arXiv subjects

Tomohiro Tanaka

Publications and source records attributed to Tomohiro Tanaka.

At least 19 recordsLinked to original sources

arXiv2026

MV2GF: Multi-view Pedestrian Detection with a Visual Geometric Foundation Model

Multi-View Pedestrian Detection (MVPD) aims to detect pedestrians in the form of a bird's eye view map from multi-view images. Recent MVPD methods adopt a unified framework that projects 2D image features into a 3D world space and aggregates them into a single feature. Although they are effective, they struggle to generalize to unseen camera configurations during training due to two main issues. First, they are difficult to capture accurate visual geometry across views in unseen camera configurations. Second, they make detection models highly dependent on distortion patterns during training arising from their image feature projection. To address these, we leverage a visual geometric foundation model and propose MV2GF. This foundation model has exhibited strong generalization in capturing visual geometry across views and predicting accurate 3D attributes in diverse camera configurations. MV2GF fuses task-specific features with general-purpose geometric features extracted by the foundation model to effectively capture the visual geometry even in unseen camera configurations. Furthermore, MV2GF projects each pixel in the image features to an appropriate 3D location using 3D pointmaps predicted by the foundation model, preventing the detection model from depending on distortion patterns during training. Our experiments demonstrate the effectiveness of leveraging a visual geometric foundation model for MVPD and that MV2GF generalizes better than existing methods.

cs.CV↗

arXiv2026

Nonexchangeable logit dynamics with cost constraints: different viewpoints and numerical analysis

The logit dynamic, a nonlinear dynamical system, subject to a const constraint with heterogeneous agents is formulated, and its well-posedness is studied from both agent-based (stochastic differential equation: SDE) and probabilistic (Fokker-Planck equation: FPE) viewpoints. The state space of agent actions is a compact domain in a finite-dimensional Euclidean space. The SDE is of the McKean-Vlasov type and is driven by jumps with finite variations, whereas the FPE is a nonlinear integro-differential equation. A key to our mathematical analysis of the FPE is adding a regularization factor into the cost constraint to mitigate the blow-up of the logit function. This property carries over to the McKean-Vlasov SDE. We also present a numerical method based on a na\"ive finite difference discretization for computing the FPE along with demonstrative computational examples, showing that the regularization method does not critically affect numerical solutions while preventing the breakdown of numerical computation. Finally, we conduct another demonstrative application study in which environmental, energy, and fishery resources intersect.

math.DS↗

arXiv2026

Resonant two-cluster scattering in a quasi-one-dimensional Bose gas

We investigate two-cluster scattering in a quasi-one-dimensional Bose gas. We focus on the effective three-body interaction induced by transverse confinement, which is the leading term for breaking integrability in the quasi-one-dimensional setting. Exploiting the L\"uscher formula and the integrability of the Lieb-Liniger Bose gas, we find a finite and positive scattering length for elastic two-cluster scattering. The resulting scattering lengths indicate the emergence of a resonance.

cond-mat.quant-gas↗

arXiv2026

Constant Rate Scheduling: A General Framework for Optimizing Diffusion Noise Schedule via Distributional Change

We propose a general framework for optimizing noise schedules in diffusion models, applicable to both training and sampling. Our method enforces a constant rate of change in the probability distribution of diffused data throughout the diffusion process, where the rate of change is quantified using a user-defined discrepancy measure. We introduce three such measures, which can be flexibly selected or combined depending on the domain and model architecture. While our framework is inspired by theoretical insights, we do not aim to provide a complete theoretical justification of how distributional change affects sample quality. Instead, we focus on establishing a general-purpose scheduling framework and validating its empirical effectiveness. Through extensive experiments, we demonstrate that our approach consistently improves the performance of both pixel-space and latent-space diffusion models, across various datasets, samplers, and a wide range of number of function evaluations from 5 to 250. In particular, when applied to both training and sampling schedules, our method achieves a state-of-the-art FID score of 2.03 on LSUN Horse 256$\times$256, without compromising mode coverage.

cs.CV↗

arXiv2025

All-in-One ASR: Unifying Encoder-Decoder Models of CTC, Attention, and Transducer in Dual-Mode ASR

This paper proposes a unified framework, All-in-One ASR, that allows a single model to support multiple automatic speech recognition (ASR) paradigms, including connectionist temporal classification (CTC), attention-based encoder-decoder (AED), and Transducer, in both offline and streaming modes. While each ASR architecture offers distinct advantages and trade-offs depending on the application, maintaining separate models for each scenario incurs substantial development and deployment costs. To address this issue, we introduce a multi-mode joiner that enables seamless integration of various ASR modes within a single unified model. Experiments show that All-in-One ASR significantly reduces the total model footprint while matching or even surpassing the recognition performance of individually optimized ASR models. Furthermore, joint decoding leverages the complementary strengths of different ASR modes, yielding additional improvements in recognition accuracy.

eess.AS↗

arXiv2025

Difference Vector Equalization for Robust Fine-tuning of Vision-Language Models

Contrastive pre-trained vision-language models, such as CLIP, demonstrate strong generalization abilities in zero-shot classification by leveraging embeddings extracted from image and text encoders. This paper aims to robustly fine-tune these vision-language models on in-distribution (ID) data without compromising their generalization abilities in out-of-distribution (OOD) and zero-shot settings. Current robust fine-tuning methods tackle this challenge by reusing contrastive learning, which was used in pre-training, for fine-tuning. However, we found that these methods distort the geometric structure of the embeddings, which plays a crucial role in the generalization of vision-language models, resulting in limited OOD and zero-shot performance. To address this, we propose Difference Vector Equalization (DiVE), which preserves the geometric structure during fine-tuning. The idea behind DiVE is to constrain difference vectors, each of which is obtained by subtracting the embeddings extracted from the pre-trained and fine-tuning models for the same data sample. By constraining the difference vectors to be equal across various data samples, we effectively preserve the geometric structure. Therefore, we introduce two losses: average vector loss (AVL) and pairwise vector loss (PVL). AVL preserves the geometric structure globally by constraining difference vectors to be equal to their weighted average. PVL preserves the geometric structure locally by ensuring a consistent multimodal alignment. Our experiments demonstrate that DiVE effectively preserves the geometric structure, achieving strong results across ID, OOD, and zero-shot metrics.

cs.CV↗

arXiv2025

Joint Modeling of Big Five and HEXACO for Multimodal Apparent Personality-trait Recognition

This paper proposes a joint modeling method of the Big Five, which has long been studied, and HEXACO, which has recently attracted attention in psychology, for automatically recognizing apparent personality traits from multimodal human behavior. Most previous studies have used the Big Five for multimodal apparent personality-trait recognition. However, no study has focused on apparent HEXACO which can evaluate an Honesty-Humility trait related to displaced aggression and vengefulness, social-dominance orientation, etc. In addition, the relationships between the Big Five and HEXACO when modeled by machine learning have not been clarified. We expect awareness of multimodal human behavior to improve by considering these relationships. The key advance of our proposed method is to optimize jointly recognizing the Big Five and HEXACO. Experiments using a self-introduction video dataset demonstrate that the proposed method can effectively recognize the Big Five and HEXACO.

cs.CV↗

arXiv2025

Automated flood detection from Sentinel-1 GRD time series using Bayesian analysis for change point problems

Current Synthetic Aperture Radar (SAR)-based flood detection methods face critical limitations that hinder operational deployment. Supervised learning approaches require extensive labeled training data, exhibit poor geographical transferability, and may fail to adapt to new regions without additional training examples. Existing approaches do not fully exploit the rich temporal information available in SAR time series, instead relying on simple change detection between pre- and post-flood images or supplementary datasets that often introduce error propagation. These limitations prevent effective automated flood monitoring in data-scarce regions where disaster response is most needed. To address these limitations, we develop a novel training-free approach by adapting Bayesian analysis for change point problems, specifically for automated flood detection from Sentinel-1 Ground Range Detected time series data. Our method statistically models the temporal behavior of SAR backscatter intensity over a one-year baseline period, then computes the posterior probability of change points at flood observation dates. This approach eliminates supervised learning dependencies by using Bayesian inference to identify when backscatter deviations exceed expected normal variations, leveraging inherent statistical properties of time series data. Validation across three diverse geographical contexts using the UrbanSARFloods benchmark dataset demonstrates superior performance compared to conventional thresholding and deep learning approaches, achieving F1 scores up to 0.75. This enables immediate deployment to any region with SAR coverage, providing critical advantages for disaster response.

stat.AP↗

arXiv2025

Sensor-Adaptive Flood Mapping with Pre-trained Multi-Modal Transformers across SAR and Multispectral Modalities

Floods are increasingly frequent natural disasters causing extensive human and economic damage, highlighting the critical need for rapid and accurate flood inundation mapping. While remote sensing technologies have advanced flood monitoring capabilities, operational challenges persist: single-sensor approaches face weather-dependent data availability and limited revisit periods, while multi-sensor fusion methods require substantial computational resources and large-scale labeled datasets. To address these limitations, this study introduces a novel sensor-flexible flood detection methodology by fine-tuning Presto, a lightweight ($\sim$0.4M parameters) multi-modal pre-trained transformer that processes both Synthetic Aperture Radar (SAR) and multispectral (MS) data at the pixel level. Our approach uniquely enables flood mapping using SAR-only, MS-only, or combined SAR+MS inputs through a single model architecture, addressing the critical operational need for rapid response with whatever sensor data becomes available first during disasters. We evaluated our method on the Sen1Floods11 dataset against the large-scale Prithvi-100M baseline ($\sim$100M parameters) across three realistic data availability scenarios. The proposed model achieved superior performance with an F1 score of 0.896 and mIoU of 0.886 in the optimal sensor-fusion scenario, outperforming the established baseline. Crucially, the model demonstrated robustness by maintaining effective performance in MS-only scenarios (F1: 0.893) and functional capabilities in challenging SAR-only conditions (F1: 0.718), confirming the advantage of multi-modal pre-training for operational flood mapping. Our parameter-efficient, sensor-flexible approach offers an accessible and robust solution for real-world disaster scenarios requiring immediate flood extent assessment regardless of sensor availability constraints.

cs.CV↗

arXiv2025

Few-shot Personalization via In-Context Learning for Speech Emotion Recognition based on Speech-Language Model

This paper proposes a personalization method for speech emotion recognition (SER) through in-context learning (ICL). Since the expression of emotions varies from person to person, speaker-specific adaptation is crucial for improving the SER performance. Conventional SER methods have been personalized using emotional utterances of a target speaker, but it is often difficult to prepare utterances corresponding to all emotion labels in advance. Our idea to overcome this difficulty is to obtain speaker characteristics by conditioning a few emotional utterances of the target speaker in ICL-based inference. ICL is a method to perform unseen tasks by conditioning a few input-output examples through inference in large language models (LLMs). We meta-train a speech-language model extended from the LLM to learn how to perform personalized SER via ICL. Experimental results using our newly collected SER dataset demonstrate that the proposed method outperforms conventional methods.

eess.AS↗

arXiv2025

MSMVD: Exploiting Multi-scale Image Features via Multi-scale BEV Features for Multi-view Pedestrian Detection

Multi-View Pedestrian Detection (MVPD) aims to detect pedestrians in the form of a bird's eye view (BEV) from multi-view images. In MVPD, end-to-end trainable deep learning methods have progressed greatly. However, they often struggle to detect pedestrians with consistently small or large scales in views or with vastly different scales between views. This is because they do not exploit multi-scale image features to generate the BEV feature and detect pedestrians. To overcome this problem, we propose a novel MVPD method, called Multi-Scale Multi-View Detection (MSMVD). MSMVD generates multi-scale BEV features by projecting multi-scale image features extracted from individual views into the BEV space, scale-by-scale. Each of these BEV features inherits the properties of its corresponding scale image features from multiple views. Therefore, these BEV features help the precise detection of pedestrians with consistently small or large scales in views. Then, MSMVD combines information at different scales of multiple views by processing the multi-scale BEV features using a feature pyramid network. This improves the detection of pedestrians with vastly different scales between views. Extensive experiments demonstrate that exploiting multi-scale image features via multi-scale BEV features greatly improves the detection performance, and MSMVD outperforms the previous highest MODA by $4.5$ points on the GMVD dataset.

cs.CV↗

arXiv2024

SpeechGLUE: How Well Can Self-Supervised Speech Models Capture Linguistic Knowledge?

Self-supervised learning (SSL) for speech representation has been successfully applied in various downstream tasks, such as speech and speaker recognition. More recently, speech SSL models have also been shown to be beneficial in advancing spoken language understanding tasks, implying that the SSL models have the potential to learn not only acoustic but also linguistic information. In this paper, we aim to clarify if speech SSL techniques can well capture linguistic knowledge. For this purpose, we introduce SpeechGLUE, a speech version of the General Language Understanding Evaluation (GLUE) benchmark. Since GLUE comprises a variety of natural language understanding tasks, SpeechGLUE can elucidate the degree of linguistic ability of speech SSL models. Experiments demonstrate that speech SSL models, although inferior to text-based SSL models, perform better than baselines, suggesting that they can acquire a certain amount of general linguistic knowledge from just unlabeled speech data.

cs.CL↗

arXiv2024

Exploring Limits of Diffusion-Synthetic Training with Weakly Supervised Semantic Segmentation

The advance of generative models for images has inspired various training techniques for image recognition utilizing synthetic images. In semantic segmentation, one promising approach is extracting pseudo-masks from attention maps in text-to-image diffusion models, which enables real-image-and-annotation-free training. However, the pioneering training method using the diffusion-synthetic images and pseudo-masks, i.e., DiffuMask has limitations in terms of mask quality, scalability, and ranges of applicable domains. To overcome these limitations, this work introduces three techniques for diffusion-synthetic semantic segmentation training. First, reliability-aware robust training, originally used in weakly supervised learning, helps segmentation with insufficient synthetic mask quality. %Second, large-scale pretraining of whole segmentation models, not only backbones, on synthetic ImageNet-1k-class images with pixel-labels benefits downstream segmentation tasks. Second, we introduce prompt augmentation, data augmentation to the prompt text set to scale up and diversify training images with a limited text resources. Finally, LoRA-based adaptation of Stable Diffusion enables the transfer to a distant domain, e.g., auto-driving images. Experiments in PASCAL VOC, ImageNet-S, and Cityscapes show that our method effectively closes gap between real and synthetic training in semantic segmentation.

cs.CV↗

arXiv2023

Transfer Learning from Pre-trained Language Models Improves End-to-End Speech Summarization

End-to-end speech summarization (E2E SSum) directly summarizes input speech into easy-to-read short sentences with a single model. This approach is promising because it, in contrast to the conventional cascade approach, can utilize full acoustical information and mitigate to the propagation of transcription errors. However, due to the high cost of collecting speech-summary pairs, an E2E SSum model tends to suffer from training data scarcity and output unnatural sentences. To overcome this drawback, we propose for the first time to integrate a pre-trained language model (LM), which is highly capable of generating natural sentences, into the E2E SSum decoder via transfer learning. In addition, to reduce the gap between the independently pre-trained encoder and decoder, we also propose to transfer the baseline E2E SSum encoder instead of the commonly used automatic speech recognition encoder. Experimental results show that the proposed model outperforms baseline and data augmented models.

cs.CL↗

arXiv2023

End-to-End Joint Target and Non-Target Speakers ASR

This paper proposes a novel automatic speech recognition (ASR) system that can transcribe individual speaker's speech while identifying whether they are target or non-target speakers from multi-talker overlapped speech. Target-speaker ASR systems are a promising way to only transcribe a target speaker's speech by enrolling the target speaker's information. However, in conversational ASR applications, transcribing both the target speaker's speech and non-target speakers' ones is often required to understand interactive information. To naturally consider both target and non-target speakers in a single ASR model, our idea is to extend autoregressive modeling-based multi-talker ASR systems to utilize the enrollment speech of the target speaker. Our proposed ASR is performed by recursively generating both textual tokens and tokens that represent target or non-target speakers. Our experiments demonstrate the effectiveness of our proposed method.

cs.CL↗

arXiv2023

Improving Scheduled Sampling for Neural Transducer-based ASR

The recurrent neural network-transducer (RNNT) is a promising approach for automatic speech recognition (ASR) with the introduction of a prediction network that autoregressively considers linguistic aspects. To train the autoregressive part, the ground-truth tokens are used as substitutions for the previous output token, which leads to insufficient robustness to incorrect past tokens; a recognition error in the decoding leads to further errors. Scheduled sampling (SS) is a technique to train autoregressive model robustly to past errors by randomly replacing some ground-truth tokens with actual outputs generated from a model. SS mitigates the gaps between training and decoding steps, known as exposure bias, and it is often used for attentional encoder-decoder training. However SS has not been fully examined for RNNT because of the difficulty in applying SS to RNNT due to the complicated RNNT output form. In this paper we propose SS approaches suited for RNNT. Our SS approaches sample the tokens generated from the distiribution of RNNT itself, i.e. internal language model or RNNT outputs. Experiments in three datasets confirm that RNNT trained with our SS approach achieves the best ASR performance. In particular, on a Japanese ASR task, our best system outperforms the previous state-of-the-art alternative.

eess.AS↗

arXiv2023

Knowledge Distillation for Neural Transducer-based Target-Speaker ASR: Exploiting Parallel Mixture/Single-Talker Speech Data

Neural transducer (RNNT)-based target-speaker speech recognition (TS-RNNT) directly transcribes a target speaker's voice from a multi-talker mixture. It is a promising approach for streaming applications because it does not incur the extra computation costs of a target speech extraction frontend, which is a critical barrier to quick response. TS-RNNT is trained end-to-end given the input speech (i.e., mixtures and enrollment speech) and reference transcriptions. The training mixtures are generally simulated by mixing single-talker signals, but conventional TS-RNNT training does not utilize single-speaker signals. This paper proposes using knowledge distillation (KD) to exploit the parallel mixture/single-talker speech data. Our proposed KD scheme uses an RNNT system pretrained with the target single-talker speech input to generate pseudo labels for the TS-RNNT training. Experimental results show that TS-RNNT systems trained with the proposed KD scheme outperform a baseline TS-RNNT.

eess.AS↗

arXiv2023

Downstream Task Agnostic Speech Enhancement with Self-Supervised Representation Loss

Self-supervised learning (SSL) is the latest breakthrough in speech processing, especially for label-scarce downstream tasks by leveraging massive unlabeled audio data. The noise robustness of the SSL is one of the important challenges to expanding its application. We can use speech enhancement (SE) to tackle this issue. However, the mismatch between the SE model and SSL models potentially limits its effect. In this work, we propose a new SE training criterion that minimizes the distance between clean and enhanced signals in the feature representation of the SSL model to alleviate the mismatch. We expect that the loss in the SSL domain could guide SE training to preserve or enhance various levels of characteristics of the speech signals that may be required for high-level downstream tasks. Experiments show that our proposal improves the performance of an SE and SSL pipeline on five downstream tasks with noisy input while maintaining the SE performance.

eess.AS↗