Few-shot object detection (FSOD) aims at extending a generic detector for novel object detection with only a few training examples. It attracts great concerns recently due to the practical meanings. Meta-learning has been demonstrated to be an effective paradigm for this task. In general, methods based on meta-learning employ an additional support branch to encode novel examples (a.k.a. support images) into class prototypes, which are then fused with query branch to facilitate the model prediction. However, the class-level prototypes are difficult to precisely generate, and they also lack detailed information, leading to instability in performance.New methods are required to capture the distinctive local context for more robust novel object detection. To this end, we propose to distill the most representative support features into fine-grained prototypes. These prototypes are then assigned into query feature maps based on the matching results, modeling the detailed feature relations between two branches. This process is realized by our Fine-Grained Feature Aggregation (FFA) module. Moreover, in terms of high-level feature fusion, we propose Balanced Class-Agnostic Sampling (B-CAS) strategy and Non-Linear Fusion (NLF) module from differenct perspectives. They are complementary to each other and depict the high-level feature relations more effectively. Extensive experiments on PASCAL VOC and MS COCO benchmarks show that our method sets a new state-of-the-art performance in most settings. Our code is available at https://github.com/wangchen1801/FPD.
Deep learning now enables automatic and robust extraction of cardiac function descriptors from echocardiographic sequences, such as ejection fraction or strain. These descriptors provide fine-grained information that physicians consider, in conjunction with more global variables from the clinical record, to assess patients' condition. Drawing on novel transformer models applied to tabular data (e.g., variables from electronic health records), we propose a method that considers all descriptors extracted from medical records and echocardiograms to learn the representation of a difficult-to-characterize cardiovascular pathology, namely hypertension. Our method first projects each variable into its own representation space using modality-specific approaches. These standardized representations of multimodal data are then fed to a transformer encoder, which learns to merge them into a comprehensive representation of the patient through a pretext task of predicting a clinical rating. This pretext task is formulated as an ordinal classification to enforce a pathological continuum in the representation space. We observe the major trends along this continuum for a cohort of 239 hypertensive patients to describe, with unprecedented gradation, the effect of hypertension on a number of cardiac function descriptors. Our analysis shows that i) pretrained weights from a foundation model allow to reach good performance (83% accuracy) even with limited data (less than 200 training samples), ii) trends across the population are reproducible between trainings, and iii) for descriptors whose interactions with hypertension are well documented, patterns are consistent with prior physiological knowledge.
Recognizing and learning from similar crisis situations is crucial for the development of effective response strategies. This study addresses the challenge of identifying similarities within a wide range of crisis-related information. To overcome this challenge, we employed an ontology-based crisis situation knowledge base enriched with crisis-related information. Additionally, we implemented a semantic similarity measure to assess the degree of similarity between crisis situations. Our investigation specifically focuses on recognizing similar crises through the application of ontology-based knowledge mining. Through our experiments, we demonstrate the accuracy and efficiency of our approach to recognizing similar crises. These findings highlight the potential of ontology-based knowledge mining for enhancing crisis recognition processes and improving overall crisis management strategies.
The fairness of Natural Language Processing (NLP) models has emerged as a crucial concern. Information theory indicates that to achieve fairness, a model should not be able to predict sensitive variables, such as gender, ethnicity, and age. However, information related to these variables often appears implicitly in language, posing a challenge in identifying and mitigating biases effectively. To tackle this issue, we present a novel approach that operates at the embedding level of an NLP model, independent of the specific architecture. Our method leverages insights from recent advances in XAI techniques and employs an embedding transformation to eliminate implicit information from a selected variable. By directly manipulating the embeddings in the final layer, our approach enables a seamless integration into existing models without requiring significant modifications or retraining. In evaluation, we show that the proposed post-hoc approach significantly reduces gender-related associations in NLP models while preserving the overall performance and functionality of the models. An implementation of our method is available: https://github.com/fanny-jourdan/TaCo
Group activity recognition in video is a complex task due to the need for a model to recognise the actions of all individuals in the video and their complex interactions. Recent studies propose that optimal performance is achieved by individually tracking each person and subsequently inputting the sequence of poses or cropped images/optical flow into a model. This helps the model to recognise what actions each person is performing before they are merged to arrive at the group action class. However, all previous models are highly reliant on high quality tracking and have only been evaluated using ground truth tracking information. In practice it is almost impossible to achieve highly reliable tracking information for all individuals in a group activity video. We introduce an innovative deep learning-based group activity recognition approach called Rendered Pose based Group Activity Recognition System (RePGARS) which is designed to be tolerant of unreliable tracking and pose information. Experimental results confirm that RePGARS outperforms all existing group activity recognition algorithms tested which do not use ground truth detection and tracking information.
Deep graph convolution networks (GCNs) have recently shown excellent performance in traffic prediction tasks. However, they face some challenges. First, few existing models consider the influence of auxiliary information, i.e., weather and holidays, which may result in a poor grasp of spatial-temporal dynamics of traffic data. Second, both the construction of a dynamic adjacent matrix and regular graph convolution operations have quadratic computation complexity, which restricts the scalability of GCN-based models. To address such challenges, this work proposes a deep encoder-decoder model entitled AIMSAN. It contains an auxiliary information-aware module (AIM) and sparse cross attention-based graph convolution network (SAN). The former learns multi-attribute auxiliary information and obtains its embedded presentation of different time-window sizes. The latter uses a cross-attention mechanism to construct dynamic adjacent matrices by fusing traffic data and embedded auxiliary data. Then, SAN applies diffusion GCN on traffic data to mine rich spatial-temporal dynamics. Furthermore, AIMSAN considers and uses the spatial sparseness of traffic nodes to reduce the quadratic computation complexity. Experimental results on three public traffic datasets demonstrate that the proposed method outperforms other counterparts in terms of various performance indices. Specifically, the proposed method has competitive performance with the state-of-the-art algorithms but saves 35.74% of GPU memory usage, 42.25% of training time, and 45.51% of validation time on average.
While Language Models have become workhorses for NLP, their interplay with textual knowledge graphs (KGs) - structured memories of general or domain knowledge - is actively researched. Current embedding methodologies for such graphs typically either (i) linearize graphs for embedding them using sequential Language Models (LMs), which underutilize structural information, or (ii) use Graph Neural Networks (GNNs) to preserve graph structure, while GNNs cannot represent textual features as well as a pre-trained LM could. In this work we introduce a novel language model, the Graph Language Model (GLM), that integrates the strengths of both approaches, while mitigating their weaknesses. The GLM parameters are initialized from a pretrained LM, to facilitate nuanced understanding of individual concepts and triplets. Simultaneously, its architectural design incorporates graph biases, thereby promoting effective knowledge distribution within the graph. Empirical evaluations on relation classification tasks on ConceptNet subgraphs reveal that GLM embeddings surpass both LM- and GNN-based baselines in supervised and zero-shot settings.
Ensemble modeling has been widely used to solve complex problems as it helps to improve overall performance and generalization. In this paper, we propose a novel TemporalAugmenter approach based on ensemble modeling for augmenting the temporal information capturing for long-term and short-term dependencies in data integration of two variations of recurrent neural networks in two learning streams to obtain the maximum possible temporal extraction. Thus, the proposed model augments the extraction of temporal dependencies. In addition, the proposed approach reduces the preprocessing and prior stages of feature extraction, which reduces the required energy to process the models built upon the proposed TemporalAugmenter approach, contributing towards green AI. Moreover, the proposed model can be simply integrated into various domains including industrial, medical, and human-computer interaction applications. Our proposed approach empirically evaluated the speech emotion recognition, electrocardiogram signal, and signal quality examination tasks as three different signals with varying complexity and different temporal dependency features.
Image compression has been applied in the fields of image storage and video broadcasting. However, it's formidably tough to distinguish the subtle quality differences between those distorted images generated by different algorithms. In this paper, we propose a new image quality assessment framework to decide which image is better in an image group. To capture the subtle differences, a fine-grained network is adopted to acquire multi-scale features. Subsequently, we design a cross subtract block for separating and gathering the information within positive and negative image pairs. Enabling image comparison in feature space. After that, a progressive feature fusion block is designed, which fuses multi-scale features in a novel progressive way. Hierarchical spatial 2D features can thus be processed gradually. Experimental results show that compared with the current mainstream image quality assessment methods, the proposed network can achieve more accurate image quality assessment and ranks second in the benchmark of CLIC in the image perceptual model track.
Image splice manipulation presents a severe challenge in today's society. With easy access to image manipulation tools, it is easier than ever to modify images that can mislead individuals, organizations or society. In this work, a novel, "Visually Attentive Splice Localization Network with Multi-Domain Feature Extractor and Multi-Receptive Field Upsampler" has been proposed. It contains a unique "visually attentive multi-domain feature extractor" (VA-MDFE) that extracts attentional features from the RGB, edge and depth domains. Next, a "visually attentive downsampler" (VA-DS) is responsible for fusing and downsampling the multi-domain features. Finally, a novel "visually attentive multi-receptive field upsampler" (VA-MRFU) module employs multiple receptive field-based convolutions to upsample attentional features by focussing on different information scales. Experimental results conducted on the public benchmark dataset CASIA v2.0 prove the potency of the proposed model. It comfortably beats the existing state-of-the-arts by achieving an IoU score of 0.851, pixel F1 score of 0.9195 and pixel AUC score of 0.8989.