A Multimodal Approach for Cross-Domain Image Retrieval

Image generators are gaining vast amount of popularity and have rapidly changed how digital content is created. With the latest AI technology, millions of high quality images are being generated by the public, which are constantly motivating the research community to push the limits of generative models to create more complex and realistic images. This paper focuses on Cross-Domain Image Retrieval (CDIR) which can be used as an additional tool to inspect collections of generated images by determining the level of similarity between images in a dataset. An ideal retrieval system would be able to generalize to unseen complex images from multiple domains (e.g., photos, drawings and paintings). To address this goal, we propose a novel caption-matching approach that leverages multimodal language-vision architectures pre-trained on large datasets. The method is tested on DomainNet and Office-Home datasets and consistently achieves state-of-the-art performance over the latest approaches in the literature for cross-domain image retrieval. In order to verify the effectiveness with AI-generated images, the method was also put to test with a database composed by samples collected from Midjourney, which is a widely used generative platform for content creation.

Detecting and Triaging Spoofing using Temporal Convolutional Networks

As algorithmic trading and electronic markets continue to transform the landscape of financial markets, detecting and deterring rogue agents to maintain a fair and efficient marketplace is crucial. The explosion of large datasets and the continually changing tricks of the trade make it difficult to adapt to new market conditions and detect bad actors. To that end, we propose a framework that can be adapted easily to various problems in the space of detecting market manipulation. Our approach entails initially employing a labelling algorithm which we use to create a training set to learn a weakly supervised model to identify potentially suspicious sequences of order book states. The main goal here is to learn a representation of the order book that can be used to easily compare future events. Subsequently, we posit the incorporation of expert assessment to scrutinize specific flagged order book states. In the event of an expert's unavailability, recourse is taken to the application of a more complex algorithm on the identified suspicious order book states. We then conduct a similarity search between any new representation of the order book against the expert labelled representations to rank the results of the weak learner. We show some preliminary results that are promising to explore further in this direction

Image edge enhancement for effective image classification

Image classification has been a popular task due to its feasibility in real-world applications. Training neural networks by feeding them RGB images has demonstrated success over it. Nevertheless, improving the classification accuracy and computational efficiency of this process continues to present challenges that researchers are actively addressing. A widely popular embraced method to improve the classification performance of neural networks is to incorporate data augmentations during the training process. Data augmentations are simple transformations that create slightly modified versions of the training data and can be very effective in training neural networks to mitigate overfitting and improve their accuracy performance. In this study, we draw inspiration from high-boost image filtering and propose an edge enhancement-based method as means to enhance both accuracy and training speed of neural networks. Specifically, our approach involves extracting high frequency features, such as edges, from images within the available dataset and fusing them with the original images, to generate new, enriched images. Our comprehensive experiments, conducted on two distinct datasets CIFAR10 and CALTECH101, and three different network architectures ResNet-18, LeNet-5 and CNN-9 demonstrates the effectiveness of our proposed method.

Adaptive Anchor Label Propagation for Transductive Few-Shot Learning

Few-shot learning addresses the issue of classifying images using limited labeled data. Exploiting unlabeled data through the use of transductive inference methods such as label propagation has been shown to improve the performance of few-shot learning significantly. Label propagation infers pseudo-labels for unlabeled data by utilizing a constructed graph that exploits the underlying manifold structure of the data. However, a limitation of the existing label propagation approaches is that the positions of all data points are fixed and might be sub-optimal so that the algorithm is not as effective as possible. In this work, we propose a novel algorithm that adapts the feature embeddings of the labeled data by minimizing a differentiable loss function optimizing their positions in the manifold in the process. Our novel algorithm, Adaptive Anchor Label Propagation}, outperforms the standard label propagation algorithm by as much as 7% and 2% in the 1-shot and 5-shot settings respectively. We provide experimental results highlighting the merits of our algorithm on four widely used few-shot benchmark datasets, namely miniImageNet, tieredImageNet, CUB and CIFAR-FS and two commonly used backbones, ResNet12 and WideResNet-28-10. The source code can be found at https://github.com/MichalisLazarou/A2LP.

Adaptive manifold for imbalanced transductive few-shot learning

Transductive few-shot learning algorithms have showed substantially superior performance over their inductive counterparts by leveraging the unlabeled queries. However, the vast majority of such methods are evaluated on perfectly class-balanced benchmarks. It has been shown that they undergo remarkable drop in performance under a more realistic, imbalanced setting. To this end, we propose a novel algorithm to address imbalanced transductive few-shot learning, named Adaptive Manifold. Our method exploits the underlying manifold of the labeled support examples and unlabeled queries by using manifold similarity to predict the class probability distribution per query. It is parameterized by one centroid per class as well as a set of graph-specific parameters that determine the manifold. All parameters are optimized through a loss function that can be tuned towards class-balanced or imbalanced distributions. The manifold similarity shows substantial improvement over Euclidean distance, especially in the 1-shot setting. Our algorithm outperforms or is on par with other state of the art methods in three benchmark datasets, namely miniImageNet, tieredImageNet and CUB, and three different backbones, namely ResNet-18, WideResNet-28-10 and DenseNet-121. In certain cases, our algorithm outperforms the previous state of the art by as much as 4.2%.

Towards Automated Polyp Segmentation Using Weakly- and Semi-Supervised Learning and Deformable Transformers

Polyp segmentation is a crucial step towards computer-aided diagnosis of colorectal cancer. However, most of the polyp segmentation methods require pixel-wise annotated datasets. Annotated datasets are tedious and time-consuming to produce, especially for physicians who must dedicate their time to their patients. We tackle this issue by proposing a novel framework that can be trained using only weakly annotated images along with exploiting unlabeled images. To this end, we propose three ideas to address this problem, more specifically our contributions are: 1) a novel sparse foreground loss that suppresses false positives and improves weakly-supervised training, 2) a batch-wise weighted consistency loss utilizing predicted segmentation maps from identical networks trained using different initialization during semi-supervised training, 3) a deformable transformer encoder neck for feature enhancement by fusing information across levels and flexible spatial locations. Extensive experimental results demonstrate the merits of our ideas on five challenging datasets outperforming some state-of-the-art fully supervised models. Also, our framework can be utilized to fine-tune models trained on natural image segmentation datasets drastically improving their performance for polyp segmentation and impressively demonstrating superior performance to fully supervised fine-tuning.

Dynamic Knowledge Distillation with A Single Stream Structure for RGB-D Salient Object Detection

RGB-D salient object detection(SOD) demonstrates its superiority on detecting in complex environments due to the additional depth information introduced in the data. Inevitably, an independent stream is introduced to extract features from depth images, leading to extra computation and parameters. This methodology which sacrifices the model size to improve the detection accuracy may impede the practical application of SOD problems. To tackle this dilemma, we propose a dynamic distillation method along with a lightweight framework, which significantly reduces the parameters. This method considers the factors of both teacher and student performance within the training stage and dynamically assigns the distillation weight instead of applying a fixed weight on the student model. Extensive experiments are conducted on five public datasets to demonstrate that our method can achieve competitive performance compared to 10 prior methods through a 78.2MB lightweight structure.

Dynamic Knowledge Distillation with A Single Stream Structure for RGB-DSalient Object Detection

RGB-D salient object detection(SOD) demonstrates its superiority on detecting in complex environments due to the additional depth information introduced in the data. Inevitably, an independent stream is introduced to extract features from depth images, leading to extra computation and parameters. This methodology which sacrifices the model size to improve the detection accuracy may impede the practical application of SOD problems. To tackle this dilemma, we propose a dynamic distillation method along with a lightweight framework, which significantly reduces the parameters. This method considers the factors of both teacher and student performance within the training stage and dynamically assigns the distillation weight instead of applying a fixed weight on the student model. Extensive experiments are conducted on five public datasets to demonstrate that our method can achieve competitive performance compared to 10 prior methods through a 78.2MB lightweight structure.

Tensor feature hallucination for few-shot learning

Few-shot classification addresses the challenge of classifying examples given not just limited supervision but limited data as well. An attractive solution is synthetic data generation. However, most such methods are overly sophisticated, focusing on high-quality, realistic data in the input space. It is unclear whether adapting them to the few-shot regime and using them for the downstream task of classification is the right approach. Previous works on synthetic data generation for few-shot classification focus on exploiting complex models, e.g. a Wasserstein GAN with multiple regularizers or a network that transfers latent diversities from known to novel classes. We follow a different approach and investigate how a simple and straightforward synthetic data generation method can be used effectively. We make two contributions, namely we show that: (1) using a simple loss function is more than enough for training a feature generator in the few-shot setting; and (2) learning to generate tensor features instead of vector features is superior. Extensive experiments on miniImagenet, CUB and CIFAR-FS datasets show that our method sets a new state of the art, outperforming more sophisticated few-shot data augmentation methods.

Progressive Multi-scale Fusion Network for RGB-D Salient Object Detection

Salient object detection(SOD) aims at locating the most significant object within a given image. In recent years, great progress has been made in applying SOD on many vision tasks. The depth map could provide additional spatial prior and boundary cues to boost the performance. Combining the depth information with image data obtained from standard visual cameras has been widely used in recent SOD works, however, introducing depth information in a suboptimal fusion strategy may have negative influence in the performance of SOD. In this paper, we discuss about the advantages of the so-called progressive multi-scale fusion method and propose a mask-guided feature aggregation module(MGFA). The proposed framework can effectively combine the two features of different modalities and, furthermore, alleviate the impact of erroneous depth features, which are inevitably caused by the variation of depth quality. We further introduce a mask-guided refinement module(MGRM) to complement the high-level semantic features and reduce the irrelevant features from multi-scale fusion, leading to an overall refinement of detection. Experiments on five challenging benchmarks demonstrate that the proposed method outperforms 11 state-of-the-art methods under different evaluation metrics.