Recent high-performance transformer-based speech enhancement models demonstrate that time domain methods could achieve similar performance as time-frequency domain methods. However, time-domain speech enhancement systems typically receive input audio sequences consisting of a large number of time steps, making it challenging to model extremely long sequences and train models to perform adequately. In this paper, we utilize smaller audio chunks as input to achieve efficient utilization of audio information to address the above challenges. We propose a dual-phase audio transformer for denoising (DPATD), a novel model to organize transformer layers in a deep structure to learn clean audio sequences for denoising. DPATD splits the audio input into smaller chunks, where the input length can be proportional to the square root of the original sequence length. Our memory-compressed explainable attention is efficient and converges faster compared to the frequently used self-attention module. Extensive experiments demonstrate that our model outperforms state-of-the-art methods.
相關內容
This paper explores preference distillation for large vision language models (LVLMs), improving their ability to generate helpful and faithful responses anchoring the visual context. We first build a vision-language feedback (VLFeedback) dataset utilizing AI annotation. Specifically, responses are generated by models sampled from 12 LVLMs, conditioned on multi-modal instructions sourced from various datasets. We adopt GPT-4V to assess the generated outputs regarding helpfulness, visual faithfulness, and ethical considerations. Furthermore, the preference supervision is distilled into Qwen-VL-Chat through the direct preference optimization (DPO) method. The resulting model Silkie, achieves 6.9% and 9.5% relative improvement on the MME benchmark regarding the perception and cognition capabilities, respectively. Silkie also demonstrates reduced hallucination by setting a new state-of-the-art score of 3.02 on the MMHal-Bench benchmark. Further analysis shows that DPO with our VLFeedback dataset mainly boosts the fine-grained perception and complex cognition abilities of LVLMs, leading to more comprehensive improvements compared to human-annotated preference datasets.
Recent advances in contrastive language-image pretraining (CLIP) have demonstrated strong capabilities in zero-shot classification by aligning visual representations with target text embeddings in an image level. However, in dense prediction tasks, CLIP often struggles to localize visual features within an image and fails to give accurate pixel-level predictions, which prevents it from functioning as a generalized visual foundation model. In this work, we aim to enhance CLIP's potential for semantic segmentation with minimal modifications to its pretrained models. By rethinking self-attention, we surprisingly find that CLIP can adapt to dense prediction tasks by simply introducing a novel Correlative Self-Attention (CSA) mechanism. Specifically, we replace the traditional self-attention block of CLIP vision encoder's last layer by our CSA module and reuse its pretrained projection matrices of query, key, and value, leading to a training-free adaptation approach for CLIP's zero-shot semantic segmentation. Extensive experiments show the advantage of CSA: we obtain a 38.2% average zero-shot mIoU across eight semantic segmentation benchmarks highlighted in this paper, significantly outperforming the existing SoTA's 33.9% and the vanilla CLIP's 14.1%.
The development of autoregressive modeling (AM) in computer vision lags behind natural language processing (NLP) in self-supervised pre-training. This is mainly caused by the challenge that images are not sequential signals and lack a natural order when applying autoregressive modeling. In this study, inspired by human beings' way of grasping an image, i.e., focusing on the main object first, we present a semantic-aware autoregressive image modeling (SemAIM) method to tackle this challenge. The key insight of SemAIM is to autoregressive model images from the semantic patches to the less semantic patches. To this end, we first calculate a semantic-aware permutation of patches according to their feature similarities and then perform the autoregression procedure based on the permutation. In addition, considering that the raw pixels of patches are low-level signals and are not ideal prediction targets for learning high-level semantic representation, we also explore utilizing the patch features as the prediction targets. Extensive experiments are conducted on a broad range of downstream tasks, including image classification, object detection, and instance/semantic segmentation, to evaluate the performance of SemAIM. The results demonstrate SemAIM achieves state-of-the-art performance compared with other self-supervised methods. Specifically, with ViT-B, SemAIM achieves 84.1% top-1 accuracy for fine-tuning on ImageNet, 51.3% AP and 45.4% AP for object detection and instance segmentation on COCO, which outperforms the vanilla MAE by 0.5%, 1.0%, and 0.5%, respectively.
Large-scale pre-trained models have achieved remarkable success in various computer vision tasks. A standard approach to leverage these models is to fine-tune all model parameters for downstream tasks, which poses challenges in terms of computational and storage costs. Recently, inspired by Natural Language Processing (NLP), parameter-efficient transfer learning has been successfully applied to vision tasks. However, most existing techniques primarily focus on single-task adaptation, and despite limited research on multi-task adaptation, these methods often exhibit suboptimal training and inference efficiency. In this paper, we first propose an once-for-all Vision Multi-Task Adapter (VMT-Adapter), which strikes approximately O(1) training and inference efficiency w.r.t task number. Concretely, VMT-Adapter shares the knowledge from multiple tasks to enhance cross-task interaction while preserves task-specific knowledge via independent knowledge extraction modules. Notably, since task-specific modules require few parameters, VMT-Adapter can handle an arbitrary number of tasks with a negligible increase of trainable parameters. We also propose VMT-Adapter-Lite, which further reduces the trainable parameters by learning shared parameters between down- and up-projections. Extensive experiments on four dense scene understanding tasks demonstrate the superiority of VMT-Adapter(-Lite), achieving a 3.96%(1.34%) relative improvement compared to single-task full fine-tuning, while utilizing merely ~1% (0.36%) trainable parameters of the pre-trained model.
We investigate the challenges of style transfer in multi-modal visual narratives. Among static visual narratives such as comics and manga, there are distinct visual styles in terms of presentation. They include style features across multiple dimensions, such as panel layout, size, shape, and color. They include both visual and text media elements. The layout of both text and media elements is also significant in terms of narrative communication. The sequential transitions between panels are where readers make inferences about the narrative world. These feature differences provide an interesting challenge for style transfer in which there are distinctions between the processing of features for each modality. We introduce the notion of comprehension-preserving style transfer (CPST) in such multi-modal domains. CPST requires not only traditional metrics of style transfer but also metrics of narrative comprehension. To spur further research in this area, we present an annotated dataset of comics and manga and an initial set of algorithms that utilize separate style transfer modules for the visual, textual, and layout parameters. To test whether the style transfer preserves narrative semantics, we evaluate this algorithm through visual story cloze tests inspired by work in computational cognition of narrative systems. Understanding the connection between style and narrative semantics provides insight for applications ranging from informational brochure designs to data storytelling.
We introduce FaceTalk, a novel generative approach designed for synthesizing high-fidelity 3D motion sequences of talking human heads from input audio signal. To capture the expressive, detailed nature of human heads, including hair, ears, and finer-scale eye movements, we propose to couple speech signal with the latent space of neural parametric head models to create high-fidelity, temporally coherent motion sequences. We propose a new latent diffusion model for this task, operating in the expression space of neural parametric head models, to synthesize audio-driven realistic head sequences. In the absence of a dataset with corresponding NPHM expressions to audio, we optimize for these correspondences to produce a dataset of temporally-optimized NPHM expressions fit to audio-video recordings of people talking. To the best of our knowledge, this is the first work to propose a generative approach for realistic and high-quality motion synthesis of volumetric human heads, representing a significant advancement in the field of audio-driven 3D animation. Notably, our approach stands out in its ability to generate plausible motion sequences that can produce high-fidelity head animation coupled with the NPHM shape space. Our experimental results substantiate the effectiveness of FaceTalk, consistently achieving superior and visually natural motion, encompassing diverse facial expressions and styles, outperforming existing methods by 75% in perceptual user study evaluation.
With the capability of modeling bidirectional contexts, denoising autoencoding based pretraining like BERT achieves better performance than pretraining approaches based on autoregressive language modeling. However, relying on corrupting the input with masks, BERT neglects dependency between the masked positions and suffers from a pretrain-finetune discrepancy. In light of these pros and cons, we propose XLNet, a generalized autoregressive pretraining method that (1) enables learning bidirectional contexts by maximizing the expected likelihood over all permutations of the factorization order and (2) overcomes the limitations of BERT thanks to its autoregressive formulation. Furthermore, XLNet integrates ideas from Transformer-XL, the state-of-the-art autoregressive model, into pretraining. Empirically, XLNet outperforms BERT on 20 tasks, often by a large margin, and achieves state-of-the-art results on 18 tasks including question answering, natural language inference, sentiment analysis, and document ranking.
To provide more accurate, diverse, and explainable recommendation, it is compulsory to go beyond modeling user-item interactions and take side information into account. Traditional methods like factorization machine (FM) cast it as a supervised learning problem, which assumes each interaction as an independent instance with side information encoded. Due to the overlook of the relations among instances or items (e.g., the director of a movie is also an actor of another movie), these methods are insufficient to distill the collaborative signal from the collective behaviors of users. In this work, we investigate the utility of knowledge graph (KG), which breaks down the independent interaction assumption by linking items with their attributes. We argue that in such a hybrid structure of KG and user-item graph, high-order relations --- which connect two items with one or multiple linked attributes --- are an essential factor for successful recommendation. We propose a new method named Knowledge Graph Attention Network (KGAT) which explicitly models the high-order connectivities in KG in an end-to-end fashion. It recursively propagates the embeddings from a node's neighbors (which can be users, items, or attributes) to refine the node's embedding, and employs an attention mechanism to discriminate the importance of the neighbors. Our KGAT is conceptually advantageous to existing KG-based recommendation methods, which either exploit high-order relations by extracting paths or implicitly modeling them with regularization. Empirical results on three public benchmarks show that KGAT significantly outperforms state-of-the-art methods like Neural FM and RippleNet. Further studies verify the efficacy of embedding propagation for high-order relation modeling and the interpretability benefits brought by the attention mechanism.
Retrieving object instances among cluttered scenes efficiently requires compact yet comprehensive regional image representations. Intuitively, object semantics can help build the index that focuses on the most relevant regions. However, due to the lack of bounding-box datasets for objects of interest among retrieval benchmarks, most recent work on regional representations has focused on either uniform or class-agnostic region selection. In this paper, we first fill the void by providing a new dataset of landmark bounding boxes, based on the Google Landmarks dataset, that includes $94k$ images with manually curated boxes from $15k$ unique landmarks. Then, we demonstrate how a trained landmark detector, using our new dataset, can be leveraged to index image regions and improve retrieval accuracy while being much more efficient than existing regional methods. In addition, we further introduce a novel regional aggregated selective match kernel (R-ASMK) to effectively combine information from detected regions into an improved holistic image representation. R-ASMK boosts image retrieval accuracy substantially at no additional memory cost, while even outperforming systems that index image regions independently. Our complete image retrieval system improves upon the previous state-of-the-art by significant margins on the Revisited Oxford and Paris datasets. Code and data will be released.
The cross-domain recommendation technique is an effective way of alleviating the data sparsity in recommender systems by leveraging the knowledge from relevant domains. Transfer learning is a class of algorithms underlying these techniques. In this paper, we propose a novel transfer learning approach for cross-domain recommendation by using neural networks as the base model. We assume that hidden layers in two base networks are connected by cross mappings, leading to the collaborative cross networks (CoNet). CoNet enables dual knowledge transfer across domains by introducing cross connections from one base network to another and vice versa. CoNet is achieved in multi-layer feedforward networks by adding dual connections and joint loss functions, which can be trained efficiently by back-propagation. The proposed model is evaluated on two real-world datasets and it outperforms baseline models by relative improvements of 3.56\% in MRR and 8.94\% in NDCG, respectively.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191