Transformers have demonstrated their effectiveness in image restoration tasks. Existing Transformer architectures typically comprise two essential components: multi-head self-attention and feed-forward network (FFN). The former captures long-range pixel dependencies, while the latter enables the model to learn complex patterns and relationships in the data. Previous studies have demonstrated that FFNs are key-value memories \cite{geva2020transformer}, which are vital in modern Transformer architectures. In this paper, we conduct an empirical study to explore the potential of attention mechanisms without using FFN and provide novel structures to demonstrate that removing FFN is flexible for image restoration. Specifically, we propose Continuous Scaling Attention (\textbf{CSAttn}), a method that computes attention continuously in three stages without using FFN. To achieve competitive performance, we propose a series of key components within the attention. Our designs provide a closer look at the attention mechanism and reveal that some simple operations can significantly affect the model performance. We apply our \textbf{CSAttn} to several image restoration tasks and show that our model can outperform CNN-based and Transformer-based image restoration approaches.
Single-domain generalized object detection aims to enhance a model's generalizability to multiple unseen target domains using only data from a single source domain during training. This is a practical yet challenging task as it requires the model to address domain shift without incorporating target domain data into training. In this paper, we propose a novel phrase grounding-based style transfer (PGST) approach for the task. Specifically, we first define textual prompts to describe potential objects for each unseen target domain. Then, we leverage the grounded language-image pre-training (GLIP) model to learn the style of these target domains and achieve style transfer from the source to the target domain. The style-transferred source visual features are semantically rich and could be close to imaginary counterparts in the target domain. Finally, we employ these style-transferred visual features to fine-tune GLIP. By introducing imaginary counterparts, the detector could be effectively generalized to unseen target domains using only a single source domain for training. Extensive experimental results on five diverse weather driving benchmarks demonstrate our proposed approach achieves state-of-the-art performance, even surpassing some domain adaptive methods that incorporate target domain images into the training process.The source codes and pre-trained models will be made available.
The feature selection in a traditional binary classification algorithm is always used in the stage of dataset preprocessing, which makes the obtained features not necessarily the best ones for the classification algorithm, thus affecting the classification performance. For a traditional rule-based binary classification algorithm, classification rules are usually deterministic, which results in the fuzzy information contained in the rules being ignored. To do so, this paper employs iterative feature selection in fuzzy rule-based binary classification. The proposed algorithm combines feature selection based on fuzzy correlation family with rule mining based on biclustering. It first conducts biclustering on the dataset after feature selection. Then it conducts feature selection again for the biclusters according to the feedback of biclusters evaluation. In this way, an iterative feature selection framework is build. During the iteration process, it stops until the obtained bicluster meets the requirements. In addition, the rule membership function is introduced to extract vectorized fuzzy rules from the bicluster and construct weak classifiers. The weak classifiers with good classification performance are selected by Adaptive Boosting and the strong classifier is constructed by "weighted average". Finally, we perform the proposed algorithm on different datasets and compare it with other peers. Experimental results show that it achieves good classification performance and outperforms its peers.
Speech emotion recognition (SER) systems aim to recognize human emotional state during human-computer interaction. Most existing SER systems are trained based on utterance-level labels. However, not all frames in an audio have affective states consistent with utterance-level label, which makes it difficult for the model to distinguish the true emotion of the audio and perform poorly. To address this problem, we propose a frame-level emotional state alignment method for SER. First, we fine-tune HuBERT model to obtain a SER system with task-adaptive pretraining (TAPT) method, and extract embeddings from its transformer layers to form frame-level pseudo-emotion labels with clustering. Then, the pseudo labels are used to pretrain HuBERT. Hence, the each frame output of HuBERT has corresponding emotional information. Finally, we fine-tune the above pretrained HuBERT for SER by adding an attention layer on the top of it, which can focus only on those frames that are emotionally more consistent with utterance-level label. The experimental results performed on IEMOCAP indicate that our proposed method performs better than state-of-the-art (SOTA) methods.
Image-to-video generation, which aims to generate a video starting from a given reference image, has drawn great attention. Existing methods try to extend pre-trained text-guided image diffusion models to image-guided video generation models. Nevertheless, these methods often result in either low fidelity or flickering over time due to their limitation to shallow image guidance and poor temporal consistency. To tackle these problems, we propose a high-fidelity image-to-video generation method by devising a frame retention branch on the basis of a pre-trained video diffusion model, named DreamVideo. Instead of integrating the reference image into the diffusion process in a semantic level, our DreamVideo perceives the reference image via convolution layers and concatenate the features with the noisy latents as model input. By this means, the details of the reference image can be preserved to the greatest extent. In addition, by incorporating double-condition classifier-free guidance, a single image can be directed to videos of different actions by providing varying prompt texts. This has significant implications for controllable video generation and holds broad application prospects. We conduct comprehensive experiments on the public dataset, both quantitative and qualitative results indicate that our method outperforms the state-of-the-art method. Especially for fidelity, our model has powerful image retention ability and result in high FVD in UCF101 compared to other image-to-video models. Also, precise control can be achieved by giving different text prompts. Further details and comprehensive results of our model will be presented in https://anonymous0769.github.io/DreamVideo/.
The development of X-ray Free Electron Lasers (XFELs) has opened numerous opportunities to probe atomic structure and ultrafast dynamics of various materials. Single Particle Imaging (SPI) with XFELs enables the investigation of biological particles in their natural physiological states with unparalleled temporal resolution, while circumventing the need for cryogenic conditions or crystallization. However, reconstructing real-space structures from reciprocal-space x-ray diffraction data is highly challenging due to the absence of phase and orientation information, which is further complicated by weak scattering signals and considerable fluctuations in the number of photons per pulse. In this work, we present an end-to-end, self-supervised machine learning approach to recover particle orientations and estimate reciprocal space intensities from diffraction images only. Our method demonstrates great robustness under demanding experimental conditions with significantly enhanced reconstruction capabilities compared with conventional algorithms, and signifies a paradigm shift in SPI as currently practiced at XFELs.
Semi-supervised learning provides an expressive framework for exploiting unlabeled data when labels are insufficient. Previous semi-supervised learning methods typically match model predictions of different data-augmented views in a single-level interaction manner, which highly relies on the quality of pseudo-labels and results in semi-supervised learning not robust. In this paper, we propose a novel SSL method called DualMatch, in which the class prediction jointly invokes feature embedding in a dual-level interaction manner. DualMatch requires consistent regularizations for data augmentation, specifically, 1) ensuring that different augmented views are regulated with consistent class predictions, and 2) ensuring that different data of one class are regulated with similar feature embeddings. Extensive experiments demonstrate the effectiveness of DualMatch. In the standard SSL setting, the proposal achieves 9% error reduction compared with SOTA methods, even in a more challenging class-imbalanced setting, the proposal can still achieve 6% error reduction. Code is available at https://github.com/CWangAI/DualMatch
Recent work has showcased the significant potential of diffusion models in pose-guided person image synthesis. However, owing to the inconsistency in pose between the source and target images, synthesizing an image with a distinct pose, relying exclusively on the source image and target pose information, remains a formidable challenge. This paper presents Progressive Conditional Diffusion Models (PCDMs) that incrementally bridge the gap between person images under the target and source poses through three stages. Specifically, in the first stage, we design a simple prior conditional diffusion model that predicts the global features of the target image by mining the global alignment relationship between pose coordinates and image appearance. Then, the second stage establishes a dense correspondence between the source and target images using the global features from the previous stage, and an inpainting conditional diffusion model is proposed to further align and enhance the contextual features, generating a coarse-grained person image. In the third stage, we propose a refining conditional diffusion model to utilize the coarsely generated image from the previous stage as a condition, achieving texture restoration and enhancing fine-detail consistency. The three-stage PCDMs work progressively to generate the final high-quality and high-fidelity synthesized image. Both qualitative and quantitative results demonstrate the consistency and photorealism of our proposed PCDMs under challenging scenarios.The code and model will be available at https://github.com/muzishen/PCDMs.
Large language models, such as OpenAI's ChatGPT, have demonstrated exceptional language understanding capabilities in various NLP tasks. Sparsely activated mixture-of-experts (MoE) has emerged as a promising solution for scaling models while maintaining a constant number of computational operations. Existing MoE model adopts a fixed gating network where each token is computed by the same number of experts. However, this approach contradicts our intuition that the tokens in each sequence vary in terms of their linguistic complexity and, consequently, require different computational costs. Little is discussed in prior research on the trade-off between computation per token and model performance. This paper introduces adaptive gating in MoE, a flexible training strategy that allows tokens to be processed by a variable number of experts based on expert probability distribution. The proposed framework preserves sparsity while improving training efficiency. Additionally, curriculum learning is leveraged to further reduce training time. Extensive experiments on diverse NLP tasks show that adaptive gating reduces at most 22.5% training time while maintaining inference quality. Moreover, we conduct a comprehensive analysis of the routing decisions and present our insights when adaptive gating is used.