The assessment of breast density is crucial in the context of breast cancer screening, especially in populations with a higher percentage of dense breast tissues. This study introduces a novel data augmentation technique termed Attention-Guided Erasing (AGE), devised to enhance the downstream classification of four distinct breast density categories in mammography following the BI-RADS recommendation in the Vietnamese cohort. The proposed method integrates supplementary information during transfer learning, utilizing visual attention maps derived from a vision transformer backbone trained using the self-supervised DINO method. These maps are utilized to erase background regions in the mammogram images, unveiling only the potential areas of dense breast tissues to the network. Through the incorporation of AGE during transfer learning with varying random probabilities, we consistently surpass classification performance compared to scenarios without AGE and the traditional random erasing transformation. We validate our methodology using the publicly available VinDr-Mammo dataset. Specifically, we attain a mean F1-score of 0.5910, outperforming values of 0.5594 and 0.5691 corresponding to scenarios without AGE and with random erasing (RE), respectively. This superiority is further substantiated by t-tests, revealing a p-value of p<0.0001, underscoring the statistical significance of our approach.
Recently it has been shown that tensor networks (TNs) have the ability to represent the expected return of a single-agent finite Markov decision process (FMDP). The TN represents a distribution model, where all possible trajectories are considered. When extending these ideas to a multi-agent setting, distribution models suffer from the curse of dimensionality: the exponential relation between the number of possible trajectories and the number of agents. The key advantage of using TNs in this setting is that there exists a large number of established optimisation and decomposition techniques that are specific to TNs, that one can apply to ensure the most efficient representation is found. In this report, these methods are used to form a TN that represents the expected return of a multi-agent reinforcement learning (MARL) task. This model is then applied to a 2 agent random walker example, where it was shown that the policy is correctly optimised using a DMRG technique. Finally, I demonstrate the use of an exact decomposition technique, reducing the number of elements in the tensors by 97.5%, without experiencing any loss of information.
Striking a balance between precision and efficiency presents a prominent challenge in the bird's-eye-view (BEV) 3D object detection. Although previous camera-based BEV methods achieved remarkable performance by incorporating long-term temporal information, most of them still face the problem of low efficiency. One potential solution is knowledge distillation. Existing distillation methods only focus on reconstructing spatial features, while overlooking temporal knowledge. To this end, we propose TempDistiller, a Temporal knowledge Distiller, to acquire long-term memory from a teacher detector when provided with a limited number of frames. Specifically, a reconstruction target is formulated by integrating long-term temporal knowledge through self-attention operation applied to feature teachers. Subsequently, novel features are generated for masked student features via a generator. Ultimately, we utilize this reconstruction target to reconstruct the student features. In addition, we also explore temporal relational knowledge when inputting full frames for the student model. We verify the effectiveness of the proposed method on the nuScenes benchmark. The experimental results show our method obtain an enhancement of +1.6 mAP and +1.1 NDS compared to the baseline, a speed improvement of approximately 6 FPS after compressing temporal knowledge, and the most accurate velocity estimation.
This paper presents a video coding scheme that combines traditional optimization methods with deep learning methods based on the Enhanced Compression Model (ECM). In this paper, the traditional optimization methods adaptively adjust the quantization parameter (QP). The key frame QP offset is set according to the video content characteristics, and the coding tree unit (CTU) level QP of all frames is also adjusted according to the spatial-temporal perception information. Block importance mapping technology (BIM) is also introduced, which adjusts the QP according to the block importance. Meanwhile, the deep learning methods propose a convolutional neural network-based loop filter (CNNLF), which is turned on/off based on the rate-distortion optimization at the CTU and frame level. Besides, intra-prediction using neural networks (NN-intra) is proposed to further improve compression quality, where 8 neural networks are used for predicting blocks of different sizes. The experimental results show that compared with ECM-3.0, the proposed traditional methods and adding deep learning methods improve the PSNR by 0.54 dB and 1 dB at 0.05Mbps, respectively; 0.38 dB and 0.71dB at 0.5 Mbps, respectively, which proves the superiority of our method.
Knowledge-grounded dialogue (KGD) learns to generate an informative response based on a given dialogue context and external knowledge (\emph{e.g.}, knowledge graphs; KGs). Recently, the emergence of large language models (LLMs) and pre-training techniques has brought great success to knowledge-grounded dialogue. However, when building KGD systems in real applications, there are various real-world noises that are inevitable to face. For example, the dialogue context might involve perturbations such as misspellings and abbreviations. In addition, KGs typically suffer from incompletion and also might contain erroneous and outdated facts. Such real-world noises pose a challenge to the robustness of KGD systems and hinder their applications in the real world. In this paper, we propose an entity-based contrastive learning framework for improving the robustness of KGD. Specifically, we make use of the entity information in a KGD sample to create both its positive and negative samples which involve semantic-irrelevant and semantic-relevant perturbations, respectively. The contrastive learning framework ensures the KGD model is aware of these two types of perturbations, thus generating informative responses with the potentially noisy inputs in real applications. Experimental results on three benchmark datasets show that our method achieves new state-of-the-art performance in terms of automatic evaluation scores, verifying its effectiveness and potentiality. Furthermore, we show that our method can generate better responses than comparison models in both the noisy and the few-shot settings.
Large Language Models (LLMs) have shown extraordinary capabilities in understanding and generating text that closely mirrors human communication. However, a primary limitation lies in the significant computational demands during training, arising from their extensive parameterization. This challenge is further intensified by the dynamic nature of the world, necessitating frequent updates to LLMs to correct outdated information or integrate new knowledge, thereby ensuring their continued relevance. Note that many applications demand continual model adjustments post-training to address deficiencies or undesirable behaviors. There is an increasing interest in efficient, lightweight methods for on-the-fly model modifications. To this end, recent years have seen a burgeoning in the techniques of knowledge editing for LLMs, which aim to efficiently modify LLMs' behaviors within specific domains while preserving overall performance across various inputs. In this paper, we first define the knowledge editing problem and then provide a comprehensive review of cutting-edge approaches. Drawing inspiration from educational and cognitive research theories, we propose a unified categorization criterion that classifies knowledge editing methods into three groups: resorting to external knowledge, merging knowledge into the model, and editing intrinsic knowledge. Furthermore, we introduce a new benchmark, KnowEdit, for a comprehensive empirical evaluation of representative knowledge editing approaches. Additionally, we provide an in-depth analysis of knowledge location, which can give a deeper understanding of the knowledge structures inherent within LLMs. Finally, we discuss several potential applications of knowledge editing, outlining its broad and impactful implications.
This work investigates how hierarchically structured data can help neural networks learn conceptual representations of cathedrals. The underlying WikiScenes dataset provides a spatially organized hierarchical structure of cathedral components. We propose a novel hierarchical contrastive training approach that leverages a triplet margin loss to represent the data's spatial hierarchy in the encoder's latent space. As such, the proposed approach investigates if the dataset structure provides valuable information for self-supervised learning. We apply t-SNE to visualize the resultant latent space and evaluate the proposed approach by comparing it with other dataset-specific contrastive learning methods using a common downstream classification task. The proposed method outperforms the comparable weakly-supervised and baseline methods. Our findings suggest that dataset structure is a valuable modality for weakly-supervised learning.
Accurate air quality forecasting is crucial for public health, environmental monitoring and protection, and urban planning. However, existing methods fail to effectively utilize multi-scale information, both spatially and temporally. Spatially, there is a lack of integration between individual monitoring stations and city-wide scales. Temporally, the periodic nature of air quality variations is often overlooked or inadequately considered. To address these limitations, we present a novel Multi-spatial Multi-temporal air quality forecasting method based on Graph Convolutional Networks and Gated Recurrent Units (M2G2), bridging the gap in air quality forecasting across spatial and temporal scales. The proposed framework consists of two modules: Multi-scale Spatial GCN (MS-GCN) for spatial information fusion and Multi-scale Temporal GRU(MT-GRU) for temporal information integration. In the spatial dimension, the MS-GCN module employs a bidirectional learnable structure and a residual structure, enabling comprehensive information exchange between individual monitoring stations and the city-scale graph. Regarding the temporal dimension, the MT-GRU module adaptively combines information from different temporal scales through parallel hidden states. Leveraging meteorological indicators and four air quality indicators, we present comprehensive comparative analyses and ablation experiments, showcasing the higher accuracy of M2G2 in comparison to nine currently available advanced approaches across all aspects. The improvements of M2G2 over the second-best method on RMSE of the 24h/48h/72h are as follows: PM2.5: (7.72%, 6.67%, 10.45%); PM10: (6.43%, 5.68%, 7.73%); NO2: (5.07%, 7.76%, 16.60%); O3: (6.46%, 6.86%, 9.79%). Furthermore, we demonstrate the effectiveness of each module of M2G2 by ablation study.
The importance of the information in the direct sound to human perception of spatial sound sources is an ongoing research topic. The classification between direct sound and diffuse or reverberant sound forms the basis of numerous studies in the field of spatial audio. In particular, parametric spatial audio representation methods use this classification and employ signal processing in order to enhance the audio quality at reproduction. However, current literature does not provide information concerning the impact of ideal direct sound representation on externalization, in the context of Ambisonics. This paper aims to assess the importance of the spatial information in the direct sound in the externalization of a sound field when using binaural reproduction. This is done in the spherical harmonics (SH) domain, where an ideal direct sound representation within an otherwise Ambisonics signal is simulated, and its perceived externalization is evaluated in a formal listening test. This investigation leads to the conclusion that externalization of a first order Ambisonics signal may be significantly improved by enhancing the direct sound component, up to a level similar to a third order Ambisonics signal.
Pan-sharpening involves reconstructing missing high-frequency information in multi-spectral images with low spatial resolution, using a higher-resolution panchromatic image as guidance. Although the inborn connection with frequency domain, existing pan-sharpening research has not almost investigated the potential solution upon frequency domain. To this end, we propose a novel Frequency Adaptive Mixture of Experts (FAME) learning framework for pan-sharpening, which consists of three key components: the Adaptive Frequency Separation Prediction Module, the Sub-Frequency Learning Expert Module, and the Expert Mixture Module. In detail, the first leverages the discrete cosine transform to perform frequency separation by predicting the frequency mask. On the basis of generated mask, the second with low-frequency MOE and high-frequency MOE takes account for enabling the effective low-frequency and high-frequency information reconstruction. Followed by, the final fusion module dynamically weights high-frequency and low-frequency MOE knowledge to adapt to remote sensing images with significant content variations. Quantitative and qualitative experiments over multiple datasets demonstrate that our method performs the best against other state-of-the-art ones and comprises a strong generalization ability for real-world scenes. Code will be made publicly at \url{https://github.com/alexhe101/FAME-Net}.