论文检索

Menglin Wang 0001, Xiaojin Gong

Supervised person re-identification assumes that a person has images captured under multiple cameras. However when cameras are placed in distance, a person rarely appears in more than one camera. This paper thus studies person re-ID under such isolated camera supervised (ISCS) setting. Instead of trying to generate fake cross-camera features like previous methods, we explore a novel perspective by making efficient use of the variation in training data. Under ISCS setting, a person only has limited images from a single camera, so the camera bias becomes a critical issue confounding ID discrimination. Cross-camera images are prone to being recognized as different IDs simply by camera style. To eliminate the confounding effect of camera bias, we propose to learn both intra- and inter-camera invariance under a unified framework. First, we construct style-consistent environments via clustering, and perform prototypical contrastive learning within each environment. Meanwhile, strongly augmented images are contrasted with original prototypes to enforce intra-camera augmentation invariance. For inter-camera invariance, we further design a much improved variant of multi-camera negative loss that optimizes the distance of multi-level negatives. The resulting model learns to be invariant to both subtle and severe style variation within and cross-camera. On multiple benchmarks, we conduct extensive experiments and validate the effectiveness and superiority of the proposed method. Code will be available athttps://github.com/Terminator8758/IICI.

Zhen Zhao 0001, Meng Zhao 0003, Ye Liu 0013, Di Yin, Luping Zhou

Pseudo-labelling-based semi-supervised learning (SSL) has demonstrated remarkable success in enhancing model performance by effectively leveraging a large amount of unlabeled data. However, existing studies focus mainly on rectifying individual predictions (i.e., pseudo-labels) on each unlabeled instance but ignore the overall prediction statistics from a global perspective. Such neglect may lead to model collapse and performance degradation in SSL, especially in label-scarce scenarios. In this paper, we emphasize the cruciality of global prediction constraints and propose a new SSL method that employs Entropy-based optimization on both Individual and Global predictions of unlabeled instances, dubbed EntInG. Specifically, we propose two criteria for leveraging unlabeled data in SSL: individual prediction entropy minimization (IPEM) and global distribution entropy maximization (GDEM). On the one hand, we show that current dominant SSL methods can be viewed as an implicit form of IPEM improved by recent augmentation techniques. On the other hand, we construct a new distribution loss to encourage GDEM, which greatly benefits producing better pseudo-labels for unlabeled data. Theoretical analysis also demonstrates that our proposed criteria can be derived by enforcing mutual information maximization on unlabeled instances. Despite its simplicity, our proposed method can achieve significant accuracy gains on popular SSL classification benchmarks.

Han Kim, Chunggi Lee, Junsoo Lee 0002, Dohyun Kim, Kwangjin Lee, Moohyun Oh, Daesik Kim

The process of drawing digital comics and animations is a complex process that involves multiple stages. Flat-coloring, the task of filling segmented regions in a line art image with uniform tone and hue, is a particularly time-consuming and labor-intensive task. We have identified that artists suffer from not only adjusting colors in overflowing regions due to line discontinuity but also finding to replace misaligned pixels near the line due to region-bleeding problems (aliasing issues). To address these issues, we propose a holistic data generation pipeline (FlatGAN-DG) that awares the region of line discontinuity and augments the input sketch image to build robust models for noise. In addition, we propose a real-time post-processing method (FlatGAN-PP) that automatically finds and replaces miscolored pixels to alleviate the region-bleeding problems (aliasing issues). To enhance inference speed, we build FlatGAN, which shares the parameters of a generator to predict the foreground, background, and trimap at once to learn in a multi-task manner. Our experimental results show that our method outperforms other rule-and learning-based methods on three different datasets with different painting styles. To evaluate the segmented regions, we collect datasets with the annotation of split-score, merge-hard-score, and merge-easy-score. We also introduce a new evaluation metric (Region Score) on these datasets, validating the efficacy of our methods through a user study. Code is available at https://github.com/hanish3464/FlatGAN.

Danni Yang, Jiayi Ji, Xiaoshuai Sun, Haowei Wang 0001, Yinan Li 0005, Yiwei Ma, Rongrong Ji

Despite considerable progress, the advancement of Panoptic Narrative Grounding (PNG) remains hindered by costly annotations. In this paper, we introduce a novel Semi-Supervised Panoptic Narrative Grounding (SS-PNG) learning scheme, capitalizing on a smaller set of labeled image-text pairs and a larger set of unlabeled pairs to achieve competitive performance. Unlike visual segmentation tasks, PNG involves one pixel belonging to multiple open-ended nouns. As a result, existing multi-class based semi-supervised segmentation frameworks cannot be directly applied to this task. To address this challenge, we first develop a novel SS-PNG Network (SS-PNG-NW) tailored to the SS-PNG setting. We thoroughly investigate strategies such as Burn-In and data augmentation to determine the optimal generic configuration for the SS-PNG-NW. Additionally, to tackle the issue of imbalanced pseudo-label quality, we propose a Quality-Based Loss Adjustment (QLA) approach to adjust the semi-supervised objective, resulting in an enhanced SS-PNG-NW+. Employing our proposed QLA, we improve BCE Loss and Dice loss at pixel and mask levels, respectively. We conduct extensive experiments on PNG datasets, with our SS-PNG-NW+ demonstrating promising results comparable to fully-supervised models across all data ratios. Remarkably, our SS-PNG-NW+ outperforms fully-supervised models with only 30% and 50% supervision data, exceeding their performance by 0.8% and 1.1% respectively. This highlights the effectiveness of our proposed SS-PNG-NW+ in overcoming the challenges posed by limited annotations and enhancing the applicability of PNG tasks. The source code is available at https://github.com/nini0919/SSPNG.

Xiaolei Diao, Daqian Shi, Jian Li, Lida Shi, Mingzhe Yue, Ruihua Qi, Chuntao Li, Hao Xu 0012

Optical character recognition (OCR) methods have been applied to diverse tasks, e.g., street view text recognition and document analysis. Recently, zero-shot OCR has piqued the interest of the research community because it considers a practical OCR scenario with unbalanced data distribution. However, there is a lack of benchmarks for evaluating such zero-shot methods that apply a divide-and-conquer recognition strategy by decomposing characters into radicals. Meanwhile, radical recognition, as another important OCR task, also lacks radical-level annotation for model training. In this paper, we construct an ancient Chinese character image dataset that contains both radical-level and character-level annotations to satisfy the requirements of the above-mentioned methods, namely, ACCID, where radical-level annotations include radical categories, radical locations, and structural relations. To increase the adaptability of ACCID, we propose a splicing-based synthetic character algorithm to augment the training samples and apply an image denoising method to improve the image quality. By introducing character decomposition and recombination, we propose a baseline method for zero-shot OCR. The experimental results demonstrate the validity of ACCID and the baseline model quantitatively and qualitatively.

Wuyuan Xie, Shukang Wang, Rong Zhang, Miaohui Wang

Composite images are generated by combining two or more different photographs, and their content is typically heterogeneous. However, existing unimodal visual redundancy prediction methods are difficult to accurately model the complex characteristics of this image type. In this paper, we investigate the visual redundancy modeling of composite images from an end-to-end multimodal perspective, including four cross-media modalities (i.e., text, brightness, color, and segmentation). Specifically, we design a two-stage cross-modal alignment module based on self-attention mechanism and contrastive learning, and develop a fusion module based on a cross-modal augmentation paradigm. Further, we establish the first cross-media visual redundancy dataset for composite images, which contains 413 groups of cross-modal data and generates 13629 realistic compression distortions using the latest versatile video coding (VVC) standard. Experimental results on nine benchmark datasets demonstrate the effectiveness of our method, outperforming seven representative methods.

Wenfeng Liu, Xudong Wang, Lei Tan, Yan Zhang 0109, Pingyang Dai, Yongjian Wu 0001, Rongrong Ji

Person re-identification (Re-ID) has been extensively investigated in recent years. However, many existing paradigms rely on holistic person regions for matching, disregarding the challenges posed by occlusions in real-world scenarios. Recent methods have explored occlusion augmentation or external semantic cues. Nevertheless, these approaches tend to be coarse-grained, discarding valuable semantic information in local regions when determining them as occlusions. In this paper, we propose a Fine-grained Occlusion Disentanglement Network (FODN) that can extract more information from limited person regions. Specifically, we propose a fine-grained occlusion augmentation scheme to generate diverse occlusion data and employ bilinear interpolation and downsampling strategies to obtain fine-grained occlusion labels. We then design an occlusion feature disentanglement Module that decouples norm and angle from features and supervises the occlusion-aware task using the aforementioned occlusion labeling and person re-identification tasks, respectively, resulting in more robust features. Additionally, we propose a dynamic local weight controller to balance the relative importance of various human body parts, thereby improving the model's ability to mine more effective local features from limited human body regions after occlusion removal. Comprehensive experiments on various person Re-ID benchmarks demonstrate the superiority of FODN over state-of-the-art methods.

Wei Yang 0041, Zhengru Fang, Tianle Zhang, Shiguang Wu 0001, Chi Lu 0001

Multimodal recommendation system has been widely used in short video platform, e-commerce platform and news media. Multimodal data contains information such as product image and product text, which is often used as auxiliary signal to improve the effect of recommendation system significantly. In order to alleviate the problems of data sparsity and noise, some researchers construct data augmentation to use self-supervised learning to help model training. These methods have achieved certain results. However, most of the work is based on data augmentation in random ways, such as random masking and random perturbation. This random method is likely to lose important information and introduce new noise, resulting in biased augmentation data. Therefore, we propose a Modal-aware Bias Constrained Contrastive Learning method (BCCL) to solve the above problems. Specifically, BCCL introduces a bias-constrained data augmentation method to ensure the quality of augmentation samples. Then the multi-modal semantic information is modeled by the designed modal awareness module. Furthermore, we propose a information alignment module to improve the sparse modal feature learning of the model. We conducted a comprehensive experiment on three real-world data sets, and the experimental results showed that the proposed BCCL outperformed all the state-of-art methods. In-depth experiments have verified the effectiveness of our proposed modules.

Zhenpeng Song, Qinliang Su, Jiayang Chen

By noticing the superior ability of contrastive learning in representation learning, several recent works have proposed to use it to learn semantic-rich hash codes. However, due to the absence of label information, existing contrastive-based hashing methods simply follow contrastive learning by only using the augmentation of the anchor as positive, while treating all other samples in the batch as negatives, resulting in the ignorance of a large number of potential positives. Consequently, the learned hash codes tend to be distributed dispersedly in the space, making their distances unable to accurately reflect their semantic similarities. To address this issue, we propose to exploit the similarity knowledge and hidden structure of the dataset. Specifically, we first develop an intuitive approach based on self-training that comprises two main components, a pseudo-label predictor and a hash code improving module, which mutually benefit from each other by utilizing the output from one another, in conjunction with the similarity knowledge obtained from pre-trained models. Furthermore, we subjected the intuitive approach to a more rigorous probabilistic framework and propose CGHash, a probabilistic hashing model based on conditional generative models, which is theoretically more reasonable and could model the similarity knowledge and the hidden group structure more accurately. Our extensive experimental results on three image datasets demonstrate that CGHash exhibits significant superiority when compared to both the proposed intuitive approach and existing baselines. Our code is available at https://github.com/KARLSZP/CGHash.

Tianyu Chang, Xun Yang 0001, Xin Luo 0006, Wei Ji 0008, Meng Wang 0001

Visual Instance Retrieval (VIR) is a hot research topic for its wide application in real world, such as object re-identification in smart city scenarios. However, due to the limited style diversity in source training data, most existing VIR models always fail to generalize well to unseen domain. How to improve the generalizability of VIR models has received increasing attention in most recent years. In this paper, we pay attention to the Single Domain Generalization (SDG) based VIR task, a more challenging but practical problem, where the model is only trained on single domain data and directly evaluated on unseen target domain without any fine-tuning or adaptations. In this case, the limited style variance in training data may cause the model learning incorrect reliance on the superficial style feature and reduce the generalizability of the model. To address this issue, we propose a novel Style-Invariant robust Representation Learning (SIRL) method for the challenging task, which mainly aims to first diversify the training data with style augmentation, and then enforce the model to learn style-invariant features. Specifically, we first design an adversarial style synthesis module which learns to synthesize diverse augmented samples with adversarially learned styles. Then, we devise an invariant feature learning module to minimize cross-domain feature inconsistency between source images and style-augmented images for capturing domain-invariant instance features. In this way, we can prevent the model from over-exploiting semantic content-independent cues (e.g., color) as shortcut features, thereby estimating the pairwise instance similarity more robustly. We integrate our SIRL method with SOTA VIR networks and evaluate its effectiveness on several public benchmark datasets. Extensive experiments clearly show that the SIRL method can substantially improve the generalizability of existing VIR networks in the challenging SDG-VIR setting.

Ming Jin 0006, Jinpeng Li 0002

Multimodal emotion recognition based on electroencephalogram (EEG) and compensating physiological signals (e.g., eye tracking) has shown potential in the diagnosis and rehabilitation tracking of depression. Since the multi-channel EEG signals are generally processed as one-dimensional (1-D) graph-like features, existing approaches can only adopt underdeveloped shallow models to recognize emotions. However, these simple models have difficulty decoupling complex emotion patterns due to their limited representation capacity. To address this problem, we propose the graph-to-grid (G2G), a concise and plug-and-play module that transforms the 1-D graph-like data into the two-dimensional (2-D) grid-like data via the numerical relation coding. After that, the well developed deep models, e.g., ResNet can be used to downstream tasks. In addition, G2G simplifies the previous complex multimodal fusion into an input matrix augmentation operation, which greatly reduces the difficulty of model design and parameter tuning. Extensive results on three public datasets (SEED, SEED5 and MPED) indicate that the proposed approach achieves state-of-the-art emotion recognition accuracy in both unimodal and multimodal settings, with good cross-session generalization ability. G2G enables the development of more appropriate multimodal emotion recognition algorithms for follow-up studies. Our code is publicly available at https://github.com/Jinminbox/G2G.

Hanbing Liu, Jun-Yan He, Zhi-Qi Cheng, Wangmeng Xiang, Qize Yang, Wenhao Chai, Gaoang Wang, Xu Bao 0003, Bin Luo 0008, Yifeng Geng 等

The current 3D human pose estimators face challenges in adapting to new datasets due to the scarcity of 2D-3D pose pairs in target domain training sets. We present the Multi-Hypothesis Pose Synthesis Domain Adaptation (PoSynDA) framework to overcome this issue without extensive target domain annotation. Utilizing a diffusion-centric structure, PoSynDA simulates the 3D pose distribution in the target domain, filling the data diversity gap. By incorporating a multi-hypothesis network, it creates diverse pose hypotheses and aligns them with the target domain. Target-specific source augmentation obtains the target domain distribution data from the source domain by decoupling the scale and position parameters. The teacher-student paradigm and low-rank adaptation further refine the process. PoSynDA demonstrates competitive performance on benchmarks, such as Human3.6M, MPI-INF-3DHP, and 3DPW, even comparable with the target-trained MixSTE model. This work paves the way for the practical application of 3D human pose estimation1. The source code is available at https://github.com/hbing-l/PoSynDA.

Zilin Du, Yunxin Li, Xu Guo 0002, Yidan Sun, Boyang Li 0001

Contemporary news reporting increasingly features multimedia content, motivating research on multimedia event extraction. However, the task lacks annotated multimodal training data and artificially generated training data suffer from the distribution shift from the real-world data. In this paper, we propose Cross-modality Augmented Multimedia Event Learning (CAMEL), which successfully utilizes artificially generated multimodal training data and achieves state-of-the-art performance. Conditioned on unimodal training data, we generate multimodal training data using off-the-shelf image generators like Stable Diffusion [45] and image captioners like BLIP [24]. After that, we train the network on the resultant multimodal datasets. In order to learn robust features that are effective across domains, we devise an iterative and gradual training strategy. Substantial experiments show that CAMEL surpasses state-of-the-art (SOTA) baselines on the M2E2 benchmark. On multimedia events in particular, we outperform the prior SOTA by 4.2% F1 on event mention identification and by 9.8% F1 on argument identification, which demonstrates that CAMEL learns synergistic representations from the two modalities. Our work demonstrates a recipe to unleash the power of synthetic training data in structured prediction.

Jianlong Yuan, Jinchao Ge, Zhibin Wang 0004, Yifan Liu 0001

Consistency regularization has been widely studied in recent semi- supervised semantic segmentation methods, and promising per- formance has been achieved. In this work, we propose a new con- sistency regularization framework, termed mutual knowledge dis- tillation (MKD), combined with data and feature augmentation. We introduce two auxiliary mean-teacher models based on consis- tency regularization. More specifically, we use the pseudo-labels generated by a mean teacher to supervise the student network to achieve a mutual knowledge distillation between the two branches. In addition to using image-level strong and weak augmentation, we also discuss feature augmentation. This involves considering various sources of knowledge to distill the student network. Thus, we can significantly increase the diversity of the training samples. Experiments on public benchmarks show that our framework out- performs previous state-of-the-art (SOTA) methods under various semi-supervised settings. Code is available at https://github.com/jianlong-yuan/semi-mmseg.

Jiahua Rao, Zifei Shan, Longpo Liu, Yao Zhou 0011, Yuedong Yang

With the recent progress in large-scale vision and language representation learning, Vision Language Pre-training (VLP) models have achieved promising improvements on various multi-modal downstream tasks. Albeit powerful, these models have not fully leveraged world knowledge to their advantage. A key challenge of knowledge-augmented VLP is the lack of clear connections between knowledge and multi-modal data. Moreover, not all knowledge present in images/texts is useful, therefore prior approaches often struggle to effectively integrate knowledge, visual, and textual information. In this study, we propose REtrieval-based knowledge Augmented Vision Language (REAVL), a novel knowledge-augmented pre-training framework to address the above issues. For the first time, we introduce a knowledge-aware self-supervised learning scheme that efficiently establishes the correspondence between knowledge and multi-modal data and identifies informative knowledge to improve the modeling of alignment and interactions between visual and textual modalities. By adaptively integrating informative knowledge with visual and textual information, REAVL achieves new state-of-the-art performance uniformly on knowledge-based vision-language understanding and multi-modal entity linking tasks, as well as competitive results on general vision-language tasks while only using 0.2% pre-training data of the best models. Our model shows strong sample efficiency and effective knowledge utilization.

Yuehui Han, Jiaxin Chen 0001, Jianjun Qian, Jin Xie 0001

3D point cloud contrastive learning has attracted increasing attention due to its efficient learning ability. By distinguishing the similarity relationship between positive and negative samples in the feature space, it can learn effective point cloud feature representations without manual annotation. However, most point cloud contrastive learning methods construct contrastive samples by perturbing point clouds in data space or introducing multi-modality/format data, which may be difficult to control the intensity of the perturbation or introduce interference from different modalities/formats. To this end, in this paper, we propose a novel graph spectral perturbation based contrastive learning framework (GSPCon) for efficient and robust self-supervised 3D point cloud representation learning. It aims to perform perturbations in the graph spectral domain to construct contrastive samples of the point cloud. Specifically, we first naturally represent the point cloud as a k-nearest neighbors (KNN) graph, and adaptively transform the coordinates of the points into the graph spectral domain based on the graph Fourier transform (GFT). Then we implement data augmentation in the graph spectral domain by perturbing the spectral representations. Finally, the contrastive samples are generated by employing the inverse graph Fourier transform (IGFT) to transform the augmented spectral representations back to the point clouds. Experimental results show that our method achieves the state-of-the-art performance on various downstream tasks. Source code is available at https://github.com/yh-han/GSPCon.git.

Zhaoxin Wang, Handing Wang, Cong Tian 0001, Yaochu Jin

Adversarial training (AT) is one of the most effective ways for deep neural network models to resist adversarial examples. However, there is still a significant gap between robust training accuracy and testing accuracy. Although recent studies have shown that data augmentation can effectively reduce this gap, most methods heavily rely on generating large amounts of training data without considering which features are beneficial for model robustness, making them inefficient. To address the above issue, we propose a two-stage AT algorithm for image data that adopts different data augmentation strategies during the training process to improve model robustness. In the first stage, we focus on the convergence of the algorithm, which uses structure and texture information to guide AT. In the second stage, we introduce a strategy that randomly fuses the data features to generate diverse adversarial examples for AT. We compare our proposed algorithm with five state-of-the-art algorithms on three models, and the experimental results achieve the best robust accuracy under all evaluation metrics on the CIFAR10 dataset, demonstrating the superiority of our method.

Yanbiao Ma, Licheng Jiao, Fang Liu 0001, Shuyuan Yang 0001, Xu Liu 0006, Lingling Li 0002

In scenarios with long-tailed distributions, the model's ability to identify tail classes is limited due to the under-representation of tail samples. Class rebalancing, information augmentation, and other techniques have been proposed to facilitate models to learn the potential distribution of tail classes. The disadvantage is that these methods generally pursue models with balanced class accuracy on the data manifold, while ignoring the ability of the model to resist interference. By constructing noisy data manifold, we found that the robustness of models trained on unbalanced data has a long-tail phenomenon. That is, even if the class accuracy is balanced on the data domain, it still has bias on the noisy data manifold. However, existing methods cannot effectively mitigate the above phenomenon, which makes the model vulnerable in long-tailed scenarios. In this work, we propose an Orthogonal Uncertainty Representation (hOUR) of feature embedding and an end-to-end training strategy to improve the long-tail phenomenon of model robustness. As a general enhancement tool, OUR has excellent compatibility with other methods and does not require additional data generation, ensuring fast and efficient training. Comprehensive evaluations on long-tailed datasets show that our method significantly improves the long-tail phenomenon of robustness, bringing consistent performance gains to other long-tailed learning methods.

Zhuoling Li, Yong Wang 0002

Some recent methods address few-shot classification by integrating visual and semantic prototypes. However, they usually ignore the difference in feature structure between the visual and semantic modalities, which leads to limited performance improvements. In this paper, we propose a novel method, called bimodal integrator (BMI), to better integrate visual and semantic prototypes. In BMI, we first construct a latent space for each modality via a variational autoencoder, and then align the semantic latent space to the visual latent space. Through this semantics-to-vision alignment, the semantic modality is mapped to the visual latent space and has the same feature structure as the visual modality. As a result, the visual and semantic prototypes can be better integrated. In addition, based on the multivariate Gaussian distribution and the prompt engineering, a data augmentation scheme is designed to ensure the accuracy of modality alignment during the training process. Experimental results demonstrate that BMI significantly improves few-shot classification, making simple baselines outperform the most advanced methods on miniImageNet and tieredImageNet datasets.

Decheng Liu, Weizhao Yang, Chunlei Peng, Nannan Wang 0001, Ruimin Hu, Xinbo Gao 0001

Heterogeneous face recognition (HFR) aims to match input face identity across different image modalities. Due to the existing large modality gap and the limited number of training data, HFR is still a challenging problem in biometrics and draws more and more attention. Existing researchers always extract modality invariant features or generate homogeneous images to decrease the modality gap, lacking abundant labeled data to avoid the overfitting problem. In this paper, we proposed a novel Modality-Agnostic Augmented Multi-Collaboration representation for Heterogeneous Face Recognition (MAMCO-HFR) in a semi-supervised manner. The modality-agnostic augmentation strategy is proposed to generate adversarial perturbations to map unlabeled faces into the modality-agnostic domain. The multi-collaboration feature constraint is designed to mine the inherent relationships between diverse layers for discriminative representation. Experiments on several large-scale heterogeneous face datasets (CASIA NIR-VIS 2.0, LAMP-HQ and Tufts Face dataset) prove the proposed algorithm can achieve superior performance compared with state-of-the-art methods. The source code is available at https://github.com/xiyin11/Semi-HFR.