Imagining the future trajectory is the key for robots to make sound planning and successfully reach their goals. Therefore, text-conditioned video prediction (TVP) is an essential task to facilitate general robot policy learning. To tackle this task and empower robots with the ability to foresee the future, we propose a sample and computation-efficient model, named \textbf{Seer}, by inflating the pretrained text-to-image (T2I) stable diffusion models along the temporal axis. We enhance the U-Net and language conditioning model by incorporating computation-efficient spatial-temporal attention. Furthermore, we introduce a novel Frame Sequential Text Decomposer module that dissects a sentence's global instruction into temporally aligned sub-instructions, ensuring precise integration into each frame of generation. Our framework allows us to effectively leverage the extensive prior knowledge embedded in pretrained T2I models across the frames. With the adaptable-designed architecture, Seer makes it possible to generate high-fidelity, coherent, and instruction-aligned video frames by fine-tuning a few layers on a small amount of data. The experimental results on Something Something V2 (SSv2), Bridgedata and EpicKitchens-100 datasets demonstrate our superior video prediction performance with around 480-GPU hours versus CogVideo with over 12,480-GPU hours: achieving the 31% FVD improvement compared to the current SOTA model on SSv2 and 83.7% average preference in the human evaluation.
3D Gaussian splatting has achieved very impressive performance in real-time novel view synthesis. However, it often suffers from over-reconstruction during Gaussian densification where high-variance image regions are covered by a few large Gaussians only, leading to blur and artifacts in the rendered images. We design a progressive frequency regularization (FreGS) technique to tackle the over-reconstruction issue within the frequency space. Specifically, FreGS performs coarse-to-fine Gaussian densification by exploiting low-to-high frequency components that can be easily extracted with low-pass and high-pass filters in the Fourier space. By minimizing the discrepancy between the frequency spectrum of the rendered image and the corresponding ground truth, it achieves high-quality Gaussian densification and alleviates the over-reconstruction of Gaussian splatting effectively. Experiments over multiple widely adopted benchmarks (e.g., Mip-NeRF360, Tanks-and-Temples and Deep Blending) show that FreGS achieves superior novel view synthesis and outperforms the state-of-the-art consistently.
Recent research in self-supervised contrastive learning of music representations has demonstrated remarkable results across diverse downstream tasks. However, a prevailing trend in existing methods involves representing equally-sized music clips in either waveform or spectrogram formats, often overlooking the intrinsic part-whole hierarchies within music. In our quest to comprehend the bottom-up structure of music, we introduce MART, a hierarchical music representation learning approach that facilitates feature interactions among cropped music clips while considering their part-whole hierarchies. Specifically, we propose a hierarchical part-whole transformer to capture the structural relationships between music clips in a part-whole hierarchy. Furthermore, a hierarchical contrastive learning objective is crafted to align part-whole music representations at adjacent levels, progressively establishing a multi-hierarchy representation space. The effectiveness of our music representation learning from part-whole hierarchies has been empirically validated across multiple downstream tasks, including music classification and cover song identification.
In this paper, we propose a non-parallel any-to-many voice conversion (VC) method termed VoiceGrad. Inspired by WaveGrad, a recently introduced novel waveform generation method, VoiceGrad is based upon the concepts of score matching and Langevin dynamics. It uses weighted denoising score matching to train a score approximator, a fully convolutional network with a U-Net structure designed to predict the gradient of the log density of the speech feature sequences of multiple speakers, and performs VC by using annealed Langevin dynamics to iteratively update an input feature sequence towards the nearest stationary point of the target distribution based on the trained score approximator network. Thanks to the nature of this concept, VoiceGrad enables any-to-many VC, a VC scenario in which the speaker of input speech can be arbitrary, and allows for non-parallel training, which requires no parallel utterances or transcriptions.
COMpression with Bayesian Implicit NEural Representations (COMBINER) is a recent data compression method that addresses a key inefficiency of previous Implicit Neural Representation (INR)-based approaches: it avoids quantization and enables direct optimization of the rate-distortion performance. However, COMBINER still has significant limitations: 1) it uses factorized priors and posterior approximations that lack flexibility; 2) it cannot effectively adapt to local deviations from global patterns in the data; and 3) its performance can be susceptible to modeling choices and the variational parameters' initializations. Our proposed method, Robust and Enhanced COMBINER (RECOMBINER), addresses these issues by 1) enriching the variational approximation while retaining a low computational cost via a linear reparameterization of the INR weights, 2) augmenting our INRs with learnable positional encodings that enable them to adapt to local details and 3) splitting high-resolution data into patches to increase robustness and utilizing expressive hierarchical priors to capture dependency across patches. We conduct extensive experiments across several data modalities, showcasing that RECOMBINER achieves competitive results with the best INR-based methods and even outperforms autoencoder-based codecs on low-resolution images at low bitrates. Our PyTorch implementation is available at //github.com/cambridge-mlg/RECOMBINER/.
This paper focuses on the challenge of answering questions in scenarios that are composed of rich and complex dynamic audio-visual components. Although existing Multimodal Large Language Models (MLLMs) can respond to audio-visual content, these responses are sometimes ambiguous and fail to describe specific audio-visual events. To overcome this limitation, we introduce the CAT, which enhances MLLM in three ways: 1) besides straightforwardly bridging audio and video, we design a clue aggregator that aggregates question-related clues in dynamic audio-visual scenarios to enrich the detailed knowledge required for large language models. 2) CAT is trained on a mixed multimodal dataset, allowing direct application in audio-visual scenarios. Notably, we collect an audio-visual joint instruction dataset named AVinstruct, to further enhance the capacity of CAT to model cross-semantic correlations. 3) we propose AI-assisted ambiguity-aware direct preference optimization, a strategy specialized in retraining the model to favor the non-ambiguity response and improve the ability to localize specific audio-visual objects. Extensive experimental results demonstrate that CAT outperforms existing methods on multimodal tasks, especially in Audio-Visual Question Answering (AVQA) tasks. The codes and the collected instructions are released at //github.com/rikeilong/Bay-CAT.
Emotional voice conversion (EVC) seeks to modify the emotional tone of a speaker's voice while preserving the original linguistic content and the speaker's unique vocal characteristics. Recent advancements in EVC have involved the simultaneous modeling of pitch and duration, utilizing the potential of sequence-to-sequence (seq2seq) models. To enhance reliability and efficiency in conversion, this study shifts focus towards parallel speech generation. We introduce Duration-Flexible EVC (DurFlex-EVC), which integrates a style autoencoder and unit aligner. Traditional models, while incorporating self-supervised learning (SSL) representations that contain both linguistic and paralinguistic information, have neglected this dual nature, leading to reduced controllability. Addressing this issue, we implement cross-attention to synchronize these representations with various emotions. Additionally, a style autoencoder is developed for the disentanglement and manipulation of style elements. The efficacy of our approach is validated through both subjective and objective evaluations, establishing its superiority over existing models in the field.
Diffusion models (DMs) have shown great potential for high-quality image synthesis. However, when it comes to producing images with complex scenes, how to properly describe both image global structures and object details remains a challenging task. In this paper, we present Frido, a Feature Pyramid Diffusion model performing a multi-scale coarse-to-fine denoising process for image synthesis. Our model decomposes an input image into scale-dependent vector quantized features, followed by a coarse-to-fine gating for producing image output. During the above multi-scale representation learning stage, additional input conditions like text, scene graph, or image layout can be further exploited. Thus, Frido can be also applied for conditional or cross-modality image synthesis. We conduct extensive experiments over various unconditioned and conditional image generation tasks, ranging from text-to-image synthesis, layout-to-image, scene-graph-to-image, to label-to-image. More specifically, we achieved state-of-the-art FID scores on five benchmarks, namely layout-to-image on COCO and OpenImages, scene-graph-to-image on COCO and Visual Genome, and label-to-image on COCO. Code is available at //github.com/davidhalladay/Frido.
In this paper, we introduce a two-level attention schema, Poolingformer, for long document modeling. Its first level uses a smaller sliding window pattern to aggregate information from neighbors. Its second level employs a larger window to increase receptive fields with pooling attention to reduce both computational cost and memory consumption. We first evaluate Poolingformer on two long sequence QA tasks: the monolingual NQ and the multilingual TyDi QA. Experimental results show that Poolingformer sits atop three official leaderboards measured by F1, outperforming previous state-of-the-art models by 1.9 points (79.8 vs. 77.9) on NQ long answer, 1.9 points (79.5 vs. 77.6) on TyDi QA passage answer, and 1.6 points (67.6 vs. 66.0) on TyDi QA minimal answer. We further evaluate Poolingformer on a long sequence summarization task. Experimental results on the arXiv benchmark continue to demonstrate its superior performance.
We present Emu, a system that semantically enhances multilingual sentence embeddings. Our framework fine-tunes pre-trained multilingual sentence embeddings using two main components: a semantic classifier and a language discriminator. The semantic classifier improves the semantic similarity of related sentences, whereas the language discriminator enhances the multilinguality of the embeddings via multilingual adversarial training. Our experimental results based on several language pairs show that our specialized embeddings outperform the state-of-the-art multilingual sentence embedding model on the task of cross-lingual intent classification using only monolingual labeled data.
We propose a novel single shot object detection network named Detection with Enriched Semantics (DES). Our motivation is to enrich the semantics of object detection features within a typical deep detector, by a semantic segmentation branch and a global activation module. The segmentation branch is supervised by weak segmentation ground-truth, i.e., no extra annotation is required. In conjunction with that, we employ a global activation module which learns relationship between channels and object classes in a self-supervised manner. Comprehensive experimental results on both PASCAL VOC and MS COCO detection datasets demonstrate the effectiveness of the proposed method. In particular, with a VGG16 based DES, we achieve an mAP of 81.7 on VOC2007 test and an mAP of 32.8 on COCO test-dev with an inference speed of 31.5 milliseconds per image on a Titan Xp GPU. With a lower resolution version, we achieve an mAP of 79.7 on VOC2007 with an inference speed of 13.0 milliseconds per image.