 37 FPS and the offline performance 78.4% mAP at 34 FPS."

As facial interaction systems are prevalently deployed, security and reliability of these systems become a critical issue, with substantial research efforts devoted. Among them, face anti-spoofing emerges as an important area, whose objective is to identify whether a presented face is live or spoof. Though promising progress has been achieved, existing works still have difficulty in handling complex spoof attacks and generalizing to real-world scenarios. The main reason is that current face anti-spoofing datasets are limited in both quantity and diversity. To overcome these obstacles, we contribute a large-scale face anti-spoofing dataset, extbf{CelebA-Spoof}, with the following appealing properties: extit{1) Quantity:} CelebA-Spoof comprises of 625,537 pictures of 10,177 subjects, significantly larger than the existing datasets. extit{2) Diversity:} The spoof images are captured from 8 scenes (2 environments all_papers.txt decode_tex_noligatures.sh decode_tex_noligatures.sh~ decode_tex.sh decode_tex.sh~ ECCV_abstracts.csv ECCV_abstracts_good.csv ECCV_abstracts_good.csv.old ECCV_abstracts_ori.csv ECCV.csv ECCV.csv~ ECCV_new.csv generate_list.sh generate_list.sh~ generate_overview.sh generate_overview.sh~ gen.sh pdflist pdflist.copied RCS snippet.html 4 illumination conditions) with more than 10 sensors. extit{3) Annotation Richness:} CelebA-Spoof contains 10 spoof type annotations, as well as the 40 attribute annotations inherited from the original CelebA dataset. Equipped with CelebA-Spoof, we carefully benchmark existing methods in a unified multi-task framework, extbf{Auxiliary Information Embedding Network (AENet)}, and reveal several valuable observations. Our key insight is that, compared with the commonly-used binary supervision or mid-level geometric representations, rich semantic annotations as auxiliary tasks can greatly boost the performance and generalizability of face anti-spoofing across a wide range of spoof attacks. Through comprehensive studies, we show that CelebA-Spoof serves as an effective training data source. Models trained on CelebA-Spoof (without fine-tuning) exhibit state-of-the-art performance on standard benchmarks such as CASIA-MFSD. The datasets are available at \href{https://github.com/Davidzhangyuanhan/CelebA-Spoof}{https://github.com/Davidzhangyuanhan/CelebA-Spoof} . "

Many object pose estimation algorithms rely on the analysis-by-synthesis framework which requires explicit representations of individual object instances. In this paper we combine a gradient-based fitting procedure with a parametric neural image synthesis module that is capable of implicitly representing the appearance, shape and pose of entire object categories, thus rendering the need for explicit CAD models per object instance unnecessary. The image synthesis network is designed to efficiently span the pose configuration space so that model capacity can be used to capture the shape and local appearance (i.e., texture) variations jointly. At inference time the synthesized images are compared to the target via an appearance based loss and the error signal is backpropagated through the network to the input parameters, i.e. poses and appearances. Keeping the network parameters fixed, this allows for iterative optimization of the object pose, shape and appearance in a joint manner and we experimentally show that the method can recover orientation of objects with high accuracy from 2D images alone. When provided with depth measurements, to overcome scale ambiguities, the method can accurately recover the full 6DOF pose successfully. "