An-An Liu

Zheren Fu, Zhendong Mao, Bo Hu et al.

Deep metric learning aims to learn an embedding space, where semantically similar samples are close together and dissimilar ones are repelled against. To explore more hard and informative training signals for augmentation and generalization, recent methods focus on generating synthetic samples to boost metric learning losses. However, these methods just use the deterministic and class-independent generations (e.g., simple linear interpolation), which only can cover the limited part of distribution spaces around original samples. They have overlooked the wide characteristic changes of different classes and can not model abundant intra-class variations for generations. Therefore, generated samples not only lack rich semantics within the certain class, but also might be noisy signals to disturb training. In this paper, we propose a novel intra-class adaptive augmentation (IAA) framework for deep metric learning. We reasonably estimate intra-class variations for every class and generate adaptive synthetic samples to support hard samples mining and boost metric learning losses. Further, for most datasets that have a few samples within the class, we propose the neighbor correction to revise the inaccurate estimations, according to our correlation discovery where similar classes generally have similar variation distributions. Extensive experiments on five benchmarks show our method significantly improves and outperforms the state-of-the-art methods on retrieval performances by 3%-6%. Our code is available at https://github.com/darkpromise98/IAA

Weizhi Nie, Chen Zhang, Dan Song et al.

The chest X-ray is often utilized for diagnosing common thoracic diseases. In recent years, many approaches have been proposed to handle the problem of automatic diagnosis based on chest X-rays. However, the scarcity of labeled data for related diseases still poses a huge challenge to an accurate diagnosis. In this paper, we focus on the thorax disease diagnostic problem and propose a novel deep reinforcement learning framework, which introduces prior knowledge to direct the learning of diagnostic agents and the model parameters can also be continuously updated as the data increases, like a person's learning process. Especially, 1) prior knowledge can be learned from the pre-trained model based on old data or other domains' similar data, which can effectively reduce the dependence on target domain data, and 2) the framework of reinforcement learning can make the diagnostic agent as exploratory as a human being and improve the accuracy of diagnosis through continuous exploration. The method can also effectively solve the model learning problem in the case of few-shot data and improve the generalization ability of the model. Finally, our approach's performance was demonstrated using the well-known NIH ChestX-ray 14 and CheXpert datasets, and we achieved competitive results. The source code can be found here: \url{https://github.com/NeaseZ/MARL}.

Jianhao Zeng, Dan Song, Weizhi Nie et al.

Generative Adversarial Networks (GANs) dominate the research field in image-based virtual try-on, but have not resolved problems such as unnatural deformation of garments and the blurry generation quality. While the generative quality of diffusion models is impressive, achieving controllability poses a significant challenge when applying it to virtual try-on and multiple denoising iterations limit its potential for real-time applications. In this paper, we propose Controllable Accelerated virtual Try-on with Diffusion Model (CAT-DM). To enhance the controllability, a basic diffusion-based virtual try-on network is designed, which utilizes ControlNet to introduce additional control conditions and improves the feature extraction of garment images. In terms of acceleration, CAT-DM initiates a reverse denoising process with an implicit distribution generated by a pre-trained GAN-based model. Compared with previous try-on methods based on diffusion models, CAT-DM not only retains the pattern and texture details of the inshop garment but also reduces the sampling steps without compromising generation quality. Extensive experiments demonstrate the superiority of CAT-DM against both GANbased and diffusion-based methods in producing more realistic images and accurately reproducing garment patterns.

Yuting Su, Yichen Wei, Weizhi Nie et al.

Emotion detection is a critical technology extensively employed in diverse fields. While the incorporation of commonsense knowledge has proven beneficial for existing emotion detection methods, dialogue-based emotion detection encounters numerous difficulties and challenges due to human agency and the variability of dialogue content.In dialogues, human emotions tend to accumulate in bursts. However, they are often implicitly expressed. This implies that many genuine emotions remain concealed within a plethora of unrelated words and dialogues.In this paper, we propose a Dynamic Causal Disentanglement Model based on hidden variable separation, which is founded on the separation of hidden variables. This model effectively decomposes the content of dialogues and investigates the temporal accumulation of emotions, thereby enabling more precise emotion recognition. First, we introduce a novel Causal Directed Acyclic Graph (DAG) to establish the correlation between hidden emotional information and other observed elements. Subsequently, our approach utilizes pre-extracted personal attributes and utterance topics as guiding factors for the distribution of hidden variables, aiming to separate irrelevant ones. Specifically, we propose a dynamic temporal disentanglement model to infer the propagation of utterances and hidden variables, enabling the accumulation of emotion-related information throughout the conversation. To guide this disentanglement process, we leverage the ChatGPT-4.0 and LSTM networks to extract utterance topics and personal attributes as observed information.Finally, we test our approach on two popular datasets in dialogue emotion detection and relevant experimental results verified the model's superiority.

An-An Liu, Guokai Zhang, Yuting Su et al.

Recent developments in text-conditioned image generative models have revolutionized the production of realistic results. Unfortunately, this has also led to an increase in privacy violations and the spread of false information, which requires the need for traceability, privacy protection, and other security measures. However, existing text-to-image paradigms lack the technical capabilities to link traceable messages with image generation. In this study, we introduce a novel task for the joint generation of text to image and watermark (T2IW). This T2IW scheme ensures minimal damage to image quality when generating a compound image by forcing the semantic feature and the watermark signal to be compatible in pixels. Additionally, by utilizing principles from Shannon information theory and non-cooperative game theory, we are able to separate the revealed image and the revealed watermark from the compound image. Furthermore, we strengthen the watermark robustness of our approach by subjecting the compound image to various post-processing attacks, with minimal pixel distortion observed in the revealed watermark. Extensive experiments have demonstrated remarkable achievements in image quality, watermark invisibility, and watermark robustness, supported by our proposed set of evaluation metrics.

Dan Song, Xinwei Fu, Ning Liu et al.

Large-scale pre-trained models have demonstrated impressive performance in vision and language tasks within open-world scenarios. Due to the lack of comparable pre-trained models for 3D shapes, recent methods utilize language-image pre-training to realize zero-shot 3D shape recognition. However, due to the modality gap, pretrained language-image models are not confident enough in the generalization to 3D shape recognition. Consequently, this paper aims to improve the confidence with view selection and hierarchical prompts. Leveraging the CLIP model as an example, we employ view selection on the vision side by identifying views with high prediction confidence from multiple rendered views of a 3D shape. On the textual side, the strategy of hierarchical prompts is proposed for the first time. The first layer prompts several classification candidates with traditional class-level descriptions, while the second layer refines the prediction based on function-level descriptions or further distinctions between the candidates. Remarkably, without the need for additional training, our proposed method achieves impressive zero-shot 3D classification accuracies of 84.44%, 91.51%, and 66.17% on ModelNet40, ModelNet10, and ShapeNet Core55, respectively. Furthermore, we will make the code publicly available to facilitate reproducibility and further research in this area.

Zan Gao, Xinglei Cui, Tao Zhuo et al.

Temporal action localization plays an important role in video analysis, which aims to localize and classify actions in untrimmed videos. The previous methods often predict actions on a feature space of a single-temporal scale. However, the temporal features of a low-level scale lack enough semantics for action classification while a high-level scale cannot provide rich details of the action boundaries. To address this issue, we propose to predict actions on a feature space of multi-temporal scales. Specifically, we use refined feature pyramids of different scales to pass semantics from high-level scales to low-level scales. Besides, to establish the long temporal scale of the entire video, we use a spatial-temporal transformer encoder to capture the long-range dependencies of video frames. Then the refined features with long-range dependencies are fed into a classifier for the coarse action prediction. Finally, to further improve the prediction accuracy, we propose to use a frame-level self attention module to refine the classification and boundaries of each action instance. Extensive experiments show that the proposed method can outperform state-of-the-art approaches on the THUMOS14 dataset and achieves comparable performance on the ActivityNet1.3 dataset. Compared with A2Net (TIP20, Avg\{0.3:0.7\}), Sub-Action (CSVT2022, Avg\{0.1:0.5\}), and AFSD (CVPR21, Avg\{0.3:0.7\}) on the THUMOS14 dataset, the proposed method can achieve improvements of 12.6\%, 17.4\% and 2.2\%, respectively

Wenhui Li, Xinqi Su, Dan Song et al.

Prior image-text matching methods have shown remarkable performance on many benchmark datasets, but most of them overlook the bias in the dataset, which exists in intra-modal and inter-modal, and tend to learn the spurious correlations that extremely degrade the generalization ability of the model. Furthermore, these methods often incorporate biased external knowledge from large-scale datasets as prior knowledge into image-text matching model, which is inevitable to force model further learn biased associations. To address above limitations, this paper firstly utilizes Structural Causal Models (SCMs) to illustrate how intra- and inter-modal confounders damage the image-text matching. Then, we employ backdoor adjustment to propose an innovative Deconfounded Causal Inference Network (DCIN) for image-text matching task. DCIN (1) decomposes the intra- and inter-modal confounders and incorporates them into the encoding stage of visual and textual features, effectively eliminating the spurious correlations during image-text matching, and (2) uses causal inference to mitigate biases of external knowledge. Consequently, the model can learn causality instead of spurious correlations caused by dataset bias. Extensive experiments on two well-known benchmark datasets, i.e., Flickr30K and MSCOCO, demonstrate the superiority of our proposed method.

Qiang Li, Qiuyang Ma, Weizhi Nie et al.

With the development of deep learning techniques, supervised learning has achieved performances surpassing those of humans. Researchers have designed numerous corresponding models for different data modalities, achieving excellent results in supervised tasks. However, with the exponential increase of data in multiple fields, the recognition and classification of unlabeled data have gradually become a hot topic. In this paper, we employed a Reinforcement Learning framework to simulate the cognitive processes of humans for effectively addressing novel class discovery in the Open-set domain. We deployed a Member-to-Leader Multi-Agent framework to extract and fuse features from multi-modal information, aiming to acquire a more comprehensive understanding of the feature space. Furthermore, this approach facilitated the incorporation of self-supervised learning to enhance model training. We employed a clustering method with varying constraint conditions, ranging from strict to loose, allowing for the generation of dependable labels for a subset of unlabeled data during the training phase. This iterative process is similar to human exploratory learning of unknown data. These mechanisms collectively update the network parameters based on rewards received from environmental feedback. This process enables effective control over the extent of exploration learning, ensuring the accuracy of learning in unknown data categories. We demonstrate the performance of our approach in both the 3D and 2D domains by employing the OS-MN40, OS-MN40-Miss, and Cifar10 datasets. Our approach achieves competitive competitive results.

Chenyu Zhang, Lanjun Wang, Yiwen Ma et al.

Text-to-image (T2I) models commonly incorporate defense mechanisms to prevent the generation of sensitive images. Unfortunately, recent jailbreak attacks have shown that adversarial prompts can effectively bypass these mechanisms and induce T2I models to produce sensitive content, revealing critical safety vulnerabilities. However, existing attack methods implicitly assume that the attacker knows the type of deployed defenses, which limits their effectiveness against unknown or diverse defense mechanisms. In this work, we reveal an underexplored vulnerability of T2I models to metaphor-based jailbreak attacks (MJA), which aims to attack diverse defense mechanisms without prior knowledge of their type by generating metaphor-based adversarial prompts. Specifically, MJA consists of two modules: an LLM-based multi-agent generation module (LMAG) and an adversarial prompt optimization module (APO). LMAG decomposes the generation of metaphor-based adversarial prompts into three subtasks: metaphor retrieval, context matching, and adversarial prompt generation. Subsequently, LMAG coordinates three LLM-based agents to generate diverse adversarial prompts by exploring various metaphors and contexts. To enhance attack efficiency, APO first trains a surrogate model to predict the attack results of adversarial prompts and then designs an acquisition strategy to adaptively identify optimal adversarial prompts. Extensive experiments on T2I models with various external and internal defense mechanisms demonstrate that MJA achieves stronger attack performance while using fewer queries, compared with six baseline methods. Additionally, we provide an in-depth vulnerability analysis suggesting that metaphor-based adversarial prompts evade safety mechanisms by inducing semantic ambiguity, while sensitive images arise from the model's probabilistic interpretation of concealed semantics.

Erxin Guo, Pei An, You Yang et al.

4D occupancy forecasting is one of the important techniques for autonomous driving, which can avoid potential risk in the complex traffic scenes. Scene flow is a crucial element to describe 4D occupancy map tendency. However, an accurate scene flow is difficult to predict in the real scene. In this paper, we find that BEV scene flow can approximately represent 3D scene flow in most traffic scenes. And coarse BEV scene flow is easy to generate. Under this thought, we propose 4D occupancy forecasting method FSF-Net based on coarse BEV scene flow. At first, we develop a general occupancy forecasting architecture based on coarse BEV scene flow. Then, to further enhance 4D occupancy feature representation ability, we propose a vector quantized based Mamba (VQ-Mamba) network to mine spatial-temporal structural scene feature. After that, to effectively fuse coarse occupancy maps forecasted from BEV scene flow and latent features, we design a U-Net based quality fusion (UQF) network to generate the fine-grained forecasting result. Extensive experiments are conducted on public Occ3D dataset. FSF-Net has achieved IoU and mIoU 9.56% and 10.87% higher than state-of-the-art method. Hence, we believe that proposed FSF-Net benefits to the safety of autonomous driving.

Chenyu Zhang, Lanjun Wang, Yiwen Ma et al.

Text-to-Image(T2I) models typically deploy safety filters to prevent the generation of sensitive images. Unfortunately, recent jailbreaking attack methods manually design prompts for the LLM to generate adversarial prompts, which effectively bypass safety filters while producing sensitive images, exposing safety vulnerabilities of T2I models. However, due to the LLM's limited understanding of the T2I model and its safety filters, existing methods require numerous queries to achieve a successful attack, limiting their practical applicability. To address this issue, we propose Reason2Attack(R2A), which aims to enhance the LLM's reasoning capabilities in generating adversarial prompts by incorporating the jailbreaking attack into the post-training process of the LLM. Specifically, we first propose a CoT example synthesis pipeline based on Frame Semantics, which generates adversarial prompts by identifying related terms and corresponding context illustrations. Using CoT examples generated by the pipeline, we fine-tune the LLM to understand the reasoning path and format the output structure. Subsequently, we incorporate the jailbreaking attack task into the reinforcement learning process of the LLM and design an attack process reward that considers prompt length, prompt stealthiness, and prompt effectiveness, aiming to further enhance reasoning accuracy. Extensive experiments on various T2I models show that R2A achieves a better attack success ratio while requiring fewer queries than baselines. Moreover, our adversarial prompts demonstrate strong attack transferability across both open-source and commercial T2I models.

Ning Xu, Yifei Gao, Hongshuo Tian et al.

In the fundamental statistics course, students are taught to remember the well-known saying: "Correlation is not Causation". Till now, statistics (i.e., correlation) have developed various successful frameworks, such as Transformer and Pre-training large-scale models, which have stacked multiple parallel self-attention blocks to imitate a wide range of tasks. However, in the causation community, how to build an integrated causal framework still remains an untouched domain despite its excellent intervention capabilities. In this paper, we propose the Causal Graph Routing (CGR) framework, an integrated causal scheme relying entirely on the intervention mechanisms to reveal the cause-effect forces hidden in data. Specifically, CGR is composed of a stack of causal layers. Each layer includes a set of parallel deconfounding blocks from different causal graphs. We combine these blocks via the concept of the proposed sufficient cause, which allows the model to dynamically select the suitable deconfounding methods in each layer. CGR is implemented as the stacked networks, integrating no confounder, back-door adjustment, front-door adjustment, and probability of sufficient cause. We evaluate this framework on two classical tasks of CV and NLP. Experiments show CGR can surpass the current state-of-the-art methods on both Visual Question Answer and Long Document Classification tasks. In particular, CGR has great potential in building the "causal" pre-training large-scale model that effectively generalizes to diverse tasks. It will improve the machines' comprehension of causal relationships within a broader semantic space.

Chenyu Zhang, Lanjun Wang, Anan Liu

Recent developments in text-to-image models, particularly Stable Diffusion, have marked significant achievements in various applications. With these advancements, there are growing safety concerns about the vulnerability of the model that malicious entities exploit to generate targeted harmful images. However, the existing methods in the vulnerability of the model mainly evaluate the alignment between the prompt and generated images, but fall short in revealing the vulnerability associated with targeted image generation. In this study, we formulate the problem of targeted adversarial attack on Stable Diffusion and propose a framework to generate adversarial prompts. Specifically, we design a gradient-based embedding optimization method to craft reliable adversarial prompts that guide stable diffusion to generate specific images. Furthermore, after obtaining successful adversarial prompts, we reveal the mechanisms that cause the vulnerability of the model. Extensive experiments on two targeted attack tasks demonstrate the effectiveness of our method in targeted attacks. The code can be obtained in https://github.com/datar001/Revealing-Vulnerabilities-in-Stable-Diffusion-via-Targeted-Attacks.

Dan Song, Shumeng Huo, Wenhui Li et al.

The classification and recognition of maritime objects are crucial for enhancing maritime safety, monitoring, and intelligent sea environment prediction. However, existing unsupervised methods for maritime object classification often struggle with the long-tail data distributions in both object categories and weather conditions. In this paper, we construct a dataset named AIMO produced by large-scale generative models with diverse weather conditions and balanced object categories, and collect a dataset named RMO with real-world images where long-tail issue exists. We propose a novel domain adaptation approach that leverages AIMO (source domain) to address the problem of limited labeled data, unbalanced distribution and domain shift in RMO (target domain), enhance the generalization of source features with the Vision-Language Models such as CLIP, and propose a difficulty score for curriculum learning to optimize training process. Experimental results shows that the proposed method significantly improves the classification accuracy, particularly for samples within rare object categories and weather conditions. Datasets and codes will be publicly available at https://github.com/honoria0204/AIMO.

Weizhi Nie, Chen Zhang, Dan Song et al.

The chest X-ray (CXR) is one of the most common and easy-to-get medical tests used to diagnose common diseases of the chest. Recently, many deep learning-based methods have been proposed that are capable of effectively classifying CXRs. Even though these techniques have worked quite well, it is difficult to establish whether what these algorithms actually learn is the cause-and-effect link between diseases and their causes or just how to map labels to photos.In this paper, we propose a causal approach to address the CXR classification problem, which constructs a structural causal model (SCM) and uses the backdoor adjustment to select effective visual information for CXR classification. Specially, we design different probability optimization functions to eliminate the influence of confounders on the learning of real causality. Experimental results demonstrate that our proposed method outperforms the open-source NIH ChestX-ray14 in terms of classification performance.

Guokai Zhang, Lanjun Wang, Yuting Su et al.

Today, the family of latent diffusion models (LDMs) has gained prominence for its high quality outputs and scalability. This has also raised security concerns on social media, as malicious users can create and disseminate harmful content. Existing approaches typically involve training specific components or entire generative models to embed a watermark in generated images for traceability and responsibility. However, in the fast-evolving era of AI-generated content (AIGC), the rapid iteration and modification of LDMs makes retraining with watermark models costly. To address the problem, we propose MarkPlugger, a generalizable plug-and-play watermark framework without LDM retraining. In particular, to reduce the disturbance of the watermark on the semantics of the generated image, we try to identify a watermark representation that is approaching orthogonal to the semantic in latent space, and apply an additive fusion strategy for the watermark and the semantic. Without modifying any components of the LDMs, we embed diverse watermarks in latent space, adapting to the denoising process. Our experimental findings reveal that our method effectively harmonizes image quality and watermark recovery rate. We also have validated that our method is generalized to multiple official versions and modified variants of LDMs, even without retraining the watermark model. Furthermore, it performs robustly under various attacks of different intensities.

Zibo Xu, Qiang Li, Weizhi Nie et al.

Medical Visual Question Answering (MedVQA) aims to answer medical questions according to medical images. However, the complexity of medical data leads to confounders that are difficult to observe, so bias between images and questions is inevitable. Such cross-modal bias makes it challenging to infer medically meaningful answers. In this work, we propose a causal inference framework for the MedVQA task, which effectively eliminates the relative confounding effect between the image and the question to ensure the precision of the question-answering (QA) session. We are the first to introduce a novel causal graph structure that represents the interaction between visual and textual elements, explicitly capturing how different questions influence visual features. During optimization, we apply the mutual information to discover spurious correlations and propose a multi-variable resampling front-door adjustment method to eliminate the relative confounding effect, which aims to align features based on their true causal relevance to the question-answering task. In addition, we also introduce a prompt strategy that combines multiple prompt forms to improve the model's ability to understand complex medical data and answer accurately. Extensive experiments on three MedVQA datasets demonstrate that 1) our method significantly improves the accuracy of MedVQA, and 2) our method achieves true causal correlations in the face of complex medical data.

Ning Xu, Tingting Zhang, Hongshuo Tian et al.

News captioning task aims to generate sentences by describing named entities or concrete events for an image with its news article. Existing methods have achieved remarkable results by relying on the large-scale pre-trained models, which primarily focus on the correlations between the input news content and the output predictions. However, the news captioning requires adhering to some fundamental rules of news reporting, such as accurately describing the individuals and actions associated with the event. In this paper, we propose the rule-driven news captioning method, which can generate image descriptions following designated rule signal. Specifically, we first design the news-aware semantic rule for the descriptions. This rule incorporates the primary action depicted in the image (e.g., "performing") and the roles played by named entities involved in the action (e.g., "Agent" and "Place"). Second, we inject this semantic rule into the large-scale pre-trained model, BART, with the prefix-tuning strategy, where multiple encoder layers are embedded with news-aware semantic rule. Finally, we can effectively guide BART to generate news sentences that comply with the designated rule. Extensive experiments on two widely used datasets (i.e., GoodNews and NYTimes800k) demonstrate the effectiveness of our method.

Ning Xu, Yanhui Wang, Tingting Zhang et al.

News captioning aims to describe an image with its news article body as input. It greatly relies on a set of detected named entities, including real-world people, organizations, and places. This paper exploits commonsense knowledge to understand named entities for news captioning. By ``understand'', we mean correlating the news content with common sense in the wild, which helps an agent to 1) distinguish semantically similar named entities and 2) describe named entities using words outside of training corpora. Our approach consists of three modules: (a) Filter Module aims to clarify the common sense concerning a named entity from two aspects: what does it mean? and what is it related to?, which divide the common sense into explanatory knowledge and relevant knowledge, respectively. (b) Distinguish Module aggregates explanatory knowledge from node-degree, dependency, and distinguish three aspects to distinguish semantically similar named entities. (c) Enrich Module attaches relevant knowledge to named entities to enrich the entity description by commonsense information (e.g., identity and social position). Finally, the probability distributions from both modules are integrated to generate the news captions. Extensive experiments on two challenging datasets (i.e., GoodNews and NYTimes) demonstrate the superiority of our method. Ablation studies and visualization further validate its effectiveness in understanding named entities.

Weizhi Nie, Chen Zhang, Dan song et al.

The chest X-ray (CXR) is commonly employed to diagnose thoracic illnesses, but the challenge of achieving accurate automatic diagnosis through this method persists due to the complex relationship between pathology. In recent years, various deep learning-based approaches have been suggested to tackle this problem but confounding factors such as image resolution or noise problems often damage model performance. In this paper, we focus on the chest X-ray classification task and proposed an interpretable instrumental variable (IV) learning framework, to eliminate the spurious association and obtain accurate causal representation. Specifically, we first construct a structural causal model (SCM) for our task and learn the confounders and the preliminary representations of IV, we then leverage electronic health record (EHR) as auxiliary information and we fuse the above feature with our transformer-based semantic fusion module, so the IV has the medical semantic. Meanwhile, the reliability of IV is further guaranteed via the constraints of mutual information between related causal variables. Finally, our approach's performance is demonstrated using the MIMIC-CXR, NIH ChestX-ray 14, and CheXpert datasets, and we achieve competitive results.

Zan Gao, Chao Sun, Zhiyong Cheng et al.

Finding tampered regions in images is a hot research topic in machine learning and computer vision. Although many image manipulation location algorithms have been proposed, most of them only focus on the RGB images with different color spaces, and the frequency information that contains the potential tampering clues is often ignored. In this work, a novel end-to-end two-stream boundary-aware network (abbreviated as TBNet) is proposed for generic image manipulation localization in which the RGB stream, the frequency stream, and the boundary artifact location are explored in a unified framework. Specifically, we first design an adaptive frequency selection module (AFS) to adaptively select the appropriate frequency to mine inconsistent statistics and eliminate the interference of redundant statistics. Then, an adaptive cross-attention fusion module (ACF) is proposed to adaptively fuse the RGB feature and the frequency feature. Finally, the boundary artifact location network (BAL) is designed to locate the boundary artifacts for which the parameters are jointly updated by the outputs of the ACF, and its results are further fed into the decoder. Thus, the parameters of the RGB stream, the frequency stream, and the boundary artifact location network are jointly optimized, and their latent complementary relationships are fully mined. The results of extensive experiments performed on four public benchmarks of the image manipulation localization task, namely, CASIA1.0, COVER, Carvalho, and In-The-Wild, demonstrate that the proposed TBNet can significantly outperform state-of-the-art generic image manipulation localization methods in terms of both MCC and F1.

Chunxiao Liu, Zhendong Mao, An-An Liu et al.

Learning semantic correspondence between image and text is significant as it bridges the semantic gap between vision and language. The key challenge is to accurately find and correlate shared semantics in image and text. Most existing methods achieve this goal by representing the shared semantic as a weighted combination of all the fragments (image regions or text words), where fragments relevant to the shared semantic obtain more attention, otherwise less. However, despite relevant ones contribute more to the shared semantic, irrelevant ones will more or less disturb it, and thus will lead to semantic misalignment in the correlation phase. To address this issue, we present a novel Bidirectional Focal Attention Network (BFAN), which not only allows to attend to relevant fragments but also diverts all the attention into these relevant fragments to concentrate on them. The main difference with existing works is they mostly focus on learning attention weight while our BFAN focus on eliminating irrelevant fragments from the shared semantic. The focal attention is achieved by pre-assigning attention based on inter-modality relation, identifying relevant fragments based on intra-modality relation and reassigning attention. Furthermore, the focal attention is jointly applied in both image-to-text and text-to-image directions, which enables to avoid preference to long text or complex image. Experiments show our simple but effective framework significantly outperforms state-of-the-art, with relative Recall@1 gains of 2.2% on both Flicr30K and MSCOCO benchmarks.