Existing Self-Supervised Learning (SSL) models for speech typically process speech signals at a fixed resolution of 20 milliseconds. This approach overlooks the varying informational content present at different resolutions in speech signals. In contrast, this paper aims to incorporate multi-resolution information into speech self-supervised representation learning. We introduce a SSL model that leverages a hierarchical Transformer architecture, complemented by HuBERT-style masked prediction objectives, to process speech at multiple resolutions. Experimental results indicate that the proposed model not only achieves more efficient inference but also exhibits superior or comparable performance to the original HuBERT model over various tasks. Specifically, significant performance improvements over the original HuBERT have been observed in fine-tuning experiments on the LibriSpeech speech recognition benchmark as well as in evaluations using the Speech Universal PERformance Benchmark (SUPERB) and Multilingual SUPERB (ML-SUPERB).
相關內容
Vision-language pre-trained models have achieved impressive performance on various downstream tasks. However, their large model sizes hinder their utilization on platforms with limited computational resources. We find that directly using smaller pre-trained models and applying magnitude-based pruning on CLIP models leads to inflexibility and inferior performance. Recent efforts for VLP compression either adopt uni-modal compression metrics resulting in limited performance or involve costly mask-search processes with learnable masks. In this paper, we first propose the Module-wise Pruning Error (MoPE) metric, accurately assessing CLIP module importance by performance decline on cross-modal tasks. Using the MoPE metric, we introduce a unified pruning framework applicable to both pre-training and task-specific fine-tuning compression stages. For pre-training, MoPE-CLIP effectively leverages knowledge from the teacher model, significantly reducing pre-training costs while maintaining strong zero-shot capabilities. For fine-tuning, consecutive pruning from width to depth yields highly competitive task-specific models. Extensive experiments in two stages demonstrate the effectiveness of the MoPE metric, and MoPE-CLIP outperforms previous state-of-the-art VLP compression methods.
Image super-resolution (SR) methods typically model degradation to improve reconstruction accuracy in complex and unknown degradation scenarios. However, extracting degradation information from low-resolution images is challenging, which limits the model performance. To boost image SR performance, one feasible approach is to introduce additional priors. Inspired by advancements in multi-modal methods and text prompt image processing, we introduce text prompts to image SR to provide degradation priors. Specifically, we first design a text-image generation pipeline to integrate text into the SR dataset through the text degradation representation and degradation model. The text representation applies a discretization manner based on the binning method to describe the degradation abstractly. This method maintains the flexibility of the text and is user-friendly. Meanwhile, we propose the PromptSR to realize the text prompt SR. The PromptSR utilizes the pre-trained language model (e.g., T5 or CLIP) to enhance restoration. We train the model on the generated text-image dataset. Extensive experiments indicate that introducing text prompts into SR, yields excellent results on both synthetic and real-world images. Code is available at: //github.com/zhengchen1999/PromptSR.
Multiple extended target tracking (ETT) has gained increasing attention due to the development of high-precision LiDAR and radar sensors in automotive applications. For LiDAR point cloud-based vehicle tracking, this paper presents a probabilistic measurement-region association (PMRA) ETT model, which can describe the complex measurement distribution by partitioning the target extent into different regions. The PMRA model overcomes the drawbacks of previous data-region association (DRA) models by eliminating the approximation error of constrained estimation and using continuous integrals to more reliably calculate the association probabilities. Furthermore, the PMRA model is integrated with the Poisson multi-Bernoulli mixture (PMBM) filter for tracking multiple vehicles. Simulation results illustrate the superior estimation accuracy of the proposed PMRA-PMBM filter in terms of both positions and extents of the vehicles comparing with PMBM filters using the gamma Gaussian inverse Wishart and DRA implementations.
We propose FocusCLIP, integrating subject-level guidance--a specialized mechanism for target-specific supervision--into the CLIP framework for improved zero-shot transfer on human-centric tasks. Our novel contributions enhance CLIP on both the vision and text sides. On the vision side, we incorporate ROI heatmaps emulating human visual attention mechanisms to emphasize subject-relevant image regions. On the text side, we introduce human pose descriptions to provide rich contextual information. For human-centric tasks, FocusCLIP is trained with images from the MPII Human Pose dataset. The proposed approach surpassed CLIP by an average of 8.61% across five previously unseen datasets covering three human-centric tasks. FocusCLIP achieved an average accuracy of 33.65% compared to 25.04% by CLIP. We observed a 3.98% improvement in activity recognition, a 14.78% improvement in age classification, and a 7.06% improvement in emotion recognition. Moreover, using our proposed single-shot LLM prompting strategy, we release a high-quality MPII Pose Descriptions dataset to encourage further research in multimodal learning for human-centric tasks. Furthermore, we also demonstrate the effectiveness of our subject-level supervision on non-human-centric tasks. FocusCLIP shows a 2.47% improvement over CLIP in zero-shot bird classification using the CUB dataset. Our findings emphasize the potential of integrating subject-level guidance with general pretraining methods for enhanced downstream performance.
Prompt-tuning methods for Continual Learning (CL) freeze a large pre-trained model and focus training on a few parameter vectors termed prompts. Most of these methods organize these vectors in a pool of key-value pairs, and use the input image as query to retrieve the prompts (values). However, as keys are learned while tasks progress, the prompting selection strategy is itself subject to catastrophic forgetting, an issue often overlooked by existing approaches. For instance, prompts introduced to accommodate new tasks might end up interfering with previously learned prompts. To make the selection strategy more stable, we ask a foundational model (CLIP) to select our prompt within a two-level adaptation mechanism. Specifically, the first level leverages standard textual prompts for the CLIP textual encoder, leading to stable class prototypes. The second level, instead, uses these prototypes along with the query image as keys to index a second pool. The retrieved prompts serve to adapt a pre-trained ViT, granting plasticity. In doing so, we also propose a novel residual mechanism to transfer CLIP semantics to the ViT layers. Through extensive analysis on established CL benchmarks, we show that our method significantly outperforms both state-of-the-art CL approaches and the zero-shot CLIP test. Notably, our findings hold true even for datasets with a substantial domain gap w.r.t. the pre-training knowledge of the backbone model, as showcased by experiments on satellite imagery and medical datasets.
The advancement of Multi-modal Pre-training highlights the necessity for a robust Multi-Modal Knowledge Graph (MMKG) representation learning framework. This framework is crucial for integrating structured knowledge into multi-modal Large Language Models (LLMs) at scale, aiming to alleviate issues like knowledge misconceptions and multi-modal hallucinations. In this work, to evaluate models' ability to accurately embed entities within MMKGs, we focus on two widely researched tasks: Multi-modal Knowledge Graph Completion (MKGC) and Multi-modal Entity Alignment (MMEA). Building on this foundation, we propose a novel SNAG method that utilizes a Transformer-based architecture equipped with modality-level noise masking for the robust integration of multi-modal entity features in KGs. By incorporating specific training objectives for both MKGC and MMEA, our approach achieves SOTA performance across a total of ten datasets (three for MKGC and seven for MEMA), demonstrating its robustness and versatility. Besides, SNAG can not only function as a standalone model but also enhance other existing methods, providing stable performance improvements. Our code and data are available at: //github.com/zjukg/SNAG.
The eXtreme Multi-label text Classification(XMC) refers to training a classifier that assigns a text sample with relevant labels from an extremely large-scale label set (e.g., millions of labels). We propose MatchXML, an efficient text-label matching framework for XMC. We observe that the label embeddings generated from the sparse Term Frequency-Inverse Document Frequency(TF-IDF) features have several limitations. We thus propose label2vec to effectively train the semantic dense label embeddings by the Skip-gram model. The dense label embeddings are then used to build a Hierarchical Label Tree by clustering. In fine-tuning the pre-trained encoder Transformer, we formulate the multi-label text classification as a text-label matching problem in a bipartite graph. We then extract the dense text representations from the fine-tuned Transformer. Besides the fine-tuned dense text embeddings, we also extract the static dense sentence embeddings from a pre-trained Sentence Transformer. Finally, a linear ranker is trained by utilizing the sparse TF-IDF features, the fine-tuned dense text representations and static dense sentence features. Experimental results demonstrate that MatchXML achieves state-of-the-art accuracy on five out of six datasets. As for the speed, MatchXML outperforms the competing methods on all the six datasets. Our source code is publicly available at //github.com/huiyegit/MatchXML.
Existing learned video compression models employ flow net or deformable convolutional networks (DCN) to estimate motion information. However, the limited receptive fields of flow net and DCN inherently direct their attentiveness towards the local contexts. Global contexts, such as large-scale motions and global correlations among frames are ignored, presenting a significant bottleneck for capturing accurate motions. To address this issue, we propose a joint local and global motion compensation module (LGMC) for leaned video coding. More specifically, we adopt flow net for local motion compensation. To capture global context, we employ the cross attention in feature domain for motion compensation. In addition, to avoid the quadratic complexity of vanilla cross attention, we divide the softmax operations in attention into two independent softmax operations, leading to linear complexity. To validate the effectiveness of our proposed LGMC, we integrate it with DCVC-TCM and obtain learned video compression with joint local and global motion compensation (LVC-LGMC). Extensive experiments demonstrate that our LVC-LGMC has significant rate-distortion performance improvements over baseline DCVC-TCM.
Despite the tremendous success of diffusion generative models in text-to-image generation, replicating this success in the domain of image compression has proven difficult. In this paper, we demonstrate that diffusion can significantly improve perceptual quality at a given bit-rate, outperforming state-of-the-art approaches PO-ELIC and HiFiC as measured by FID score. This is achieved using a simple but theoretically motivated two-stage approach combining an autoencoder targeting MSE followed by a further score-based decoder. However, as we will show, implementation details matter and the optimal design decisions can differ greatly from typical text-to-image models.
High spectral dimensionality and the shortage of annotations make hyperspectral image (HSI) classification a challenging problem. Recent studies suggest that convolutional neural networks can learn discriminative spatial features, which play a paramount role in HSI interpretation. However, most of these methods ignore the distinctive spectral-spatial characteristic of hyperspectral data. In addition, a large amount of unlabeled data remains an unexploited gold mine for efficient data use. Therefore, we proposed an integration of generative adversarial networks (GANs) and probabilistic graphical models for HSI classification. Specifically, we used a spectral-spatial generator and a discriminator to identify land cover categories of hyperspectral cubes. Moreover, to take advantage of a large amount of unlabeled data, we adopted a conditional random field to refine the preliminary classification results generated by GANs. Experimental results obtained using two commonly studied datasets demonstrate that the proposed framework achieved encouraging classification accuracy using a small number of data for training.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191