The aim of audio-visual segmentation (AVS) is to precisely differentiate audible objects within videos down to the pixel level. Traditional approaches often tackle this challenge by combining information from various modalities, where the contribution of each modality is implicitly or explicitly modeled. Nevertheless, the interconnections between different modalities tend to be overlooked in audio-visual modeling. In this paper, inspired by the human ability to mentally simulate the sound of an object and its visual appearance, we introduce a bidirectional generation framework. This framework establishes robust correlations between an object's visual characteristics and its associated sound, thereby enhancing the performance of AVS. To achieve this, we employ a visual-to-audio projection component that reconstructs audio features from object segmentation masks and minimizes reconstruction errors. Moreover, recognizing that many sounds are linked to object movements, we introduce an implicit volumetric motion estimation module to handle temporal dynamics that may be challenging to capture using conventional optical flow methods. To showcase the effectiveness of our approach, we conduct comprehensive experiments and analyses on the widely recognized AVSBench benchmark. As a result, we establish a new state-of-the-art performance level in the AVS benchmark, particularly excelling in the challenging MS3 subset which involves segmenting multiple sound sources. To facilitate reproducibility, we plan to release both the source code and the pre-trained model.
相關內容
With the rapid development of large models, the need for data has become increasingly crucial. Especially in 3D object detection, costly manual annotations have hindered further advancements. To reduce the burden of annotation, we study the problem of achieving 3D object detection solely based on 2D annotations. Thanks to advanced 3D reconstruction techniques, it is now feasible to reconstruct the overall static 3D scene. However, extracting precise object-level annotations from the entire scene and generalizing these limited annotations to the entire scene remain challenges. In this paper, we introduce a novel paradigm called BA$^2$-Det, encompassing pseudo label generation and multi-stage generalization. We devise the DoubleClustering algorithm to obtain object clusters from reconstructed scene-level points, and further enhance the model's detection capabilities by developing three stages of generalization: progressing from complete to partial, static to dynamic, and close to distant. Experiments conducted on the large-scale Waymo Open Dataset show that the performance of BA$^2$-Det is on par with the fully-supervised methods using 10% annotations. Additionally, using large raw videos for pretraining,BA$^2$-Det can achieve a 20% relative improvement on the KITTI dataset. The method also has great potential for detecting open-set 3D objects in complex scenes. Project page: //ba2det.site.
Sound event detection (SED) is essential for recognizing specific sounds and their temporal locations within acoustic signals. This becomes challenging particularly for on-device applications, where computational resources are limited. To address this issue, we introduce a novel framework referred to as dual knowledge distillation for developing efficient SED systems in this work. Our proposed dual knowledge distillation commences with temporal-averaging knowledge distillation (TAKD), utilizing a mean student model derived from the temporal averaging of the student model's parameters. This allows the student model to indirectly learn from a pre-trained teacher model, ensuring a stable knowledge distillation. Subsequently, we introduce embedding-enhanced feature distillation (EEFD), which involves incorporating an embedding distillation layer within the student model to bolster contextual learning. On DCASE 2023 Task 4A public evaluation dataset, our proposed SED system with dual knowledge distillation having merely one-third of the baseline model's parameters, demonstrates superior performance in terms of PSDS1 and PSDS2. This highlights the importance of proposed dual knowledge distillation for compact SED systems, which can be ideal for edge devices.
Influence Maximization (IM) is a crucial problem in data science. The goal is to find a fixed-size set of highly-influential seed vertices on a network to maximize the influence spread along the edges. While IM is NP-hard on commonly-used diffusion models, a greedy algorithm can achieve $(1-1/e)$-approximation, repeatedly selecting the vertex with the highest marginal gain in influence as the seed. Due to theoretical guarantees, rich literature focuses on improving the performance of the greedy algorithm. To estimate the marginal gain, existing work either runs Monte Carlo (MC) simulations of influence spread or pre-stores hundreds of sketches (usually per-vertex information). However, these approaches can be inefficient in time (MC simulation) or space (storing sketches), preventing the ideas from scaling to today's large-scale graphs. This paper significantly improves the scalability of IM using two key techniques. The first is a sketch-compression technique for the independent cascading model on undirected graphs. It allows combining the simulation and sketching approaches to achieve a time-space tradeoff. The second technique includes new data structures for parallel seed selection. Using our new approaches, we implemented PaC-IM: Parallel and Compressed IM. We compare PaC-IM with state-of-the-art parallel IM systems on a 96-core machine with 1.5TB memory. PaC-IM can process large-scale graphs with up to 900M vertices and 74B edges in about 2 hours. On average across all tested graphs, our uncompressed version is 5--18$\times$ faster and about 1.4$\times$ more space-efficient than existing parallel IM systems. Using compression further saves 3.8$\times$ space with only 70% overhead in time on average.
In contrast to close-set scenarios that restore images from a predefined set of degradations, open-set image restoration aims to handle the unknown degradations that were unforeseen during the pretraining phase, which is less-touched as far as we know. In this work, we explicitly study this challenging problem and reveal its essence, i.e., the unidentified distribution shifts between test and training data. In recent, test-time adaptation emerges as a fundamental method to address this inherent disparities. Inspired by this, we propose a test-time degradation adaption framework for open-set image restoration, which involves three components, i.e., i) a pre-trained and degradation-agnostic diffusion model to generate clean images, ii) a test-time degradation adapter adapts the unknown degradations based on the input image during the testing phase, and iii) the adapter-guided image restoration guides the model through the adapter to produce the corresponding clean image. Through experiments on multiple degradations absent from the training data, we show that our method achieves comparable even better performance than those task-specific methods.
The key challenge of image manipulation detection is how to learn generalizable features that are sensitive to manipulations in novel data, whilst specific to prevent false alarms on authentic images. Current research emphasizes the sensitivity, with the specificity overlooked. In this paper we address both aspects by multi-view feature learning and multi-scale supervision. By exploiting noise distribution and boundary artifact surrounding tampered regions, the former aims to learn semantic-agnostic and thus more generalizable features. The latter allows us to learn from authentic images which are nontrivial to be taken into account by current semantic segmentation network based methods. Our thoughts are realized by a new network which we term MVSS-Net. Extensive experiments on five benchmark sets justify the viability of MVSS-Net for both pixel-level and image-level manipulation detection.
Temporal relational modeling in video is essential for human action understanding, such as action recognition and action segmentation. Although Graph Convolution Networks (GCNs) have shown promising advantages in relation reasoning on many tasks, it is still a challenge to apply graph convolution networks on long video sequences effectively. The main reason is that large number of nodes (i.e., video frames) makes GCNs hard to capture and model temporal relations in videos. To tackle this problem, in this paper, we introduce an effective GCN module, Dilated Temporal Graph Reasoning Module (DTGRM), designed to model temporal relations and dependencies between video frames at various time spans. In particular, we capture and model temporal relations via constructing multi-level dilated temporal graphs where the nodes represent frames from different moments in video. Moreover, to enhance temporal reasoning ability of the proposed model, an auxiliary self-supervised task is proposed to encourage the dilated temporal graph reasoning module to find and correct wrong temporal relations in videos. Our DTGRM model outperforms state-of-the-art action segmentation models on three challenging datasets: 50Salads, Georgia Tech Egocentric Activities (GTEA), and the Breakfast dataset. The code is available at //github.com/redwang/DTGRM.
Video captioning is a challenging task that requires a deep understanding of visual scenes. State-of-the-art methods generate captions using either scene-level or object-level information but without explicitly modeling object interactions. Thus, they often fail to make visually grounded predictions, and are sensitive to spurious correlations. In this paper, we propose a novel spatio-temporal graph model for video captioning that exploits object interactions in space and time. Our model builds interpretable links and is able to provide explicit visual grounding. To avoid unstable performance caused by the variable number of objects, we further propose an object-aware knowledge distillation mechanism, in which local object information is used to regularize global scene features. We demonstrate the efficacy of our approach through extensive experiments on two benchmarks, showing our approach yields competitive performance with interpretable predictions.
Aspect level sentiment classification aims to identify the sentiment expressed towards an aspect given a context sentence. Previous neural network based methods largely ignore the syntax structure in one sentence. In this paper, we propose a novel target-dependent graph attention network (TD-GAT) for aspect level sentiment classification, which explicitly utilizes the dependency relationship among words. Using the dependency graph, it propagates sentiment features directly from the syntactic context of an aspect target. In our experiments, we show our method outperforms multiple baselines with GloVe embeddings. We also demonstrate that using BERT representations further substantially boosts the performance.
We consider the problem of referring image segmentation. Given an input image and a natural language expression, the goal is to segment the object referred by the language expression in the image. Existing works in this area treat the language expression and the input image separately in their representations. They do not sufficiently capture long-range correlations between these two modalities. In this paper, we propose a cross-modal self-attention (CMSA) module that effectively captures the long-range dependencies between linguistic and visual features. Our model can adaptively focus on informative words in the referring expression and important regions in the input image. In addition, we propose a gated multi-level fusion module to selectively integrate self-attentive cross-modal features corresponding to different levels in the image. This module controls the information flow of features at different levels. We validate the proposed approach on four evaluation datasets. Our proposed approach consistently outperforms existing state-of-the-art methods.
Image-to-image translation aims to learn the mapping between two visual domains. There are two main challenges for many applications: 1) the lack of aligned training pairs and 2) multiple possible outputs from a single input image. In this work, we present an approach based on disentangled representation for producing diverse outputs without paired training images. To achieve diversity, we propose to embed images onto two spaces: a domain-invariant content space capturing shared information across domains and a domain-specific attribute space. Our model takes the encoded content features extracted from a given input and the attribute vectors sampled from the attribute space to produce diverse outputs at test time. To handle unpaired training data, we introduce a novel cross-cycle consistency loss based on disentangled representations. Qualitative results show that our model can generate diverse and realistic images on a wide range of tasks without paired training data. For quantitative comparisons, we measure realism with user study and diversity with a perceptual distance metric. We apply the proposed model to domain adaptation and show competitive performance when compared to the state-of-the-art on the MNIST-M and the LineMod datasets.
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