Ye Zhao

The significant success of machine learning models is mainly based on a large amount of data for training iterations, but this limits their generalization for few-shot data. Some existing models utilize the extensive visual and textual modal knowledge of vision-language pre-trained models (VLPs) to compensate for the data scarcity problem. However, they may suffer from a classification bias problem during the fusion of multi-modal information since that they focus on the inter-modal matching while neglecting intra-modal recognition for few-shot images. In this paper, we propose a novel few-shot model with mixed-modal prototypes by partial-tuning the VLPs for better information fusion. It aims to yield a high-quality class prototype representation by integrating the abundant multi-modal knowledge of VLPs and the specific-task information of low-shot visual data. Specifically, we introduce an image-text alignment module to ensure the consistency of the few-shot visual representation and the textual knowledge of VLPs at the feature space. A self-similar learning module is designed to excavate the local and detailed characters of specific class, which is crucial under the data scarcity. Additionally, to preserve the generalizable pre-trained knowledge in the maximum extent, we partial-tune the parameters of VLPs to adapt for the few-shot tasks. To sum up, we mix multi-modal information at the feature representation level instead of fusing multi-modal matching similarities, which effectively mitigates classification bias and ultimately enhances the model performance for few-shot data. The extensive experiments are conducted to evaluate the effectiveness of our model on 11 benchmark datasets and the results show its promising.

Cross-lingual image captioning is a challenging task that requires addressing both cross-lingual and cross-modal obstacles in multimedia analysis. The crucial issue in this task is to model the global and the local matching between the image and different languages. Existing cross-modal embedding methods based on the transformer architecture oversee the local matching between the image region and monolingual words, especially when dealing with diverse languages. To overcome these limitations, we propose an Embedded Heterogeneous Attention Transformer (EHAT) to establish cross-domain relationships and local correspondences between images and different languages by using a heterogeneous network. EHAT comprises Masked Heterogeneous Cross-attention (MHCA), Heterogeneous Attention Reasoning Network (HARN), and Heterogeneous Co-attention (HCA). The HARN serves as the core network and it captures cross-domain relationships by leveraging visual bounding box representation features to connect word features from two languages and to learn heterogeneous maps. MHCA and HCA facilitate cross-domain integration in the encoder through specialized heterogeneous attention mechanisms, enabling a single model to generate captions in two languages. We evaluate our approach on the MSCOCO dataset to generate captions in English and Chinese, two languages that exhibit significant differences in their language families. The experimental results demonstrate the superior performance of our method compared to existing advanced monolingual methods. Our proposed EHAT framework effectively addresses the challenges of cross-lingual image captioning, paving the way for improved multilingual image analysis and understanding.

In recent years, label-free model evaluation has been developed to estimate the performance of models on unlabeled test sets. However, we find that existing methods perform poorly in environments with out-of-distribution (OOD) data. To address this issue, we propose a novel automatic model evaluation method using OOD detection to reduce the impact of OOD data on model evaluation. Specifically, we use the representation of datasets to train a neural network for accuracy prediction and employ energy-based OOD detection to exclude OOD data during testing. We conducted experiments on several benchmark datasets with varying amounts of OOD data (SVHN, ISUN, ImageNet, and LSUN) and demonstrated that our method reduces the RMSE compared to existing methods by at least 1.27%. Additionally, we tested our method on transformed datasets and datasets with a high proportion of OOD data, and the results show its robustness.

Text-based person search (TBPS) is of significant importance in intelligent surveillance, which aims to retrieve pedestrian images with high semantic relevance to a given text description. This retrieval task is characterized with both modal heterogeneity and fine-grained matching. To implement this task, one needs to extract multi-scale features from both image and text domains, and then perform the cross-modal alignment. However, most existing approaches only consider the alignment confined at their individual scales, e.g., an image-sentence or a region-phrase scale. Such a strategy adopts the presumable alignment in feature extraction, while overlooking the cross-scale alignment, e.g., image-phrase. In this paper, we present a transformer-based model to extract multi-scale representations, and perform Asymmetric Cross-Scale Alignment (ACSA) to precisely align the two modalities. Specifically, ACSA consists of a global-level alignment module and an asymmetric cross-attention module, where the former aligns an image and texts on a global scale, and the latter applies the cross-attention mechanism to dynamically align the cross-modal entities in region/image-phrase scales. Extensive experiments on two benchmark datasets CUHK-PEDES and RSTPReid demonstrate the effectiveness of our approach. Codes are available at https://github.com/mul-hjh/ACSA .

Text-based person search (TBPS) is of significant importance in intelligent surveillance, which aims to retrieve pedestrian images with high semantic relevance to a given text description. This retrieval task is characterized with both modal heterogeneity and fine-grained matching. To implement this task, one needs to extract multi-scale features from both image and text domains, and then perform the cross-modal alignment. However, most existing approaches only consider the alignment confined at their individual scales, e.g., an image-sentence or a region-phrase scale. Such a strategy adopts the presumable alignment in feature extraction, while overlooking the cross-scale alignment, e.g., image-phrase. In this paper, we present a transformer-based model to extract multi-scale representations, and perform Asymmetric Cross-Scale Alignment (ACSA) to precisely align the two modalities. Specifically, ACSA consists of a global-level alignment module and an asymmetric cross-attention module, where the former aligns an image and texts on a global scale, and the latter applies the cross-attention mechanism to dynamically align the cross-modal entities in region/image-phrase scales. Extensive experiments on two benchmark datasets CUHK-PEDES and RSTPReid demonstrate the effectiveness of our approach. Codes are available at \href{url}{https://github.com/mul-hjh/ACSA}.

Zero‐shot learning is dedicated to solving the classification problem of unseen categories, while generalized zero‐shot learning aims to classify the samples selected from both seen classes and unseen classes, in which “seen” and “unseen” classes indicate whether they can be used in the training process, and if so, they indicate seen classes, and vice versa. Nowadays, with the promotion of deep learning technology, the performance of zero‐shot learning has been greatly improved. Generalized zero‐shot learning is a challenging topic that has promising prospects in many realistic scenarios. Although the zero‐shot learning task has made gratifying progress, there is still a strong deviation between seen classes and unseen classes in the existing methods. Recent methods focus on learning a unified semantic‐aligned visual representation to transfer knowledge between two domains, while ignoring the intrinsic characteristics of visual features which are discriminative enough to be classified by itself. To solve the above problems, we propose a novel model that uses the discriminative information of visual features to optimize the generative module, in which the generative module is a dual generation network framework composed of conditional VAE and improved WGAN. Specifically, the model uses the discrimination information of visual features, according to the relevant semantic embedding, synthesizes the visual features of unseen categories by using the learned generator, and then trains the final softmax classifier by using the generated visual features, thus realizing the recognition of unseen categories. In addition, this paper also analyzes the effect of the additional classifiers with different structures on the transmission of discriminative information. We have conducted a lot of experiments on six commonly used benchmark datasets (AWA1, AWA2, APY, FLO, SUN, and CUB). The experimental results show that our model outperforms several state‐of‐the‐art methods for both traditional as well as generalized zero‐shot learning.

The main challenge of person re-identification (re-id) lies in the strikingly discrepancy between different camera views, including illumination, background and human pose. Existing person re-id methods rely mostly on implicit solutions, such as seeking robust features or designing discriminative distance metrics. Compared to these methods, human solutions are more straightforward. That is, imagine the appearance of the target person under different camera views before matching target person. The key idea is that human can intuitively implement viewpoint transfer, noting the association of the target person under different camera views but the machine failed. In this paper, we attempt to imitate such human behavior that transfer person image to certain camera views before matching. In practice, we propose a conditional transfer network (cTransNet) that conditionally implement viewpoint transfer, which transfers image to the viewpoint with the biggest domain gap through a variant of Generative Adversarial Networks (GANs). After that, we obtain hybrid person representation by fusing the feature of original image with the transferred image then perform similarity ranking according to cosine distance. Compared with former methods, we propose a human-like approach and obtains consistent improvement of the rank-1 precision over the baseline in Market-1501, DukeMTMC-ReID and MSMT17 dataset by 3% ,4%,4%, respectively.