RealCustom++: Representing Images as Real-Word for Real-Time Customization

Text-to-image customization, which takes given texts and images depicting given subjects as inputs, aims to synthesize new images that align with both text semantics and subject appearance. This task provides precise control over details that text alone cannot capture and is fundamental for various real-world applications, garnering significant interest from academia and industry. Existing works follow the pseudo-word paradigm, which involves representing given subjects as pseudo-words and combining them with given texts to collectively guide the generation. However, the inherent conflict and entanglement between the pseudo-words and texts result in a dual-optimum paradox, where subject similarity and text controllability cannot be optimal simultaneously. We propose a novel real-words paradigm termed RealCustom++ that instead represents subjects as non-conflict real words, thereby disentangling subject similarity from text controllability and allowing both to be optimized simultaneously. Specifically, RealCustom++ introduces a novel "train-inference" decoupled framework: (1) During training, RealCustom++ learns the alignment between vision conditions and all real words in the text, ensuring high subject-similarity generation in open domains. This is achieved by the cross-layer cross-scale projector to robustly and finely extract subject features, and a curriculum training recipe that adapts the generated subject to diverse poses and sizes. (2) During inference, leveraging the learned general alignment, an adaptive mask guidance is proposed to only customize the generation of the specific target real word, keeping other subject-irrelevant regions uncontaminated to ensure high text-controllability in real-time.

MSSTNet: A Multi-Scale Spatio-Temporal CNN-Transformer Network for Dynamic Facial Expression Recognition

Unlike typical video action recognition, Dynamic Facial Expression Recognition (DFER) does not involve distinct moving targets but relies on localized changes in facial muscles. Addressing this distinctive attribute, we propose a Multi-Scale Spatio-temporal CNN-Transformer network (MSSTNet). Our approach takes spatial features of different scales extracted by CNN and feeds them into a Multi-scale Embedding Layer (MELayer). The MELayer extracts multi-scale spatial information and encodes these features before sending them into a Temporal Transformer (T-Former). The T-Former simultaneously extracts temporal information while continually integrating multi-scale spatial information. This process culminates in the generation of multi-scale spatio-temporal features that are utilized for the final classification. Our method achieves state-of-the-art results on two in-the-wild datasets. Furthermore, a series of ablation experiments and visualizations provide further validation of our approach's proficiency in leveraging spatio-temporal information within DFER.

DreamTuner: Single Image is Enough for Subject-Driven Generation

Diffusion-based models have demonstrated impressive capabilities for text-to-image generation and are expected for personalized applications of subject-driven generation, which require the generation of customized concepts with one or a few reference images. However, existing methods based on fine-tuning fail to balance the trade-off between subject learning and the maintenance of the generation capabilities of pretrained models. Moreover, other methods that utilize additional image encoders tend to lose important details of the subject due to encoding compression. To address these challenges, we propose DreamTurner, a novel method that injects reference information from coarse to fine to achieve subject-driven image generation more effectively. DreamTurner introduces a subject-encoder for coarse subject identity preservation, where the compressed general subject features are introduced through an attention layer before visual-text cross-attention. We then modify the self-attention layers within pretrained text-to-image models to self-subject-attention layers to refine the details of the target subject. The generated image queries detailed features from both the reference image and itself in self-subject-attention. It is worth emphasizing that self-subject-attention is an effective, elegant, and training-free method for maintaining the detailed features of customized subjects and can serve as a plug-and-play solution during inference. Finally, with additional subject-driven fine-tuning, DreamTurner achieves remarkable performance in subject-driven image generation, which can be controlled by a text or other conditions such as pose. For further details, please visit the project page at https://dreamtuner-diffusion.github.io/.

CLC: Cluster Assignment via Contrastive Representation Learning

Clustering remains an important and challenging task of grouping samples into clusters without manual annotations. Recent works have achieved excellent results on small datasets by performing clustering on feature representations learned from self-supervised learning. However, for datasets with a large number of clusters, such as ImageNet, current methods still can not achieve high clustering performance. In this paper, we propose Contrastive Learning-based Clustering (CLC), which uses contrastive learning to directly learn cluster assignment. We decompose the representation into two parts: one encodes the categorical information under an equipartition constraint, and the other captures the instance-wise factors. We propose a contrastive loss using both parts of the representation. We theoretically analyze the proposed contrastive loss and reveal that CLC sets different weights for the negative samples while learning cluster assignments. Further gradient analysis shows that the larger weights tend to focus more on the hard negative samples. Therefore, the proposed loss has high expressiveness that enables us to efficiently learn cluster assignments. Experimental evaluation shows that CLC achieves overall state-of-the-art or highly competitive clustering performance on multiple benchmark datasets. In particular, we achieve 53.4% accuracy on the full ImageNet dataset and outperform existing methods by large margins (+ 10.2%).

A Voice Disease Detection Method Based on MFCCs and Shallow CNN

The incidence rate of voice diseases is increasing year by year. The use of software for remote diagnosis is a technical development trend and has important practical value. Among voice diseases, common diseases that cause hoarseness include spasmodic dysphonia, vocal cord paralysis, vocal nodule, and vocal cord polyp. This paper presents a voice disease detection method that can be applied in a wide range of clinical. We cooperated with Xiangya Hospital of Central South University to collect voice samples from sixty-one different patients. The Mel Frequency Cepstrum Coefficient (MFCC) parameters are extracted as input features to describe the voice in the form of data. An innovative model combining MFCC parameters and single convolution layer CNN is proposed for fast calculation and classification. The highest accuracy we achieved was 92%, it is fully ahead of the original research results and internationally advanced. And we use Advanced Voice Function Assessment Databases (AVFAD) to evaluate the generalization ability of the method we proposed, which achieved an accuracy rate of 98%. Experiments on clinical and standard datasets show that for the pathological detection of voice diseases, our method has greatly improved in accuracy and computational efficiency.

Multi-level Distillation of Semantic Knowledge for Pre-training Multilingual Language Model

Pre-trained multilingual language models play an important role in cross-lingual natural language understanding tasks. However, existing methods did not focus on learning the semantic structure of representation, and thus could not optimize their performance. In this paper, we propose Multi-level Multilingual Knowledge Distillation (MMKD), a novel method for improving multilingual language models. Specifically, we employ a teacher-student framework to adopt rich semantic representation knowledge in English BERT. We propose token-, word-, sentence-, and structure-level alignment objectives to encourage multiple levels of consistency between source-target pairs and correlation similarity between teacher and student models. We conduct experiments on cross-lingual evaluation benchmarks including XNLI, PAWS-X, and XQuAD. Experimental results show that MMKD outperforms other baseline models of similar size on XNLI and XQuAD and obtains comparable performance on PAWS-X. Especially, MMKD obtains significant performance gains on low-resource languages.

Decoupled IoU Regression for Object Detection

Non-maximum suppression (NMS) is widely used in object detection pipelines for removing duplicated bounding boxes. The inconsistency between the confidence for NMS and the real localization confidence seriously affects detection performance. Prior works propose to predict Intersection-over-Union (IoU) between bounding boxes and corresponding ground-truths to improve NMS, while accurately predicting IoU is still a challenging problem. We argue that the complex definition of IoU and feature misalignment make it difficult to predict IoU accurately. In this paper, we propose a novel Decoupled IoU Regression (DIR) model to handle these problems. The proposed DIR decouples the traditional localization confidence metric IoU into two new metrics, Purity and Integrity. Purity reflects the proportion of the object area in the detected bounding box, and Integrity refers to the completeness of the detected object area. Separately predicting Purity and Integrity can divide the complex mapping between the bounding box and its IoU into two clearer mappings and model them independently. In addition, a simple but effective feature realignment approach is also introduced to make the IoU regressor work in a hindsight manner, which can make the target mapping more stable. The proposed DIR can be conveniently integrated with existing two-stage detectors and significantly improve their performance. Through a simple implementation of DIR with HTC, we obtain 51.3% AP on MS COCO benchmark, which outperforms previous methods and achieves state-of-the-art.

Multi-shot Temporal Event Localization: a Benchmark

Current developments in temporal event or action localization usually target actions captured by a single camera. However, extensive events or actions in the wild may be captured as a sequence of shots by multiple cameras at different positions. In this paper, we propose a new and challenging task called multi-shot temporal event localization, and accordingly, collect a large scale dataset called MUlti-Shot EventS (MUSES). MUSES has 31,477 event instances for a total of 716 video hours. The core nature of MUSES is the frequent shot cuts, for an average of 19 shots per instance and 176 shots per video, which induces large intrainstance variations. Our comprehensive evaluations show that the state-of-the-art method in temporal action localization only achieves an mAP of 13.1% at IoU=0.5. As a minor contribution, we present a simple baseline approach for handling the intra-instance variations, which reports an mAP of 18.9% on MUSES and 56.9% on THUMOS14 at IoU=0.5. To facilitate research in this direction, we release the dataset and the project code at https://songbai.site/muses.

Multi-level Knowledge Distillation

Knowledge distillation has become an important technique for model compression and acceleration. The conventional knowledge distillation approaches aim to transfer knowledge from teacher to student networks by minimizing the KL-divergence between their probabilistic outputs, which only consider the mutual relationship between individual representations of teacher and student networks. Recently, the contrastive loss-based knowledge distillation is proposed to enable a student to learn the instance discriminative knowledge of a teacher by mapping the same image close and different images far away in the representation space. However, all of these methods ignore that the teacher's knowledge is multi-level, e.g., individual, relational and categorical level. These different levels of knowledge cannot be effectively captured by only one kind of supervisory signal. Here, we introduce Multi-level Knowledge Distillation (MLKD) to transfer richer representational knowledge from teacher to student networks. MLKD employs three novel teacher-student similarities: individual similarity, relational similarity, and categorical similarity, to encourage the student network to learn sample-wise, structure-wise and category-wise knowledge in the teacher network. Experiments demonstrate that MLKD outperforms other state-of-the-art methods on both similar-architecture and cross-architecture tasks. We further show that MLKD can improve the transferability of learned representations in the student network.

Model-Free Voltage Regulation of Unbalanced Distribution Network Based on Surrogate Model and Deep Reinforcement Learning

Accurate knowledge of the distribution system topology and parameters is required to achieve good voltage controls, but this is difficult to obtain in practice. This paper develops a model-free approach based on the surrogate model and deep reinforcement learning (DRL). We have also extended it to deal with unbalanced three-phase scenarios. The key idea is to learn a surrogate model to capture the relationship between the power injections and voltage fluctuation of each node from historical data instead of using the original inaccurate model affected by errors and uncertainties. This allows us to integrate the DRL with the learned surrogate model. In particular, DRL is applied to learn the optimal control strategy from the experiences obtained by continuous interactions with the surrogate model. The integrated framework contains training three networks, i.e., surrogate model, actor, and critic networks, which fully leverage the strong nonlinear fitting ability of deep learning and DRL for online decision making. Several single-phase approaches have also been extended to deal with three-phase unbalance scenarios and the simulation results on the IEEE 123-bus system show that our proposed method can achieve similar performance as those that use accurate physical models.