Recent advances in self-supervised contrastive learning yield good image-level representation, which favors classification tasks but usually neglects pixel-level detailed information, leading to unsatisfactory transfer performance to dense prediction tasks such as semantic segmentation. In this work, we propose a pixel-wise contrastive learning method called CP2 (Copy-Paste Contrastive Pretraining), which facilitates both image- and pixel-level representation learning and therefore is more suitable for downstream dense prediction tasks. In detail, we copy-paste a random crop from an image (the foreground) onto different background images and pretrain a semantic segmentation model with the objective of 1) distinguishing the foreground pixels from the background pixels, and 2) identifying the composed images that share the same foreground.Experiments show the strong performance of CP2 in downstream semantic segmentation: By finetuning CP2 pretrained models on PASCAL VOC 2012, we obtain 78.6% mIoU with a ResNet-50 and 79.5% with a ViT-S.
This paper presents a new vision Transformer, named Iwin Transformer, which is specifically designed for human-object interaction (HOI) detection, a detailed scene understanding task involving a sequential process of human/object detection and interaction recognition. Iwin Transformer is a hierarchical Transformer which progressively performs token representation learning and token agglomeration within irregular windows. The irregular windows, achieved by augmenting regular grid locations with learned offsets, 1) eliminate redundancy in token representation learning, which leads to efficient human/object detection, and 2) enable the agglomerated tokens to align with humans/objects with different shapes, which facilitates the acquisition of highly-abstracted visual semantics for interaction recognition. The effectiveness and efficiency of Iwin Transformer are verified on the two standard HOI detection benchmark datasets, HICO-DET and V-COCO. Results show our method outperforms existing Transformers-based methods by large margins (3.7 mAP gain on HICO-DET and 2.0 mAP gain on V-COCO) with fewer training epochs ($0.5 \times$).
Palmprints are private and stable information for biometric recognition. In the deep learning era, the development of palmprint recognition is limited by the lack of sufficient training data. In this paper, by observing that palmar creases are the key information to deep-learning-based palmprint recognition, we propose to synthesize training data by manipulating palmar creases. Concretely, we introduce an intuitive geometric model which represents palmar creases with parameterized B\'ezier curves. By randomly sampling B\'ezier parameters, we can synthesize massive training samples of diverse identities, which enables us to pretrain large-scale palmprint recognition models. Experimental results demonstrate that such synthetically pretrained models have a very strong generalization ability: they can be efficiently transferred to real datasets, leading to significant performance improvements on palmprint recognition. For example, under the open-set protocol, our method improves the strong ArcFace baseline by more than 10\% in terms of TAR@1e-6. And under the closed-set protocol, our method reduces the equal error rate (EER) by an order of magnitude.
The spleen is one of the most commonly injured solid organs in blunt abdominal trauma. The development of automatic segmentation systems from multi-phase CT for splenic vascular injury can augment severity grading for improving clinical decision support and outcome prediction. However, accurate segmentation of splenic vascular injury is challenging for the following reasons: 1) Splenic vascular injury can be highly variant in shape, texture, size, and overall appearance; and 2) Data acquisition is a complex and expensive procedure that requires intensive efforts from both data scientists and radiologists, which makes large-scale well-annotated datasets hard to acquire in general. In light of these challenges, we hereby design a novel framework for multi-phase splenic vascular injury segmentation, especially with limited data. On the one hand, we propose to leverage external data to mine pseudo splenic masks as the spatial attention, dubbed external attention, for guiding the segmentation of splenic vascular injury. On the other hand, we develop a synthetic phase augmentation module, which builds upon generative adversarial networks, for populating the internal data by fully leveraging the relation between different phases. By jointly enforcing external attention and populating internal data representation during training, our proposed method outperforms other competing methods and substantially improves the popular DeepLab-v3+ baseline by more than 7% in terms of average DSC, which confirms its effectiveness.
Anomaly segmentation is a crucial task for safety-critical applications, such as autonomous driving in urban scenes, where the goal is to detect out-of-distribution (OOD) objects with categories which are unseen during training. The core challenge of this task is how to distinguish hard in-distribution samples from OOD samples, which has not been explicitly discussed yet. In this paper, we propose a novel and simple approach named Consensus Synergizes with Memory (CosMe) to address this challenge, inspired by the psychology finding that groups perform better than individuals on memory tasks. The main idea is 1) building a memory bank which consists of seen prototypes extracted from multiple layers of the pre-trained segmentation model and 2) training an auxiliary model that mimics the behavior of the pre-trained model, and then measuring the consensus of their mid-level features as complementary cues that synergize with the memory bank. CosMe is good at distinguishing between hard in-distribution examples and OOD samples. Experimental results on several urban scene anomaly segmentation datasets show that CosMe outperforms previous approaches by large margins.
It has been a common practice to adopt the ResBlock, which learns the difference between blurry and sharp image pairs, in end-to-end image deblurring architectures. Reconstructing a sharp image from its blurry counterpart requires changes regarding both low- and high-frequency information. Although conventional ResBlock may have good abilities in capturing the high-frequency components of images, it tends to overlook the low-frequency information. Moreover, ResBlock usually fails to felicitously model the long-distance information which is non-trivial in reconstructing a sharp image from its blurry counterpart. In this paper, we present a Residual Fast Fourier Transform with Convolution Block (Res FFT-Conv Block), capable of capturing both long-term and short-term interactions, while integrating both low- and high-frequency residual information. Res FFT-Conv Block is a conceptually simple yet computationally efficient, and plug-and-play block, leading to remarkable performance gains in different architectures. With Res FFT-Conv Block, we further propose a Deep Residual Fourier Transformation (DeepRFT) framework, based upon MIMO-UNet, achieving state-of-the-art image deblurring performance on GoPro, HIDE, RealBlur and DPDD datasets. Experiments show our DeepRFT can boost image deblurring performance significantly (e.g., with 1.09 dB improvement in PSNR on GoPro dataset compared with MIMO-UNet), and DeepRFT+ even reaches 33.23 dB in PSNR on GoPro dataset.
The success of language Transformers is primarily attributed to the pretext task of masked language modeling (MLM), where texts are first tokenized into semantically meaningful pieces. In this work, we study masked image modeling (MIM) and indicate the advantages and challenges of using a semantically meaningful visual tokenizer. We present a self-supervised framework iBOT that can perform masked prediction with an online tokenizer. Specifically, we perform self-distillation on masked patch tokens and take the teacher network as the online tokenizer, along with self-distillation on the class token to acquire visual semantics. The online tokenizer is jointly learnable with the MIM objective and dispenses with a multi-stage training pipeline where the tokenizer needs to be pre-trained beforehand. We show the prominence of iBOT by achieving an 81.6% linear probing accuracy and an 86.3% fine-tuning accuracy evaluated on ImageNet-1K. Beyond the state-of-the-art image classification results, we underline emerging local semantic patterns, which helps the models to obtain strong robustness against common corruptions and achieve leading results on dense downstream tasks, eg., object detection, instance segmentation, and semantic segmentation.
Entity linking (EL) is the process of linking entity mentions appearing in web text with their corresponding entities in a knowledge base. EL plays an important role in the fields of knowledge engineering and data mining, underlying a variety of downstream applications such as knowledge base population, content analysis, relation extraction, and question answering. In recent years, deep learning (DL), which has achieved tremendous success in various domains, has also been leveraged in EL methods to surpass traditional machine learning based methods and yield the state-of-the-art performance. In this survey, we present a comprehensive review and analysis of existing DL based EL methods. First of all, we propose a new taxonomy, which organizes existing DL based EL methods using three axes: embedding, feature, and algorithm. Then we systematically survey the representative EL methods along the three axes of the taxonomy. Later, we introduce ten commonly used EL data sets and give a quantitative performance analysis of DL based EL methods over these data sets. Finally, we discuss the remaining limitations of existing methods and highlight some promising future directions.
Recently, the graph neural network (GNN) has shown great power in matrix completion by formulating a rating matrix as a bipartite graph and then predicting the link between the corresponding user and item nodes. The majority of GNN-based matrix completion methods are based on Graph Autoencoder (GAE), which considers the one-hot index as input, maps a user (or item) index to a learnable embedding, applies a GNN to learn the node-specific representations based on these learnable embeddings and finally aggregates the representations of the target users and its corresponding item nodes to predict missing links. However, without node content (i.e., side information) for training, the user (or item) specific representation can not be learned in the inductive setting, that is, a model trained on one group of users (or items) cannot adapt to new users (or items). To this end, we propose an inductive matrix completion method using GAE (IMC-GAE), which utilizes the GAE to learn both the user-specific (or item-specific) representation for personalized recommendation and local graph patterns for inductive matrix completion. Specifically, we design two informative node features and employ a layer-wise node dropout scheme in GAE to learn local graph patterns which can be generalized to unseen data. The main contribution of our paper is the capability to efficiently learn local graph patterns in GAE, with good scalability and superior expressiveness compared to previous GNN-based matrix completion methods. Furthermore, extensive experiments demonstrate that our model achieves state-of-the-art performance on several matrix completion benchmarks. Our official code is publicly available.
With the increasing scale of search engine marketing, designing an efficient bidding system is becoming paramount for the success of e-commerce companies. The critical challenges faced by a modern industrial-level bidding system include: 1. the catalog is enormous, and the relevant bidding features are of high sparsity; 2. the large volume of bidding requests induces significant computation burden to both the offline and online serving. Leveraging extraneous user-item information proves essential to mitigate the sparsity issue, for which we exploit the natural language signals from the users' query and the contextual knowledge from the products. In particular, we extract the vector representations of ads via the Transformer model and leverage their geometric relation to building collaborative bidding predictions via clustering. The two-step procedure also significantly reduces the computation stress of bid evaluation and optimization. In this paper, we introduce the end-to-end structure of the bidding system for search engine marketing for Walmart e-commerce, which successfully handles tens of millions of bids each day. We analyze the online and offline performances of our approach and discuss how we find it as a production-efficient solution.