Despite recent progress in text-to-audio (TTA) generation, we show that the state-of-the-art models, such as AudioLDM, trained on datasets with an imbalanced class distribution, such as AudioCaps, are biased in their generation performance. Specifically, they excel in generating common audio classes while underperforming in the rare ones, thus degrading the overall generation performance. We refer to this problem as long-tailed text-to-audio generation. To address this issue, we propose a simple retrieval-augmented approach for TTA models. Specifically, given an input text prompt, we first leverage a Contrastive Language Audio Pretraining (CLAP) model to retrieve relevant text-audio pairs. The features of the retrieved audio-text data are then used as additional conditions to guide the learning of TTA models. We enhance AudioLDM with our proposed approach and denote the resulting augmented system as Re-AudioLDM. On the AudioCaps dataset, Re-AudioLDM achieves a state-of-the-art Frechet Audio Distance (FAD) of 1.37, outperforming the existing approaches by a large margin. Furthermore, we show that Re-AudioLDM can generate realistic audio for complex scenes, rare audio classes, and even unseen audio types, indicating its potential in TTA tasks.
相關內容
Large-scale language models achieved state-of-the-art performance over a number of language tasks. However, they fail on adversarial language examples, which are sentences optimized to fool the language models but with similar semantic meanings for humans. While prior work focuses on making the language model robust at training time, retraining for robustness is often unrealistic for large-scale foundation models. Instead, we propose to make the language models robust at test time. By dynamically adapting the input sentence with predictions from masked words, we show that we can reverse many language adversarial attacks. Since our approach does not require any training, it works for novel tasks at test time and can adapt to novel adversarial corruptions. Visualizations and empirical results on two popular sentence classification datasets demonstrate that our method can repair adversarial language attacks over 65% o
Text-to-Image diffusion models have made tremendous progress over the past two years, enabling the generation of highly realistic images based on open-domain text descriptions. However, despite their success, text descriptions often struggle to adequately convey detailed controls, even when composed of long and complex texts. Moreover, recent studies have also shown that these models face challenges in understanding such complex texts and generating the corresponding images. Therefore, there is a growing need to enable more control modes beyond text description. In this paper, we introduce Uni-ControlNet, a unified framework that allows for the simultaneous utilization of different local controls (e.g., edge maps, depth map, segmentation masks) and global controls (e.g., CLIP image embeddings) in a flexible and composable manner within one single model. Unlike existing methods, Uni-ControlNet only requires the fine-tuning of two additional adapters upon frozen pre-trained text-to-image diffusion models, eliminating the huge cost of training from scratch. Moreover, thanks to some dedicated adapter designs, Uni-ControlNet only necessitates a constant number (i.e., 2) of adapters, regardless of the number of local or global controls used. This not only reduces the fine-tuning costs and model size, making it more suitable for real-world deployment, but also facilitate composability of different conditions. Through both quantitative and qualitative comparisons, Uni-ControlNet demonstrates its superiority over existing methods in terms of controllability, generation quality and composability. Code is available at \url{//github.com/ShihaoZhaoZSH/Uni-ControlNet}.
Audio fingerprinting is a well-established solution for song identification from short recording excerpts. Popular methods rely on the extraction of sparse representations, generally spectral peaks, and have proven to be accurate, fast, and scalable to large collections. However, real-world applications of audio identification often happen in noisy environments, which can cause these systems to fail. In this work, we tackle this problem by introducing and releasing a new audio augmentation pipeline that adds noise to music snippets in a realistic way, by stochastically mimicking real-world scenarios. We then propose and release a deep learning model that removes noisy components from spectrograms in order to improve peak-based fingerprinting systems' accuracy. We show that the addition of our model improves the identification performance of commonly used audio fingerprinting systems, even under noisy conditions.
In this paper, we propose a new multi-modal task, namely audio-visual instance segmentation (AVIS), in which the goal is to identify, segment, and track individual sounding object instances in audible videos, simultaneously. To our knowledge, it is the first time that instance segmentation has been extended into the audio-visual domain. To better facilitate this research, we construct the first audio-visual instance segmentation benchmark (AVISeg). Specifically, AVISeg consists of 1,258 videos with an average duration of 62.6 seconds from YouTube and public audio-visual datasets, where 117 videos have been annotated by using an interactive semi-automatic labeling tool based on the Segment Anything Model (SAM). In addition, we present a simple baseline model for the AVIS task. Our new model introduces an audio branch and a cross-modal fusion module to Mask2Former to locate all sounding objects. Finally, we evaluate the proposed method using two backbones on AVISeg. We believe that AVIS will inspire the community towards a more comprehensive multi-modal understanding.
After discovering that Language Models (LMs) can be good in-context few-shot learners, numerous strategies have been proposed to optimize in-context sequence configurations. Recently, researchers in Vision-Language (VL) domains also develop their few-shot learners, while they only use the simplest way, ie., randomly sampling, to configure in-context image-text pairs. In order to explore the effects of varying configurations on VL in-context learning, we devised four strategies for image selection and four for caption assignment to configure in-context image-text pairs for image captioning. Here Image Captioning is used as the case study since it can be seen as the visually-conditioned LM. Our comprehensive experiments yield two counter-intuitive but valuable insights, highlighting the distinct characteristics of VL in-context learning due to multi-modal synergy, as compared to the NLP case. Furthermore, in our exploration of optimal combination strategies, we observed an average performance enhancement of 20.7 of CIDEr scores compared to the baseline. The code is given in //github.com/yongliang-wu/ExploreCfg.
We argue that Transformers are essentially graph-to-graph models, with sequences just being a special case. Attention weights are functionally equivalent to graph edges. Our Graph-to-Graph Transformer architecture makes this ability explicit, by inputting graph edges into the attention weight computations and predicting graph edges with attention-like functions, thereby integrating explicit graphs into the latent graphs learned by pretrained Transformers. Adding iterative graph refinement provides a joint embedding of input, output, and latent graphs, allowing non-autoregressive graph prediction to optimise the complete graph without any bespoke pipeline or decoding strategy. Empirical results show that this architecture achieves state-of-the-art accuracies for modelling a variety of linguistic structures, integrating very effectively with the latent linguistic representations learned by pretraining.
This is a very short technical report, which introduces the solution of the Team BUPT-CASIA for Short-video Face Parsing Track of The 3rd Person in Context (PIC) Workshop and Challenge at CVPR 2021. Face parsing has recently attracted increasing interest due to its numerous application potentials. Generally speaking, it has a lot in common with human parsing, such as task setting, data characteristics, number of categories and so on. Therefore, this work applies state-of-the-art human parsing method to face parsing task to explore the similarities and differences between them. Our submission achieves 86.84% score and wins the 2nd place in the challenge.
With the rise of powerful pre-trained vision-language models like CLIP, it becomes essential to investigate ways to adapt these models to downstream datasets. A recently proposed method named Context Optimization (CoOp) introduces the concept of prompt learning -- a recent trend in NLP -- to the vision domain for adapting pre-trained vision-language models. Specifically, CoOp turns context words in a prompt into a set of learnable vectors and, with only a few labeled images for learning, can achieve huge improvements over intensively-tuned manual prompts. In our study we identify a critical problem of CoOp: the learned context is not generalizable to wider unseen classes within the same dataset, suggesting that CoOp overfits base classes observed during training. To address the problem, we propose Conditional Context Optimization (CoCoOp), which extends CoOp by further learning a lightweight neural network to generate for each image an input-conditional token (vector). Compared to CoOp's static prompts, our dynamic prompts adapt to each instance and are thus less sensitive to class shift. Extensive experiments show that CoCoOp generalizes much better than CoOp to unseen classes, even showing promising transferability beyond a single dataset; and yields stronger domain generalization performance as well. Code is available at //github.com/KaiyangZhou/CoOp.
Convolutional neural networks (CNNs) have shown dramatic improvements in single image super-resolution (SISR) by using large-scale external samples. Despite their remarkable performance based on the external dataset, they cannot exploit internal information within a specific image. Another problem is that they are applicable only to the specific condition of data that they are supervised. For instance, the low-resolution (LR) image should be a "bicubic" downsampled noise-free image from a high-resolution (HR) one. To address both issues, zero-shot super-resolution (ZSSR) has been proposed for flexible internal learning. However, they require thousands of gradient updates, i.e., long inference time. In this paper, we present Meta-Transfer Learning for Zero-Shot Super-Resolution (MZSR), which leverages ZSSR. Precisely, it is based on finding a generic initial parameter that is suitable for internal learning. Thus, we can exploit both external and internal information, where one single gradient update can yield quite considerable results. (See Figure 1). With our method, the network can quickly adapt to a given image condition. In this respect, our method can be applied to a large spectrum of image conditions within a fast adaptation process.
Many recent state-of-the-art recommender systems such as D-ATT, TransNet and DeepCoNN exploit reviews for representation learning. This paper proposes a new neural architecture for recommendation with reviews. Our model operates on a multi-hierarchical paradigm and is based on the intuition that not all reviews are created equal, i.e., only a select few are important. The importance, however, should be dynamically inferred depending on the current target. To this end, we propose a review-by-review pointer-based learning scheme that extracts important reviews, subsequently matching them in a word-by-word fashion. This enables not only the most informative reviews to be utilized for prediction but also a deeper word-level interaction. Our pointer-based method operates with a novel gumbel-softmax based pointer mechanism that enables the incorporation of discrete vectors within differentiable neural architectures. Our pointer mechanism is co-attentive in nature, learning pointers which are co-dependent on user-item relationships. Finally, we propose a multi-pointer learning scheme that learns to combine multiple views of interactions between user and item. Overall, we demonstrate the effectiveness of our proposed model via extensive experiments on \textbf{24} benchmark datasets from Amazon and Yelp. Empirical results show that our approach significantly outperforms existing state-of-the-art, with up to 19% and 71% relative improvement when compared to TransNet and DeepCoNN respectively. We study the behavior of our multi-pointer learning mechanism, shedding light on evidence aggregation patterns in review-based recommender systems.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191