The human face contains important and understandable information such as personal identity, gender, age, and ethnicity. In recent years, a person's age has been studied as one of the important features of the face. The age estimation system consists of a combination of two modules, the presentation of the face image and the extraction of age characteristics, and then the detection of the exact age or age group based on these characteristics. So far, various algorithms have been presented for age estimation, each of which has advantages and disadvantages. In this work, we implemented a deep residual neural network on the UTKFace data set. We validated our implementation by comparing it with the state-of-the-art implementations of different age estimation algorithms and the results show 28.3% improvement in MAE as one of the critical error validation metrics compared to the recent works and also 71.39% MAE improvements compared to the implemented AlexNet. In the end, we show that the performance degradation of our implemented network is lower than 1.5% when injecting 15 dB noise to the input data (5 times more than the normal environmental noise) which justifies the noise tolerance of our proposed method.
In 2023, the International Conference on Machine Learning (ICML) required authors with multiple submissions to rank their submissions based on perceived quality. In this paper, we aim to employ these author-specified rankings to enhance peer review in machine learning and artificial intelligence conferences by extending the Isotonic Mechanism (Su, 2021, 2022) to exponential family distributions. This mechanism generates adjusted scores closely align with the original scores while adhering to author-specified rankings. Despite its applicability to a broad spectrum of exponential family distributions, this mechanism's implementation does not necessitate knowledge of the specific distribution form. We demonstrate that an author is incentivized to provide accurate rankings when her utility takes the form of a convex additive function of the adjusted review scores. For a certain subclass of exponential family distributions, we prove that the author reports truthfully only if the question involves only pairwise comparisons between her submissions, thus indicating the optimality of ranking in truthful information elicitation. Lastly, we show that the adjusted scores improve dramatically the accuracy of the original scores and achieve nearly minimax optimality for estimating the true scores with statistical consistecy when true scores have bounded total variation.
Self-supervised methods such as Contrastive predictive Coding (CPC) have greatly improved the quality of the unsupervised representations. These representations significantly reduce the amount of labeled data needed for downstream task performance, such as automatic speech recognition. CPC learns representations by learning to predict future frames given current frames. Based on the observation that the acoustic information, e.g., phones, changes slower than the feature extraction rate in CPC, we propose regularization techniques that impose slowness constraints on the features. Here we propose two regularization techniques: Self-expressing constraint and Left-or-Right regularization. We evaluate the proposed model on ABX and linear phone classification tasks, acoustic unit discovery, and automatic speech recognition. The regularized CPC trained on 100 hours of unlabeled data matches the performance of the baseline CPC trained on 360 hours of unlabeled data. We also show that our regularization techniques are complementary to data augmentation and can further boost the system's performance. In monolingual, cross-lingual, or multilingual settings, with/without data augmentation, regardless of the amount of data used for training, our regularized models outperformed the baseline CPC models on the ABX task.
The architecture of a deep neural network is defined explicitly in terms of the number of layers, the width of each layer and the general network topology. Existing optimisation frameworks neglect this information in favour of implicit architectural information (e.g. second-order methods) or architecture-agnostic distance functions (e.g. mirror descent). Meanwhile, the most popular optimiser in practice, Adam, is based on heuristics. This paper builds a new framework for deriving optimisation algorithms that explicitly leverage neural architecture. The theory extends mirror descent to non-convex composite objective functions: the idea is to transform a Bregman divergence to account for the non-linear structure of neural architecture. Working through the details for deep fully-connected networks yields automatic gradient descent: a first-order optimiser without any hyperparameters. Automatic gradient descent trains both fully-connected and convolutional networks out-of-the-box and at ImageNet scale. A PyTorch implementation is available at https://github.com/jxbz/agd and also in Appendix B. Overall, the paper supplies a rigorous theoretical foundation for a next-generation of architecture-dependent optimisers that work automatically and without hyperparameters.
We present MONET, a new multimodal dataset captured using a thermal camera mounted on a drone that flew over rural areas, and recorded human and vehicle activities. We captured MONET to study the problem of object localisation and behaviour understanding of targets undergoing large-scale variations and being recorded from different and moving viewpoints. Target activities occur in two different land sites, each with unique scene structures and cluttered backgrounds. MONET consists of approximately 53K images featuring 162K manually annotated bounding boxes. Each image is timestamp-aligned with drone metadata that includes information about attitudes, speed, altitude, and GPS coordinates. MONET is different from previous thermal drone datasets because it features multimodal data, including rural scenes captured with thermal cameras containing both person and vehicle targets, along with trajectory information and metadata. We assessed the difficulty of the dataset in terms of transfer learning between the two sites and evaluated nine object detection algorithms to identify the open challenges associated with this type of data. Project page: https://github.com/fabiopoiesi/monet_dataset.
State-of-the-art methods on conversational recommender systems (CRS) leverage external knowledge to enhance both items' and contextual words' representations to achieve high quality recommendations and responses generation. However, the representations of the items and words are usually modeled in two separated semantic spaces, which leads to misalignment issue between them. Consequently, this will cause the CRS to only achieve a sub-optimal ranking performance, especially when there is a lack of sufficient information from the user's input. To address limitations of previous works, we propose a new CRS framework KLEVER, which jointly models items and their associated contextual words in the same semantic space. Particularly, we construct an item descriptive graph from the rich items' textual features, such as item description and categories. Based on the constructed descriptive graph, KLEVER jointly learns the embeddings of the words and items, towards enhancing both recommender and dialog generation modules. Extensive experiments on benchmarking CRS dataset demonstrate that KLEVER achieves superior performance, especially when the information from the users' responses is lacking.
Contrastive learning has shown promising potential for learning robust representations by utilizing unlabeled data. However, constructing effective positive-negative pairs for contrastive learning on facial behavior datasets remains challenging. This is because such pairs inevitably encode the subject-ID information, and the randomly constructed pairs may push similar facial images away due to the limited number of subjects in facial behavior datasets. To address this issue, we propose to utilize activity descriptions, coarse-grained information provided in some datasets, which can provide high-level semantic information about the image sequences but is often neglected in previous studies. More specifically, we introduce a two-stage Contrastive Learning with Text-Embeded framework for Facial behavior understanding (CLEF). The first stage is a weakly-supervised contrastive learning method that learns representations from positive-negative pairs constructed using coarse-grained activity information. The second stage aims to train the recognition of facial expressions or facial action units by maximizing the similarity between image and the corresponding text label names. The proposed CLEF achieves state-of-the-art performance on three in-the-lab datasets for AU recognition and three in-the-wild datasets for facial expression recognition.
Multi-modal fusion is a basic task of autonomous driving system perception, which has attracted many scholars' interest in recent years. The current multi-modal fusion methods mainly focus on camera data and LiDAR data, but pay little attention to the kinematic information provided by the bottom sensors of the vehicle, such as acceleration, vehicle speed, angle of rotation. These information are not affected by complex external scenes, so it is more robust and reliable. In this paper, we introduce the existing application fields of vehicle bottom information and the research progress of related methods, as well as the multi-modal fusion methods based on bottom information. We also introduced the relevant information of the vehicle bottom information data set in detail to facilitate the research as soon as possible. In addition, new future ideas of multi-modal fusion technology for autonomous driving tasks are proposed to promote the further utilization of vehicle bottom information.
The development of knowledge graph (KG) applications has led to a rising need for entity alignment (EA) between heterogeneous KGs that are extracted from various sources. Recently, graph neural networks (GNNs) have been widely adopted in EA tasks due to GNNs' impressive ability to capture structure information. However, we have observed that the oversimplified settings of the existing common EA datasets are distant from real-world scenarios, which obstructs a full understanding of the advancements achieved by recent methods. This phenomenon makes us ponder: Do existing GNN-based EA methods really make great progress? In this paper, to study the performance of EA methods in realistic settings, we focus on the alignment of highly heterogeneous KGs (HHKGs) (e.g., event KGs and general KGs) which are different with regard to the scale and structure, and share fewer overlapping entities. First, we sweep the unreasonable settings, and propose two new HHKG datasets that closely mimic real-world EA scenarios. Then, based on the proposed datasets, we conduct extensive experiments to evaluate previous representative EA methods, and reveal interesting findings about the progress of GNN-based EA methods. We find that the structural information becomes difficult to exploit but still valuable in aligning HHKGs. This phenomenon leads to inferior performance of existing EA methods, especially GNN-based methods. Our findings shed light on the potential problems resulting from an impulsive application of GNN-based methods as a panacea for all EA datasets. Finally, we introduce a simple but effective method: Simple-HHEA, which comprehensively utilizes entity name, structure, and temporal information. Experiment results show Simple-HHEA outperforms previous models on HHKG datasets.
Learning effective joint embedding for cross-modal data has always been a focus in the field of multimodal machine learning. We argue that during multimodal fusion, the generated multimodal embedding may be redundant, and the discriminative unimodal information may be ignored, which often interferes with accurate prediction and leads to a higher risk of overfitting. Moreover, unimodal representations also contain noisy information that negatively influences the learning of cross-modal dynamics. To this end, we introduce the multimodal information bottleneck (MIB), aiming to learn a powerful and sufficient multimodal representation that is free of redundancy and to filter out noisy information in unimodal representations. Specifically, inheriting from the general information bottleneck (IB), MIB aims to learn the minimal sufficient representation for a given task by maximizing the mutual information between the representation and the target and simultaneously constraining the mutual information between the representation and the input data. Different from general IB, our MIB regularizes both the multimodal and unimodal representations, which is a comprehensive and flexible framework that is compatible with any fusion methods. We develop three MIB variants, namely, early-fusion MIB, late-fusion MIB, and complete MIB, to focus on different perspectives of information constraints. Experimental results suggest that the proposed method reaches state-of-the-art performance on the tasks of multimodal sentiment analysis and multimodal emotion recognition across three widely used datasets. The codes are available at \url{https://github.com/TmacMai/Multimodal-Information-Bottleneck}.