arXiv subjects

Shentong Mo

Publications and source records attributed to Shentong Mo.

At least 55 records · Page 3Linked to original sources

arXiv2023

Fast Training of Diffusion Transformer with Extreme Masking for 3D Point Clouds Generation

Diffusion Transformers have recently shown remarkable effectiveness in generating high-quality 3D point clouds. However, training voxel-based diffusion models for high-resolution 3D voxels remains prohibitively expensive due to the cubic complexity of attention operators, which arises from the additional dimension of voxels. Motivated by the inherent redundancy of 3D compared to 2D, we propose FastDiT-3D, a novel masked diffusion transformer tailored for efficient 3D point cloud generation, which greatly reduces training costs. Specifically, we draw inspiration from masked autoencoders to dynamically operate the denoising process on masked voxelized point clouds. We also propose a novel voxel-aware masking strategy to adaptively aggregate background/foreground information from voxelized point clouds. Our method achieves state-of-the-art performance with an extreme masking ratio of nearly 99%. Moreover, to improve multi-category 3D generation, we introduce Mixture-of-Expert (MoE) in 3D diffusion model. Each category can learn a distinct diffusion path with different experts, relieving gradient conflict. Experimental results on the ShapeNet dataset demonstrate that our method achieves state-of-the-art high-fidelity and diverse 3D point cloud generation performance. Our FastDiT-3D improves 1-Nearest Neighbor Accuracy and Coverage metrics when generating 128-resolution voxel point clouds, using only 6.5% of the original training cost.

cs.CV↗

arXiv2023

Unveiling the Power of Audio-Visual Early Fusion Transformers with Dense Interactions through Masked Modeling

Humans possess a remarkable ability to integrate auditory and visual information, enabling a deeper understanding of the surrounding environment. This early fusion of audio and visual cues, demonstrated through cognitive psychology and neuroscience research, offers promising potential for developing multimodal perception models. However, training early fusion architectures poses significant challenges, as the increased model expressivity requires robust learning frameworks to harness their enhanced capabilities. In this paper, we address this challenge by leveraging the masked reconstruction framework, previously successful in unimodal settings, to train audio-visual encoders with early fusion. Additionally, we propose an attention-based fusion module that captures interactions between local audio and visual representations, enhancing the model's ability to capture fine-grained interactions. While effective, this procedure can become computationally intractable, as the number of local representations increases. Thus, to address the computational complexity, we propose an alternative procedure that factorizes the local representations before representing audio-visual interactions. Extensive evaluations on a variety of datasets demonstrate the superiority of our approach in audio-event classification, visual sound localization, sound separation, and audio-visual segmentation. These contributions enable the efficient training of deeply integrated audio-visual models and significantly advance the usefulness of early fusion architectures.

cs.CV↗

arXiv2023

Beyond Accuracy: Statistical Measures and Benchmark for Evaluation of Representation from Self-Supervised Learning

Recently, self-supervised metric learning has raised attention for the potential to learn a generic distance function. It overcomes the limitations of conventional supervised one, e.g., scalability and label biases. Despite progress in this domain, current benchmarks, incorporating a narrow scope of classes, stop the nuanced evaluation of semantic representations. To bridge this gap, we introduce a large-scale benchmark with diversity and granularity of classes, Statistical Metric Learning Benchmark (SMLB) built upon ImageNet-21K and WordNet. SMLB is designed to rigorously evaluate the discriminative discernment and generalizability across more than 14M images, 20K classes, and 16K taxonomic nodes. Alongside, we propose novel evaluation metrics -- `overlap' for separability and `aSTD' for consistency -- to measure distance statistical information, which are efficient and robust to the change of class number. Our benchmark offers a novel perspective of evaluating the quality of representations beyond accuracy. Our findings reveal the limitations of supervised learning and the class bias inherent in SSL models, offering insights into potential areas for future model enhancement.

cs.CV↗

arXiv2023

Linker-Tuning: Optimizing Continuous Prompts for Heterodimeric Protein Prediction

Predicting the structure of interacting chains is crucial for understanding biological systems and developing new drugs. Large-scale pre-trained Protein Language Models (PLMs), such as ESM2, have shown impressive abilities in extracting biologically meaningful representations for protein structure prediction. In this paper, we show that ESMFold, which has been successful in computing accurate atomic structures for single-chain proteins, can be adapted to predict the heterodimer structures in a lightweight manner. We propose Linker-tuning, which learns a continuous prompt to connect the two chains in a dimer before running it as a single sequence in ESMFold. Experiment results show that our method successfully predicts 56.98% of interfaces on the i.i.d. heterodimer test set, with an absolute improvement of +12.79% over the ESMFold-Linker baseline. Furthermore, our model can generalize well to the out-of-distribution (OOD) test set HeteroTest2 and two antibody test sets Fab and Fv while being $9\times$ faster than AF-Multimer.

q-bio.BM↗

arXiv2023

Weakly-Supervised Audio-Visual Segmentation

Audio-visual segmentation is a challenging task that aims to predict pixel-level masks for sound sources in a video. Previous work applied a comprehensive manually designed architecture with countless pixel-wise accurate masks as supervision. However, these pixel-level masks are expensive and not available in all cases. In this work, we aim to simplify the supervision as the instance-level annotation, i.e., weakly-supervised audio-visual segmentation. We present a novel Weakly-Supervised Audio-Visual Segmentation framework, namely WS-AVS, that can learn multi-scale audio-visual alignment with multi-scale multiple-instance contrastive learning for audio-visual segmentation. Extensive experiments on AVSBench demonstrate the effectiveness of our WS-AVS in the weakly-supervised audio-visual segmentation of single-source and multi-source scenarios.

cs.CV↗

arXiv2023

Exploring Data Augmentations on Self-/Semi-/Fully- Supervised Pre-trained Models

Data augmentation has become a standard component of vision pre-trained models to capture the invariance between augmented views. In practice, augmentation techniques that mask regions of a sample with zero/mean values or patches from other samples are commonly employed in pre-trained models with self-/semi-/fully-supervised contrastive losses. However, the underlying mechanism behind the effectiveness of these augmentation techniques remains poorly explored. To investigate the problems, we conduct an empirical study to quantify how data augmentation affects performance. Concretely, we apply 4 types of data augmentations termed with Random Erasing, CutOut, CutMix and MixUp to a series of self-/semi-/fully- supervised pre-trained models. We report their performance on vision tasks such as image classification, object detection, instance segmentation, and semantic segmentation. We then explicitly evaluate the invariance and diversity of the feature embedding. We observe that: 1) Masking regions of the images decreases the invariance of the learned feature embedding while providing a more considerable diversity. 2) Manual annotations do not change the invariance or diversity of the learned feature embedding. 3) The MixUp approach improves the diversity significantly, with only a marginal decrease in terms of the invariance.

cs.CV↗

arXiv2023

Audio-Visual Class-Incremental Learning

In this paper, we introduce audio-visual class-incremental learning, a class-incremental learning scenario for audio-visual video recognition. We demonstrate that joint audio-visual modeling can improve class-incremental learning, but current methods fail to preserve semantic similarity between audio and visual features as incremental step grows. Furthermore, we observe that audio-visual correlations learned in previous tasks can be forgotten as incremental steps progress, leading to poor performance. To overcome these challenges, we propose AV-CIL, which incorporates Dual-Audio-Visual Similarity Constraint (D-AVSC) to maintain both instance-aware and class-aware semantic similarity between audio-visual modalities and Visual Attention Distillation (VAD) to retain previously learned audio-guided visual attentive ability. We create three audio-visual class-incremental datasets, AVE-Class-Incremental (AVE-CI), Kinetics-Sounds-Class-Incremental (K-S-CI), and VGGSound100-Class-Incremental (VS100-CI) based on the AVE, Kinetics-Sounds, and VGGSound datasets, respectively. Our experiments on AVE-CI, K-S-CI, and VS100-CI demonstrate that AV-CIL significantly outperforms existing class-incremental learning methods in audio-visual class-incremental learning. Code and data are available at: https://github.com/weiguoPian/AV-CIL_ICCV2023.

cs.CV↗

arXiv2023

Variantional autoencoder with decremental information bottleneck for disentanglement

One major challenge of disentanglement learning with variational autoencoders is the trade-off between disentanglement and reconstruction fidelity. Previous studies, which increase the information bottleneck during training, tend to lose the constraint of disentanglement, leading to the information diffusion problem. In this paper, we present a novel framework for disentangled representation learning, DeVAE, which utilizes hierarchical latent spaces with decreasing information bottlenecks across these spaces. The key innovation of our approach lies in connecting the hierarchical latent spaces through disentanglement-invariant transformations, allowing the sharing of disentanglement properties among spaces while maintaining an acceptable level of reconstruction performance. We demonstrate the effectiveness of DeVAE in achieving a balance between disentanglement and reconstruction through a series of experiments and ablation studies on dSprites and Shapes3D datasets. Code is available at https://github.com/erow/disentanglement_lib/tree/pytorch#devae.

cs.LG↗

arXiv2023

Tree of Uncertain Thoughts Reasoning for Large Language Models

While the recently introduced Tree of Thoughts (ToT) has heralded advancements in allowing Large Language Models (LLMs) to reason through foresight and backtracking for global decision-making, it has overlooked the inherent local uncertainties in intermediate decision points or "thoughts". These local uncertainties, intrinsic to LLMs given their potential for diverse responses, remain a significant concern in the reasoning process. Addressing this pivotal gap, we introduce the Tree of Uncertain Thoughts (TouT) - a reasoning framework tailored for LLMs. Our TouT effectively leverages Monte Carlo Dropout to quantify uncertainty scores associated with LLMs' diverse local responses at these intermediate steps. By marrying this local uncertainty quantification with global search algorithms, TouT enhances the model's precision in response generation. We substantiate our approach with rigorous experiments on two demanding planning tasks: Game of 24 and Mini Crosswords. The empirical evidence underscores TouT's superiority over both ToT and chain-of-thought prompting methods.

cs.CL↗

arXiv2023

Class-Incremental Grouping Network for Continual Audio-Visual Learning

Continual learning is a challenging problem in which models need to be trained on non-stationary data across sequential tasks for class-incremental learning. While previous methods have focused on using either regularization or rehearsal-based frameworks to alleviate catastrophic forgetting in image classification, they are limited to a single modality and cannot learn compact class-aware cross-modal representations for continual audio-visual learning. To address this gap, we propose a novel class-incremental grouping network (CIGN) that can learn category-wise semantic features to achieve continual audio-visual learning. Our CIGN leverages learnable audio-visual class tokens and audio-visual grouping to continually aggregate class-aware features. Additionally, it utilizes class tokens distillation and continual grouping to prevent forgetting parameters learned from previous tasks, thereby improving the model's ability to capture discriminative audio-visual categories. We conduct extensive experiments on VGGSound-Instruments, VGGSound-100, and VGG-Sound Sources benchmarks. Our experimental results demonstrate that the CIGN achieves state-of-the-art audio-visual class-incremental learning performance. Code is available at https://github.com/stoneMo/CIGN.

cs.CV↗

arXiv2023

Masked Momentum Contrastive Learning for Zero-shot Semantic Understanding

Self-supervised pretraining (SSP) has emerged as a popular technique in machine learning, enabling the extraction of meaningful feature representations without labelled data. In the realm of computer vision, pretrained vision transformers (ViTs) have played a pivotal role in advancing transfer learning. Nonetheless, the escalating cost of finetuning these large models has posed a challenge due to the explosion of model size. This study endeavours to evaluate the effectiveness of pure self-supervised learning (SSL) techniques in computer vision tasks, obviating the need for finetuning, with the intention of emulating human-like capabilities in generalisation and recognition of unseen objects. To this end, we propose an evaluation protocol for zero-shot segmentation based on a prompting patch. Given a point on the target object as a prompt, the algorithm calculates the similarity map between the selected patch and other patches, upon that, a simple thresholding is applied to segment the target. Another evaluation is intra-object and inter-object similarity to gauge discriminatory ability of SSP ViTs. Insights from zero-shot segmentation from prompting and discriminatory abilities of SSP led to the design of a simple SSP approach, termed MMC. This approaches combines Masked image modelling for encouraging similarity of local features, Momentum based self-distillation for transferring semantics from global to local features, and global Contrast for promoting semantics of global features, to enhance discriminative representations of SSP ViTs. Consequently, our proposed method significantly reduces the overlap of intra-object and inter-object similarities, thereby facilitating effective object segmentation within an image. Our experiments reveal that MMC delivers top-tier results in zero-shot semantic segmentation across various datasets.

cs.CV↗

arXiv2023

Context Autoencoder for Self-Supervised Representation Learning

We present a novel masked image modeling (MIM) approach, context autoencoder (CAE), for self-supervised representation pretraining. We pretrain an encoder by making predictions in the encoded representation space. The pretraining tasks include two tasks: masked representation prediction - predict the representations for the masked patches, and masked patch reconstruction - reconstruct the masked patches. The network is an encoder-regressor-decoder architecture: the encoder takes the visible patches as input; the regressor predicts the representations of the masked patches, which are expected to be aligned with the representations computed from the encoder, using the representations of visible patches and the positions of visible and masked patches; the decoder reconstructs the masked patches from the predicted encoded representations. The CAE design encourages the separation of learning the encoder (representation) from completing the pertaining tasks: masked representation prediction and masked patch reconstruction tasks, and making predictions in the encoded representation space empirically shows the benefit to representation learning. We demonstrate the effectiveness of our CAE through superior transfer performance in downstream tasks: semantic segmentation, object detection and instance segmentation, and classification. The code will be available at https://github.com/Atten4Vis/CAE.

cs.CV↗

arXiv2023

DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generation

Recent Diffusion Transformers (e.g., DiT) have demonstrated their powerful effectiveness in generating high-quality 2D images. However, it is still being determined whether the Transformer architecture performs equally well in 3D shape generation, as previous 3D diffusion methods mostly adopted the U-Net architecture. To bridge this gap, we propose a novel Diffusion Transformer for 3D shape generation, namely DiT-3D, which can directly operate the denoising process on voxelized point clouds using plain Transformers. Compared to existing U-Net approaches, our DiT-3D is more scalable in model size and produces much higher quality generations. Specifically, the DiT-3D adopts the design philosophy of DiT but modifies it by incorporating 3D positional and patch embeddings to adaptively aggregate input from voxelized point clouds. To reduce the computational cost of self-attention in 3D shape generation, we incorporate 3D window attention into Transformer blocks, as the increased 3D token length resulting from the additional dimension of voxels can lead to high computation. Finally, linear and devoxelization layers are used to predict the denoised point clouds. In addition, our transformer architecture supports efficient fine-tuning from 2D to 3D, where the pre-trained DiT-2D checkpoint on ImageNet can significantly improve DiT-3D on ShapeNet. Experimental results on the ShapeNet dataset demonstrate that the proposed DiT-3D achieves state-of-the-art performance in high-fidelity and diverse 3D point cloud generation. In particular, our DiT-3D decreases the 1-Nearest Neighbor Accuracy of the state-of-the-art method by 4.59 and increases the Coverage metric by 3.51 when evaluated on Chamfer Distance.

cs.CV↗

arXiv2023

High-Modality Multimodal Transformer: Quantifying Modality & Interaction Heterogeneity for High-Modality Representation Learning

Many real-world problems are inherently multimodal, from spoken language, gestures, and paralinguistics humans use to communicate, to force, proprioception, and visual sensors on robots. While there has been an explosion of interest in multimodal learning, these methods are focused on a small set of modalities primarily in language, vision, and audio. In order to accelerate generalization towards diverse and understudied modalities, this paper studies efficient representation learning for high-modality scenarios involving a large set of diverse modalities. Since adding new models for every new modality becomes prohibitively expensive, a critical technical challenge is heterogeneity quantification: how can we measure which modalities encode similar information and interactions in order to permit parameter sharing with previous modalities? This paper proposes two new information theoretic metrics for heterogeneity quantification: (1) modality heterogeneity studies how similar 2 modalities {X1,X2} are by measuring how much information can be transferred from X1 to X2, while (2) interaction heterogeneity studies how similarly pairs of modalities {X1,X2}, {X3,X4} interact by measuring how much information can be transferred from fusing {X1,X2} to {X3,X4}. We show the importance of these 2 proposed metrics as a way to automatically prioritize the fusion of modalities that contain unique information or interactions. The result is a single model, HighMMT, that scales up to 10 modalities (text, image, audio, video, sensors, proprioception, speech, time-series, sets, and tables) and 15 tasks from 5 research areas. Not only does HighMMT outperform prior methods on the tradeoff between performance and efficiency, it also demonstrates a crucial scaling behavior: performance continues to improve with each modality added, and it transfers to entirely new modalities and tasks during fine-tuning.

cs.LG↗

arXiv2023

DiffComplete: Diffusion-based Generative 3D Shape Completion

We introduce a new diffusion-based approach for shape completion on 3D range scans. Compared with prior deterministic and probabilistic methods, we strike a balance between realism, multi-modality, and high fidelity. We propose DiffComplete by casting shape completion as a generative task conditioned on the incomplete shape. Our key designs are two-fold. First, we devise a hierarchical feature aggregation mechanism to inject conditional features in a spatially-consistent manner. So, we can capture both local details and broader contexts of the conditional inputs to control the shape completion. Second, we propose an occupancy-aware fusion strategy in our model to enable the completion of multiple partial shapes and introduce higher flexibility on the input conditions. DiffComplete sets a new SOTA performance (e.g., 40% decrease on l_1 error) on two large-scale 3D shape completion benchmarks. Our completed shapes not only have a realistic outlook compared with the deterministic methods but also exhibit high similarity to the ground truths compared with the probabilistic alternatives. Further, DiffComplete has strong generalizability on objects of entirely unseen classes for both synthetic and real data, eliminating the need for model re-training in various applications.

cs.CV↗

arXiv2023

A Unified Audio-Visual Learning Framework for Localization, Separation, and Recognition

The ability to accurately recognize, localize and separate sound sources is fundamental to any audio-visual perception task. Historically, these abilities were tackled separately, with several methods developed independently for each task. However, given the interconnected nature of source localization, separation, and recognition, independent models are likely to yield suboptimal performance as they fail to capture the interdependence between these tasks. To address this problem, we propose a unified audio-visual learning framework (dubbed OneAVM) that integrates audio and visual cues for joint localization, separation, and recognition. OneAVM comprises a shared audio-visual encoder and task-specific decoders trained with three objectives. The first objective aligns audio and visual representations through a localized audio-visual correspondence loss. The second tackles visual source separation using a traditional mix-and-separate framework. Finally, the third objective reinforces visual feature separation and localization by mixing images in pixel space and aligning their representations with those of all corresponding sound sources. Extensive experiments on MUSIC, VGG-Instruments, VGG-Music, and VGGSound datasets demonstrate the effectiveness of OneAVM for all three tasks, audio-visual source localization, separation, and nearest neighbor recognition, and empirically demonstrate a strong positive transfer between them.

cs.SD↗

arXiv2023

DiffAVA: Personalized Text-to-Audio Generation with Visual Alignment

Text-to-audio (TTA) generation is a recent popular problem that aims to synthesize general audio given text descriptions. Previous methods utilized latent diffusion models to learn audio embedding in a latent space with text embedding as the condition. However, they ignored the synchronization between audio and visual content in the video, and tended to generate audio mismatching from video frames. In this work, we propose a novel and personalized text-to-sound generation approach with visual alignment based on latent diffusion models, namely DiffAVA, that can simply fine-tune lightweight visual-text alignment modules with frozen modality-specific encoders to update visual-aligned text embeddings as the condition. Specifically, our DiffAVA leverages a multi-head attention transformer to aggregate temporal information from video features, and a dual multi-modal residual network to fuse temporal visual representations with text embeddings. Then, a contrastive learning objective is applied to match visual-aligned text embeddings with audio features. Experimental results on the AudioCaps dataset demonstrate that the proposed DiffAVA can achieve competitive performance on visual-aligned text-to-audio generation.

cs.CV↗

arXiv2023

AV-SAM: Segment Anything Model Meets Audio-Visual Localization and Segmentation

Segment Anything Model (SAM) has recently shown its powerful effectiveness in visual segmentation tasks. However, there is less exploration concerning how SAM works on audio-visual tasks, such as visual sound localization and segmentation. In this work, we propose a simple yet effective audio-visual localization and segmentation framework based on the Segment Anything Model, namely AV-SAM, that can generate sounding object masks corresponding to the audio. Specifically, our AV-SAM simply leverages pixel-wise audio-visual fusion across audio features and visual features from the pre-trained image encoder in SAM to aggregate cross-modal representations. Then, the aggregated cross-modal features are fed into the prompt encoder and mask decoder to generate the final audio-visual segmentation masks. We conduct extensive experiments on Flickr-SoundNet and AVSBench datasets. The results demonstrate that the proposed AV-SAM can achieve competitive performance on sounding object localization and segmentation.

cs.CV↗