In the realm of multimodal tasks, Visual Question Answering (VQA) plays a crucial role by addressing natural language questions grounded in visual content. Knowledge-Based Visual Question Answering (KBVQA) advances this concept by adding external knowledge along with images to respond to questions. We introduce an approach for KBVQA, augmenting the existing vision-language transformer encoder-decoder (OFA) model. Our main contribution involves enhancing questions by incorporating relevant external knowledge extracted from knowledge graphs, using a dynamic triple extraction method. We supply a flexible number of triples from the knowledge graph as context, tailored to meet the requirements for answering the question. Our model, enriched with knowledge, demonstrates an average improvement of 4.75\% in Exact Match Score over the state-of-the-art on three different KBVQA datasets. Through experiments and analysis, we demonstrate that furnishing variable triples for each question improves the reasoning capabilities of the language model in contrast to supplying a fixed number of triples. This is illustrated even for recent large language models. Additionally, we highlight the model's generalization capability by showcasing its SOTA-beating performance on a small dataset, achieved through straightforward fine-tuning.
We develop Scalable Latent Exploration Score (ScaLES) to mitigate over-exploration in Latent Space Optimization (LSO), a popular method for solving black-box discrete optimization problems. LSO utilizes continuous optimization within the latent space of a Variational Autoencoder (VAE) and is known to be susceptible to over-exploration, which manifests in unrealistic solutions that reduce its practicality. ScaLES is an exact and theoretically motivated method leveraging the trained decoder's approximation of the data distribution. ScaLES can be calculated with any existing decoder, e.g. from a VAE, without additional training, architectural changes, or access to the training data. Our evaluation across five LSO benchmark tasks and three VAE architectures demonstrates that ScaLES enhances the quality of the solutions while maintaining high objective values, leading to improvements over existing solutions. We believe that new avenues to LSO will be opened by ScaLES ability to identify out of distribution areas, differentiability, and computational tractability. Open source code for ScaLES is available at https://github.com/OmerRonen/scales.
Recurrent neural network-based sequence-to-sequence models have been extensively applied for multi-step-ahead time series forecasting. These models typically involve a decoder trained using either its previous forecasts or the actual observed values as the decoder inputs. However, relying on self-generated predictions can lead to the rapid accumulation of errors over multiple steps, while using the actual observations introduces exposure bias as these values are unavailable during the extrapolation stage. In this regard, this study proposes a novel training approach called reinforced decoder, which introduces auxiliary models to generate alternative decoder inputs that remain accessible when extrapolating. Additionally, a reinforcement learning algorithm is utilized to dynamically select the optimal inputs to improve accuracy. Comprehensive experiments demonstrate that our approach outperforms representative training methods over several datasets. Furthermore, the proposed approach also exhibits promising performance when generalized to self-attention-based sequence-to-sequence forecasting models.
Audio-Visual Speech Recognition (AVSR) uses lip-based video to improve performance in noise. Since videos are harder to obtain than audio, the video training data of AVSR models is usually limited to a few thousand hours. In contrast, speech models such as Whisper are trained with hundreds of thousands of hours of data, and thus learn a better speech-to-text decoder. The huge training data difference motivates us to adapt Whisper to handle video inputs. Inspired by Flamingo which injects visual features into language models, we propose Whisper-Flamingo which integrates visual features into the Whisper speech recognition and translation model with gated cross attention. Our models achieve state-of-the-art ASR WER (0.68%) and AVSR WER (0.76%) on LRS3, and state-of-the-art ASR WER (1.3%) and AVSR WER (1.4%) on LRS2. Audio-visual Whisper-Flamingo outperforms audio-only Whisper on English speech recognition and En-X translation for 6 languages in noisy conditions. Moreover, Whisper-Flamingo is versatile and conducts all of these tasks using one set of parameters, while prior methods are trained separately on each language.
Depth images have a wide range of applications, such as 3D reconstruction, autonomous driving, augmented reality, robot navigation, and scene understanding. Commodity-grade depth cameras are hard to sense depth for bright, glossy, transparent, and distant surfaces. Although existing depth completion methods have achieved remarkable progress, their performance is limited when applied to complex indoor scenarios. To address these problems, we propose a two-step Transformer-based network for indoor depth completion. Unlike existing depth completion approaches, we adopt a self-supervision pre-training encoder based on the masked autoencoder to learn an effective latent representation for the missing depth value; then we propose a decoder based on a token fusion mechanism to complete (i.e., reconstruct) the full depth from the jointly RGB and incomplete depth image. Compared to the existing methods, our proposed network, achieves the state-of-the-art performance on the Matterport3D dataset. In addition, to validate the importance of the depth completion task, we apply our methods to indoor 3D reconstruction. The code, dataset, and demo are available at https://github.com/kailaisun/Indoor-Depth-Completion.
Recently, 3D assets created via reconstruction and generation have matched the quality of manually crafted assets, highlighting their potential for replacement. However, this potential is largely unrealized because these assets always need to be converted to meshes for 3D industry applications, and the meshes produced by current mesh extraction methods are significantly inferior to Artist-Created Meshes (AMs), i.e., meshes created by human artists. Specifically, current mesh extraction methods rely on dense faces and ignore geometric features, leading to inefficiencies, complicated post-processing, and lower representation quality. To address these issues, we introduce MeshAnything, a model that treats mesh extraction as a generation problem, producing AMs aligned with specified shapes. By converting 3D assets in any 3D representation into AMs, MeshAnything can be integrated with various 3D asset production methods, thereby enhancing their application across the 3D industry. The architecture of MeshAnything comprises a VQ-VAE and a shape-conditioned decoder-only transformer. We first learn a mesh vocabulary using the VQ-VAE, then train the shape-conditioned decoder-only transformer on this vocabulary for shape-conditioned autoregressive mesh generation. Our extensive experiments show that our method generates AMs with hundreds of times fewer faces, significantly improving storage, rendering, and simulation efficiencies, while achieving precision comparable to previous methods.
This paper proposes a novel non-autoregressive (NAR) block-based Attention Mask Decoder (AMD) that flexibly balances performance-efficiency trade-offs for Conformer ASR systems. AMD performs parallel NAR inference within contiguous blocks of output labels that are concealed using attention masks, while conducting left-to-right AR prediction and history context amalgamation between blocks. A beam search algorithm is designed to leverage a dynamic fusion of CTC, AR Decoder, and AMD probabilities. Experiments on the LibriSpeech-100hr corpus suggest the tripartite Decoder incorporating the AMD module produces a maximum decoding speed-up ratio of 1.73x over the baseline CTC+AR decoding, while incurring no statistically significant word error rate (WER) increase on the test sets. When operating with the same decoding real time factors, statistically significant WER reductions of up to 0.7% and 0.3% absolute (5.3% and 6.1% relative) were obtained over the CTC+AR baseline.
A methodology based on deep recurrent models for maritime surveillance, over publicly available Automatic Identification System (AIS) data, is presented in this paper. The setup employs a deep Recurrent Neural Network (RNN)-based model, for encoding and reconstructing the observed ships' motion patterns. Our approach is based on a thresholding mechanism, over the calculated errors between observed and reconstructed motion patterns of maritime vessels. Specifically, a deep-learning framework, i.e. an encoder-decoder architecture, is trained using the observed motion patterns, enabling the models to learn and predict the expected trajectory, which will be compared to the effective ones. Our models, particularly the bidirectional GRU with recurrent dropouts, showcased superior performance in capturing the temporal dynamics of maritime data, illustrating the potential of deep learning to enhance maritime surveillance capabilities. Our work lays a solid foundation for future research in this domain, highlighting a path toward improved maritime safety through the innovative application of technology.
Open-vocabulary semantic segmentation is a challenging task, which requires the model to output semantic masks of an image beyond a close-set vocabulary. Although many efforts have been made to utilize powerful CLIP models to accomplish this task, they are still easily overfitting to training classes due to the natural gaps in semantic information between training and new classes. To overcome this challenge, we propose a novel framework for openvocabulary semantic segmentation called EBSeg, incorporating an Adaptively Balanced Decoder (AdaB Decoder) and a Semantic Structure Consistency loss (SSC Loss). The AdaB Decoder is designed to generate different image embeddings for both training and new classes. Subsequently, these two types of embeddings are adaptively balanced to fully exploit their ability to recognize training classes and generalization ability for new classes. To learn a consistent semantic structure from CLIP, the SSC Loss aligns the inter-classes affinity in the image feature space with that in the text feature space of CLIP, thereby improving the generalization ability of our model. Furthermore, we employ a frozen SAM image encoder to complement the spatial information that CLIP features lack due to the low training image resolution and image-level supervision inherent in CLIP. Extensive experiments conducted across various benchmarks demonstrate that the proposed EBSeg outperforms the state-of-the-art methods. Our code and trained models will be here: https://github.com/slonetime/EBSeg.
Streaming voice conversion has become increasingly popular for its potential in real-time applications. The recently proposed DualVC 2 has achieved robust and high-quality streaming voice conversion with a latency of about 180ms. Nonetheless, the recognition-synthesis framework hinders end-to-end optimization, and the instability of automatic speech recognition (ASR) model with short chunks makes it challenging to further reduce latency. To address these issues, we propose an end-to-end model, DualVC 3. With speaker-independent semantic tokens to guide the training of the content encoder, the dependency on ASR is removed and the model can operate under extremely small chunks, with cascading errors eliminated. A language model is trained on the content encoder output to produce pseudo context by iteratively predicting future frames, providing more contextual information for the decoder to improve conversion quality. Experimental results demonstrate that DualVC 3 achieves comparable performance to DualVC 2 in subjective and objective metrics, with a latency of only 50 ms.
In recent years, Large Language Models (LLMs) have demonstrated exceptional proficiency across a broad spectrum of Natural Language Processing (NLP) tasks, including Machine Translation. However, previous methods predominantly relied on iterative processes such as instruction fine-tuning or continual pre-training, leaving unexplored the challenges of training LLMs solely on parallel data. In this work, we introduce PLUME (Parallel Language Model), a collection of three 2B LLMs featuring varying vocabulary sizes (32k, 128k, and 256k) trained exclusively on Catalan-centric parallel examples. These models perform comparably to previous encoder-decoder architectures on 16 supervised translation directions and 56 zero-shot ones. Utilizing this set of models, we conduct a thorough investigation into the translation capabilities of LLMs, probing their performance, the impact of the different elements of the prompt, and their cross-lingual representation space.
Data-to-Text Generation (D2T), a classic natural language generation problem, aims at producing fluent descriptions for structured input data, such as a table. Existing D2T works mainly focus on describing the superficial associative relations among entities, while ignoring the deep comparative logical relations, such as A is better than B in a certain aspect with a corresponding opinion, which is quite common in our daily life. In this paper, we introduce a new D2T task named comparative logical relation generation (CLRG). Additionally, we propose a Comparative Logic (CoLo) based text generation method, which generates texts following specific comparative logical relations with contrastive learning. Specifically, we first construct various positive and negative samples by fine-grained perturbations in entities, aspects and opinions. Then, we perform contrastive learning in the encoder layer to have a better understanding of the comparative logical relations, and integrate it in the decoder layer to guide the model to correctly generate the relations. Noting the data scarcity problem, we construct a Chinese Comparative Logical Relation Dataset (CLRD), which is a high-quality human-annotated dataset and challenging for text generation with descriptions of multiple entities and annotations on their comparative logical relations. Extensive experiments show that our method achieves impressive performance in both automatic and human evaluations.
Speaker anonymization aims to conceal cues to speaker identity while preserving linguistic content. Current machine learning based approaches require substantial computational resources, hindering real-time streaming applications. To address these concerns, we propose a streaming model that achieves speaker anonymization with low latency. The system is trained in an end-to-end autoencoder fashion using a lightweight content encoder that extracts HuBERT-like information, a pretrained speaker encoder that extract speaker identity, and a variance encoder that injects pitch and energy information. These three disentangled representations are fed to a decoder that re-synthesizes the speech signal. We present evaluation results from two implementations of our system, a full model that achieves a latency of 230ms, and a lite version (0.1x in size) that further reduces latency to 66ms while maintaining state-of-the-art performance in naturalness, intelligibility, and privacy preservation.
Object-centric learning (OCL) extracts the representation of objects with slots, offering an exceptional blend of flexibility and interpretability for abstracting low-level perceptual features. A widely adopted method within OCL is slot attention, which utilizes attention mechanisms to iteratively refine slot representations. However, a major drawback of most object-centric models, including slot attention, is their reliance on predefining the number of slots. This not only necessitates prior knowledge of the dataset but also overlooks the inherent variability in the number of objects present in each instance. To overcome this fundamental limitation, we present a novel complexity-aware object auto-encoder framework. Within this framework, we introduce an adaptive slot attention (AdaSlot) mechanism that dynamically determines the optimal number of slots based on the content of the data. This is achieved by proposing a discrete slot sampling module that is responsible for selecting an appropriate number of slots from a candidate list. Furthermore, we introduce a masked slot decoder that suppresses unselected slots during the decoding process. Our framework, tested extensively on object discovery tasks with various datasets, shows performance matching or exceeding top fixed-slot models. Moreover, our analysis substantiates that our method exhibits the capability to dynamically adapt the slot number according to each instance's complexity, offering the potential for further exploration in slot attention research. Project will be available at https://kfan21.github.io/AdaSlot/
In this letter, we design a federated contrastive learning (FedCL) framework aimed at supporting personalized semantic communication. Our FedCL enables collaborative training of local semantic encoders across multiple clients and a global semantic decoder owned by the base station. This framework supports heterogeneous semantic encoders since it does not require client-side model aggregation. Furthermore, to tackle the semantic imbalance issue arising from heterogeneous datasets across distributed clients, we employ contrastive learning to train a semantic centroid generator (SCG). This generator obtains representative global semantic centroids that exhibit intra-semantic compactness and inter-semantic separability. Consequently, it provides superior supervision for learning discriminative local semantic features. Additionally, we conduct theoretical analysis to quantify the convergence performance of FedCL. Simulation results verify the superiority of the proposed FedCL framework compared to other distributed learning benchmarks in terms of task performance and robustness under different numbers of clients and channel conditions, especially in low signal-to-noise ratio and highly heterogeneous data scenarios.
Despite the recent progress in enhancing the efficacy of image deblurring, the limited decoding capability constrains the upper limit of State-Of-The-Art (SOTA) methods. This paper proposes a pioneering work, Adaptive Patch Exiting Reversible Decoder (AdaRevD), to explore their insufficient decoding capability. By inheriting the weights of the well-trained encoder, we refactor a reversible decoder which scales up the single-decoder training to multi-decoder training while remaining GPU memory-friendly. Meanwhile, we show that our reversible structure gradually disentangles high-level degradation degree and low-level blur pattern (residual of the blur image and its sharp counterpart) from compact degradation representation. Besides, due to the spatially-variant motion blur kernels, different blur patches have various deblurring difficulties. We further introduce a classifier to learn the degradation degree of image patches, enabling them to exit at different sub-decoders for speedup. Experiments show that our AdaRevD pushes the limit of image deblurring, e.g., achieving 34.60 dB in PSNR on GoPro dataset.
The traditional ingle-scale U-Net often leads to the loss of spatial information during deblurring, which affects the deblurring accracy. Additionally, due to the convolutional method's limitation in capturing long-range dependencies, the quality of the recovered image is degraded. To address the above problems, an asymmetric multiple scales U-net based on self-attention (AMSA-UNet) is proposed to improve the accuracy and computational complexity. By introducing a multiple-scales U shape architecture, the network can focus on blurry regions at the global level and better recover image details at the local level. In order to overcome the limitations of traditional convolutional methods in capturing the long-range dependencies of information, a self-attention mechanism is introduced into the decoder part of the backbone network, which significantly increases the model's receptive field, enabling it to pay more attention to semantic information of the image, thereby producing more accurate and visually pleasing deblurred images. What's more, a frequency domain-based computation method was introduced to reduces the computation amount. The experimental results demonstrate that the proposed method exhibits significant improvements in both accuracy and speed compared to eight excellent methods
Self-supervised monocular depth estimation aims to infer depth information without relying on labeled data. However, the lack of labeled information poses a significant challenge to the model's representation, limiting its ability to capture the intricate details of the scene accurately. Prior information can potentially mitigate this issue, enhancing the model's understanding of scene structure and texture. Nevertheless, solely relying on a single type of prior information often falls short when dealing with complex scenes, necessitating improvements in generalization performance. To address these challenges, we introduce a novel self-supervised monocular depth estimation model that leverages multiple priors to bolster representation capabilities across spatial, context, and semantic dimensions. Specifically, we employ a hybrid transformer and a lightweight pose network to obtain long-range spatial priors in the spatial dimension. Then, the context prior attention is designed to improve generalization, particularly in complex structures or untextured areas. In addition, semantic priors are introduced by leveraging semantic boundary loss, and semantic prior attention is supplemented, further refining the semantic features extracted by the decoder. Experiments on three diverse datasets demonstrate the effectiveness of the proposed model. It integrates multiple priors to comprehensively enhance the representation ability, improving the accuracy and reliability of depth estimation. Codes are available at: \url{https://github.com/MVME-HBUT/MPRLNet}
Breast cancer is a major global health concern. Pathologists face challenges in analyzing complex features from pathological images, which is a time-consuming and labor-intensive task. Therefore, efficient computer-based diagnostic tools are needed for early detection and treatment planning. This paper presents a modified version of MultiResU-Net for histopathology image segmentation, which is selected as the backbone for its ability to analyze and segment complex features at multiple scales and ensure effective feature flow via skip connections. The modified version also utilizes the Gaussian distribution-based Attention Module (GdAM) to incorporate histopathology-relevant text information in a Gaussian distribution. The sampled features from the Gaussian text feature-guided distribution highlight specific spatial regions based on prior knowledge. Finally, using the Controlled Dense Residual Block (CDRB) on skip connections of MultiResU-Net, the information is transferred from the encoder layers to the decoder layers in a controlled manner using a scaling parameter derived from the extracted spatial features. We validate our approach on two diverse breast cancer histopathology image datasets: TNBC and MonuSeg, demonstrating superior segmentation performance compared to state-of-the-art methods. The code for our proposed model is available on https://github.com/AyushRoy2001/GRU-Net.
Understanding representation transfer in multilingual neural machine translation can reveal the representational issue causing the zero-shot translation deficiency. In this work, we introduce the identity pair, a sentence translated into itself, to address the lack of the base measure in multilingual investigations, as the identity pair represents the optimal state of representation among any language transfers. In our analysis, we demonstrate that the encoder transfers the source language to the representational subspace of the target language instead of the language-agnostic state. Thus, the zero-shot translation deficiency arises because representations are entangled with other languages and are not transferred effectively to the target language. Based on our findings, we propose two methods: 1) low-rank language-specific embedding at the encoder, and 2) language-specific contrastive learning of the representation at the decoder. The experimental results on Europarl-15, TED-19, and OPUS-100 datasets show that our methods substantially enhance the performance of zero-shot translations by improving language transfer capacity, thereby providing practical evidence to support our conclusions.