Recent advances in neuroscience have highlighted the effectiveness of multi-modal medical data for investigating certain pathologies and understanding human cognition. However, obtaining full sets of different modalities is limited by various factors, such as long acquisition times, high examination costs and artifact suppression. In addition, the complexity, high dimensionality and heterogeneity of neuroimaging data remains another key challenge in leveraging existing randomized scans effectively, as data of the same modality is often measured differently by different machines. There is a clear need to go beyond the traditional imaging-dependent process and synthesize anatomically specific target-modality data from a source in-put. In this paper, we propose to learn dedicated features that cross both intre- and intra-modal variations using a novel CSCℓ4Net. Through an initial unification of intra-modal data in the feature maps and multivariate canonical adaptation, CSC ℓ4Net facilitates feature-level mutual transformation. The positive definite Riemannian manifold-penalized data fidelity term further enables CSCℓ4Net to re-construct missing measurements according to transformed features. Finally, the maximization ℓ4-norm boils down to a computationally efficient optimization problem. Extensive experiments validate the ability and robustness of our CSC ℓ4Net compared to the state-of-the-art methods on multiple datasets.

One-stage object detection is commonly implemented by optimizing two sub-tasks: object classification and localization, using heads with two parallel branches, which might lead to a certain level of spatial misalignment in predictions between the two tasks. In this work, we propose a Task-aligned One-stage Object Detection (TOOD) that explicitly aligns the two tasks in a learning-based manner. First, we design a novel Task-aligned Head (T-Head) which offers a better balance between learning task-interactive and task-specific features, as well as a greater flexibility to learn the alignment via a task-aligned predictor. Second, we propose Task Alignment Learning (TAL) to explicitly pull closer (or even unify) the optimal anchors for the two tasks during training via a designed sample assignment scheme and a task-aligned loss. Extensive experiments are conducted on MS-COCO, where TOOD achieves a 51.1 AP at single-model single-scale testing. This surpasses the recent one-stage detectors by a large margin, such as ATSS [30] (47.7 AP), GFL [14] (48.2 AP), and PAA [9] (49.0 AP), with fewer parameters and FLOPs. Qualitative results also demonstrate the effectiveness of TOOD for better aligning the tasks of object classification and localization. Code is available at https://github.com/fcjian/TOOD.

Fine-grained image categorization is challenging due to the subtle inter-class differences. We posit that exploiting the rich relationships between channels can help capture such differences since different channels correspond to different semantics. In this paper, we propose a channel interaction network (CIN), which models the channel-wise interplay both within an image and across images. For a single image, a self-channel interaction (SCI) module is proposed to explore channel-wise correlation within the image. This allows the model to learn the complementary features from the correlated channels, yielding stronger fine-grained features. Furthermore, given an image pair, we introduce a contrastive channel interaction (CCI) module to model the cross-sample channel interaction with a metric learning framework, allowing the CIN to distinguish the subtle visual differences between images. Our model can be trained efficiently in an end-to-end fashion without the need of multi-stage training and testing. Finally, comprehensive experiments are conducted on three publicly available benchmarks, where the proposed method consistently outperforms the state-of-the-art approaches, such as DFL-CNN(Wang, Morariu, and Davis 2018) and NTS(Yang et al. 2018).

In this work, we propose Knowledge Integration Networks (referred as KINet) for video action recognition. KINet is capable of aggregating meaningful context features which are of great importance to identifying an action, such as human information and scene context. We design a three-branch architecture consisting of a main branch for action recognition, and two auxiliary branches for human parsing and scene recognition which allow the model to encode the knowledge of human and scene for action recognition. We explore two pre-trained models as teacher networks to distill the knowledge of human and scene for training the auxiliary tasks of KINet. Furthermore, we propose a two-level knowledge encoding mechanism which contains a Cross Branch Integration (CBI) module for encoding the auxiliary knowledge into medium-level convolutional features, and an Action Knowledge Graph (AKG) for effectively fusing high-level context information. This results in an end-to-end trainable framework where the three tasks can be trained collaboratively, allowing the model to compute strong context knowledge efficiently. The proposed KINet achieves the state-of-the-art performance on a large-scale action recognition benchmark Kinetics-400, with a top-1 accuracy of 77.8%. We further demonstrate that our KINet has strong capability by transferring the Kinetics-trained model to UCF-101, where it obtains 97.8% top-1 accuracy.

Training an object detector on a data-rich domain and applying it to a data-poor one with limited performance drop is highly attractive in industry, because it saves huge annotation cost. Recent research on unsupervised domain adaptive object detection has verified that aligning data distributions between source and target images through adversarial learning is very useful. The key is when, where and how to use it to achieve best practice. We propose Image-Instance Full Alignment Networks (iFAN) to tackle this problem by precisely aligning feature distributions on both image and instance levels: 1) Image-level alignment: multi-scale features are roughly aligned by training adversarial domain classifiers in a hierarchically-nested fashion. 2) Full instance-level alignment: deep semantic information and elaborate instance representations are fully exploited to establish a strong relationship among categories and domains. Establishing these correlations is formulated as a metric learning problem by carefully constructing instance pairs. Above-mentioned adaptations can be integrated into an object detector (e.g. Faster R-CNN), resulting in an end-to-end trainable framework where multiple alignments can work collaboratively in a coarse-to-fine manner. In two domain adaptation tasks: synthetic-to-real (SIM10K → Cityscapes) and normal-to-foggy weather (Cityscapes → Foggy Cityscapes), iFAN outperforms the state-of-the-art methods with a boost of 10%+ AP over the source-only baseline.

Mining informative negative instances are of central importance to deep metric learning (DML). However, the hard-mining ability of existing DML methods is intrinsically limited by mini-batch training, where only a mini-batch of instances are accessible at each iteration. In this paper, we identify a “slow drift” phenomena by observing that the embedding features drift exceptionally slow even as the model parameters are updating throughout the training process. It suggests that the features of instances computed at preceding iterations can considerably approximate to their features extracted by current model. We propose a cross-batch memory (XBM) mechanism that memorizes the embeddings of past iterations, allowing the model to collect sufficient hard negative pairs across multiple mini-batches - even over the whole dataset. Our XBM can be directly integrated into general pair-based DML framework.We demonstrate that, without bells and whistles, XBM augmented DML can boost the performance considerably on image retrieval. In particular, with XBM, a simple contrastive loss can have large R@1 improvements of 12%-22.5% on three large-scale datasets, easily surpassing the most sophisticated state-of-the-art methods [38, 27, 2], by a large margin. Our XBM is conceptually simple, easy to implement - using several lines of codes, and is memory efficient - with a negligible 0.2 GB extra GPU memory.

Siamese-based trackers have achieved excellent performance on visual object tracking. However, the target template is not updated online, and the features of target template and search image are computed independently in a Siamese architecture. In this paper, we propose Deformable Siamese Attention Networks, referred to as SiamAttn, by introducing a new Siamese attention mechanism that computes deformable self-attention and cross-attention. The self-attention learns strong context information via spatial attention, and selectively emphasizes interdependent channel-wise features with channel attention. The crossattention is capable of aggregating rich contextual interdependencies between the target template and the search image, providing an implicit manner to adaptively update the target template. In addition, we design a region refinement module that computes depth-wise cross correlations between the attentional features for more accurate tracking. We conduct experiments on six benchmarks, where our method achieves new state-of-the-art results, outperforming recent strong baseline, SiamRPN++, by 0.464 to 0.537 and 0.415 to 0.470 EAO on VOT 2016 and 2018.

The ability to synthesize multi-modality data is highly desirable for many computer-aided medical applications, e.g. clinical diagnosis and neuroscience research, since rich imaging cohorts offer diverse and complementary information unraveling human tissues. However, collecting acquisitions can be limited by adversary factors such as patient discomfort, expensive cost and scanner unavailability. In this paper, we propose a multi-task coherent modality transferable GAN (MCMT-GAN) to address this issue for brain MRI synthesis in an unsupervised manner. Through combining the bidirectional adversarial loss, cycle-consistency loss, domain adapted loss and manifold regularization in a volumetric space, MCMT-GAN is robust for multi-modality brain image synthesis with visually high fidelity. In addition, we complement discriminators collaboratively working with segmentors which ensure the usefulness of our results to segmentation task. Experiments evaluated on various cross-modality synthesis show that our method produces visually impressive results with substitutability for clinical post-processing and also exceeds the state-of-the-art methods.

A family of loss functions built on pair-based computation have been proposed in the literature which provide a myriad of solutions for deep metric learning. In this pa-per, we provide a general weighting framework for under-standing recent pair-based loss functions. Our contributions are three-fold: (1) we establish a General Pair Weighting (GPW) framework, which casts the sampling problem of deep metric learning into a unified view of pair weighting through gradient analysis, providing a powerful tool for understanding recent pair-based loss functions; (2) we show that with GPW, various existing pair-based methods can be compared and discussed comprehensively, with clear differences and key limitations identified; (3) we propose a new loss called multi-similarity loss (MS loss) under the GPW,which is implemented in two iterative steps (i.e., mining and weighting). This allows it to fully consider three similarities for pair weighting, providing a more principled approach for collecting and weighting informative pairs. Finally, the proposed MS loss obtains new state-of-the-art performance on four image retrieval benchmarks, where it outperforms the most recent approaches, such as ABE[14] and HTL[4], by a large margin, e.g.,60.6%→65.7%on CUB200,and 80.9%→88.0%on In-Shop Clothes Retrieval datasetat Recall@1.

Multi-label image classification has achieved remarkable progress thanks to deep convolutional neural networks (CNNs). In this paper, we propose a Decouple Network (DecoupleNet) which is an end-to-end CNN-based framework able to trade off class-level feature independence and relevance during training. The proposed DecoupleNet is able to decouple category-wise independence and relevance with image-level supervision. We design a category-wise space-to-depth module with a spatial pooling strategy to exploit more meaningful convolutional features. They are integrated with class-wise correlated information which is automatically learned via a new self-attention mechanism. We conduct extensive experiments on two large-scale benchmarks: the MS-COCO and the NUS-WIDE, where the proposed DecoupleNet obtains impressive performance compared favorably against the state-of-the-art methods on multi-label image classification.

Weakly-supervised instance segmentation aims to detect and segment object instances precisely, given image-level labels only. Unlike previous methods which are composed of multiple offline stages, we propose Sequential Label Propagation and Enhancement Networks (referred as Label-PEnet) that progressively transforms image-level labels to pixel-wise labels in a coarse-to-fine manner. We design four cascaded modules including multi-label classification, object detection, instance refinement and instance segmentation, which are implemented sequentially by sharing the same backbone. The cascaded pipeline is trained alternatively with a curriculum learning strategy that generalizes labels from high level images to low-level pixels gradually with increasing accuracy. In addition, we design a proposal calibration module to explore the ability of classification networks to find key pixels that identify object parts, which serves as a post validation strategy running in the inverse order. We evaluate the efficiency of our Label-PEnet in mining instance masks on standard benchmarks: PASCAL VOC 2007 and 2012. Experimental results show that Label-PEnet outperforms the state-of-art algorithms by a clear margin, and obtains comparable performance even with fully supervised approaches.

We present ClothFlow, an appearance-flow-based generative model to synthesize clothed person for posed-guided person image generation and virtual try-on. By estimating a dense flow between source and target clothing regions, ClothFlow effectively models the geometric changes and naturally transfers the appearance to synthesize novel images as shown in Figure 1. We achieve this with a three-stage framework: 1) Conditioned on a target pose, we first estimate a person semantic layout to provide richer guidance to the generation process. 2) Built on two feature pyramid networks, a cascaded flow estimation network then accurately estimates the appearance matching between corresponding clothing regions. The resulting dense flow warps the source image to flexibly account for deformations. 3) Finally, a generative network takes the warped clothing regions as inputs and renders the target view. We conduct extensive experiments on the DeepFashion dataset for pose-guided person image generation and on the VITON dataset for the virtual try-on task. Strong qualitative and quantitative results validate the effectiveness of our method.

Visual compatibility is critical for fashion analysis, yet is missing in existing fashion image synthesis systems. In this paper, we propose to explicitly model visual compatibility through fashion image inpainting. We present Fashion Inpainting Networks (FiNet), a two-stage image-to-image generation framework that is able to perform compatible and diverse inpainting. Disentangling the generation of shape and appearance to ensure photorealistic results, our framework consists of a shape generation network and an appearance generation network. More importantly, for each generation network, we introduce two encoders interacting with one another to learn latent codes in a shared compatibility space. The latent representations are jointly optimized with the corresponding generation network to condition the synthesis process, encouraging a diverse set of generated results that are visually compatible with existing fashion garments. In addition, our framework is readily extended to clothing reconstruction and fashion transfer. Extensive experiments on fashion synthesis quantitatively and qualitatively demonstrate the effectiveness of our method.

Recent progress has been made on developing a unified framework for joint text detection and recognition in natural images, but existing joint models were mostly built on two-stage framework by involving ROI pooling, which can degrade the performance on recognition task. In this work, we propose convolutional character networks, referred as CharNet, which is an one-stage model that can process two tasks simultaneously in one pass. CharNet directly outputs bounding boxes of words and characters, with corresponding character labels. We utilize character as basic element, allowing us to overcome the main difficulty of existing approaches that attempted to optimize text detection jointly with a RNN-based recognition branch. In addition, we develop an iterative character detection approach able to transform the ability of character detection learned from synthetic data to real-world images. These technical improvements result in a simple, compact, yet powerful one-stage model that works reliably on multi-orientation and curved text. We evaluate CharNet on three standard benchmarks, where it consistently outperforms the state-of-the-art approaches [25, 24] by a large margin, e.g., with improvements of 65.33%→71.08% (with generic lexicon) on ICDAR 2015, and 54.0%→69.23% on Total-Text, on end-to-end text recognition. Code is available at: https://github.com/MalongTech/research-charnet.

No abstract available.

A critical component of today's commercial search engines is an advertisement platform. The current state-of-the-art of such platforms is primarily based on advanced keyword matching to determine the relevance of advertisements for users' queries. However, such keyword matching techniques suffer from missing user intent when the query domain is visual as opposed to textual. To handle such a domain, we propose a new advertisement platform which allows search engine advertisers to bid on images instead of just plain text. The main components of this platform include an advertisement editorial tool, ROI detection, image content understanding, and image matching modules. This platform is suitable for application scenarios where images are the main input or consumed content, for example, in Multimedia Messaging Service (MMS) or content based image retrieval. We demonstrated the effectiveness of our proposed advertisement platform solution when used in a mobile visual search scenario involving querying for real world billboards.

In this demonstration, we present VisiAds, a vision-based online advertising platform which allows advertisers to bid on image content as opposed to text keywords. The demonstration shows an implementation of the platform designed specifically for mobile application scenarios. It can be used by advertisers to trigger and deliver multiple advertisements based on a query image captured from a consumer-grade cellular phone with an embedded camera.

This paper introduces the architecture of our location sensitive indexing model which is used in a platform designed to deliver advertisements to users who primarily utilize images as queries instead of textual keywords. The indexing model facilitates an advertiser's ability to bid on images, such as billboards or logos, in order to obtain user feedback in judging image attractiveness. Additionally, the model enables automatic evaluation of advertisement popularity by mining users' query logs, which is critical for generating advertisement recommendations. The location sensitive architecture of this model enables effective and efficient functionality in large-scale scenarios. In the model's structure, our Location Sensitive Visual Indexing model (LSVI) incorporates location information that subdivides geographical regions for precise and localized image matching. By collecting feedback from mobile users, location-based mining can also help discover popular advertisements as well as their representative images. We have deployed our platform into a real-world advertising system in Beijing, China, which demonstrates effective results in comparative studies with both alternative and state-of-the-art approaches.

We present a demonstration of an interactive wrapper induction system, called Pictor, which is able to minimize labeling cost, yet extract data with high accuracy from a website. Our demonstration will introduce two proposed technologies: record-level wrappers and a wrapper-assisted labeling strategy. These approaches allow Pictor to exploit previously generated wrappers, in order to predict similar labels in a partially labeled webpage or a completely new webpage. Our experiment results show the effectiveness of the Pictor system.

In the cases of paralysis so severe that a person's ability to control movement is limited to the muscles around the eyes, eye movements or blinks are the only way for the person to communicate. Interfaces that assist in such communication are often intrusive, require special hardware, or rely on active infrared illumination. A nonintrusive communication interface system called EyeKeys was therefore developed, which runs on a consumer-grade computer with video input from an inexpensive Universal Serial Bus camera and works without special lighting. The system detects and tracks the person's face using multiscale template correlation. The symmetry between left and right eyes is exploited to detect if the person is looking at the camera or to the left or right side. The detected eye direction can then be used to control applications such as spelling programs or games. The game ldquoBlockEscaperdquo was developed to evaluate the performance of EyeKeys and compare it to a mouse substitution interface. Experiments with EyeKeys have shown that it is an easily used computer input and control device for able-bodied people and has the potential to become a practical tool for people with severe paralysis.