arXiv subjects

Yu Wu

Publications and source records attributed to Yu Wu.

At least 145 records · Page 8Linked to original sources

arXiv2024

Improving Bird's Eye View Semantic Segmentation by Task Decomposition

Semantic segmentation in bird's eye view (BEV) plays a crucial role in autonomous driving. Previous methods usually follow an end-to-end pipeline, directly predicting the BEV segmentation map from monocular RGB inputs. However, the challenge arises when the RGB inputs and BEV targets from distinct perspectives, making the direct point-to-point predicting hard to optimize. In this paper, we decompose the original BEV segmentation task into two stages, namely BEV map reconstruction and RGB-BEV feature alignment. In the first stage, we train a BEV autoencoder to reconstruct the BEV segmentation maps given corrupted noisy latent representation, which urges the decoder to learn fundamental knowledge of typical BEV patterns. The second stage involves mapping RGB input images into the BEV latent space of the first stage, directly optimizing the correlations between the two views at the feature level. Our approach simplifies the complexity of combining perception and generation into distinct steps, equipping the model to handle intricate and challenging scenes effectively. Besides, we propose to transform the BEV segmentation map from the Cartesian to the polar coordinate system to establish the column-wise correspondence between RGB images and BEV maps. Moreover, our method requires neither multi-scale features nor camera intrinsic parameters for depth estimation and saves computational overhead. Extensive experiments on nuScenes and Argoverse show the effectiveness and efficiency of our method. Code is available at https://github.com/happytianhao/TaDe.

cs.CV↗

arXiv2024

Learning by Correction: Efficient Tuning Task for Zero-Shot Generative Vision-Language Reasoning

Generative vision-language models (VLMs) have shown impressive performance in zero-shot vision-language tasks like image captioning and visual question answering. However, improving their zero-shot reasoning typically requires second-stage instruction tuning, which relies heavily on human-labeled or large language model-generated annotation, incurring high labeling costs. To tackle this challenge, we introduce Image-Conditioned Caption Correction (ICCC), a novel pre-training task designed to enhance VLMs' zero-shot performance without the need for labeled task-aware data. The ICCC task compels VLMs to rectify mismatches between visual and language concepts, thereby enhancing instruction following and text generation conditioned on visual inputs. Leveraging language structure and a lightweight dependency parser, we construct data samples of ICCC task from image-text datasets with low labeling and computation costs. Experimental results on BLIP-2 and InstructBLIP demonstrate significant improvements in zero-shot image-text generation-based VL tasks through ICCC instruction tuning.

cs.CV↗

arXiv2024

Advanced Long-Content Speech Recognition With Factorized Neural Transducer

In this paper, we propose two novel approaches, which integrate long-content information into the factorized neural transducer (FNT) based architecture in both non-streaming (referred to as LongFNT ) and streaming (referred to as SLongFNT ) scenarios. We first investigate whether long-content transcriptions can improve the vanilla conformer transducer (C-T) models. Our experiments indicate that the vanilla C-T models do not exhibit improved performance when utilizing long-content transcriptions, possibly due to the predictor network of C-T models not functioning as a pure language model. Instead, FNT shows its potential in utilizing long-content information, where we propose the LongFNT model and explore the impact of long-content information in both text (LongFNT-Text) and speech (LongFNT-Speech). The proposed LongFNT-Text and LongFNT-Speech models further complement each other to achieve better performance, with transcription history proving more valuable to the model. The effectiveness of our LongFNT approach is evaluated on LibriSpeech and GigaSpeech corpora, and obtains relative 19% and 12% word error rate reduction, respectively. Furthermore, we extend the LongFNT model to the streaming scenario, which is named SLongFNT , consisting of SLongFNT-Text and SLongFNT-Speech approaches to utilize long-content text and speech information. Experiments show that the proposed SLongFNT model achieves relative 26% and 17% WER reduction on LibriSpeech and GigaSpeech respectively while keeping a good latency, compared to the FNT baseline. Overall, our proposed LongFNT and SLongFNT highlight the significance of considering long-content speech and transcription knowledge for improving both non-streaming and streaming speech recognition systems.

cs.SD↗

arXiv2024

Diffusion in Diffusion: Cyclic One-Way Diffusion for Text-Vision-Conditioned Generation

Originating from the diffusion phenomenon in physics that describes particle movement, the diffusion generative models inherit the characteristics of stochastic random walk in the data space along the denoising trajectory. However, the intrinsic mutual interference among image regions contradicts the need for practical downstream application scenarios where the preservation of low-level pixel information from given conditioning is desired (e.g., customization tasks like personalized generation and inpainting based on a user-provided single image). In this work, we investigate the diffusion (physics) in diffusion (machine learning) properties and propose our Cyclic One-Way Diffusion (COW) method to control the direction of diffusion phenomenon given a pre-trained frozen diffusion model for versatile customization application scenarios, where the low-level pixel information from the conditioning needs to be preserved. Notably, unlike most current methods that incorporate additional conditions by fine-tuning the base text-to-image diffusion model or learning auxiliary networks, our method provides a novel perspective to understand the task needs and is applicable to a wider range of customization scenarios in a learning-free manner. Extensive experiment results show that our proposed COW can achieve more flexible customization based on strict visual conditions in different application settings. Project page: https://wangruoyu02.github.io/cow.github.io/.

cs.CV↗

arXiv2024

A Survey on Trustworthy Edge Intelligence: From Security and Reliability To Transparency and Sustainability

Edge Intelligence (EI) integrates Edge Computing (EC) and Artificial Intelligence (AI) to push the capabilities of AI to the network edge for real-time, efficient and secure intelligent decision-making and computation. However, EI faces various challenges due to resource constraints, heterogeneous network environments, and diverse service requirements of different applications, which together affect the trustworthiness of EI in the eyes of stakeholders. This survey comprehensively summarizes the characteristics, architecture, technologies, and solutions of trustworthy EI. Specifically, we first emphasize the need for trustworthy EI in the context of the trend toward large models. We then provide an initial definition of trustworthy EI, explore its key characteristics and give a multi-layered architecture for trustworthy EI. Then, we summarize several important issues that hinder the achievement of trustworthy EI. Subsequently, we present enabling technologies for trustworthy EI systems and provide an in-depth literature review of the state-of-the-art solutions for realizing the trustworthiness of EI. Finally, we discuss the corresponding research challenges and open issues.

cs.LG↗

arXiv2024

ClawCraneNet: Leveraging Object-level Relation for Text-based Video Segmentation

Text-based video segmentation is a challenging task that segments out the natural language referred objects in videos. It essentially requires semantic comprehension and fine-grained video understanding. Existing methods introduce language representation into segmentation models in a bottom-up manner, which merely conducts vision-language interaction within local receptive fields of ConvNets. We argue that such interaction is not fulfilled since the model can barely construct region-level relationships given partial observations, which is contrary to the description logic of natural language/referring expressions. In fact, people usually describe a target object using relations with other objects, which may not be easily understood without seeing the whole video. To address the issue, we introduce a novel top-down approach by imitating how we human segment an object with the language guidance. We first figure out all candidate objects in videos and then choose the refereed one by parsing relations among those high-level objects. Three kinds of object-level relations are investigated for precise relationship understanding, i.e., positional relation, text-guided semantic relation, and temporal relation. Extensive experiments on A2D Sentences and J-HMDB Sentences show our method outperforms state-of-the-art methods by a large margin. Qualitative results also show our results are more explainable.

cs.CV↗

arXiv2024

Rethinking Cross-modal Interaction from a Top-down Perspective for Referring Video Object Segmentation

Referring video object segmentation (RVOS) aims to segment video objects with the guidance of natural language reference. Previous methods typically tackle RVOS through directly grounding linguistic reference over the image lattice. Such bottom-up strategy fails to explore object-level cues, easily leading to inferior results. In this work, we instead put forward a two-stage, top-down RVOS solution. First, an exhaustive set of object tracklets is constructed by propagating object masks detected from several sampled frames to the entire video. Second, a Transformer-based tracklet-language grounding module is proposed, which models instance-level visual relations and cross-modal interactions simultaneously and efficiently. Our model ranks first place on CVPR2021 Referring Youtube-VOS challenge.

cs.CV↗

arXiv2024

WavMark: Watermarking for Audio Generation

Recent breakthroughs in zero-shot voice synthesis have enabled imitating a speaker's voice using just a few seconds of recording while maintaining a high level of realism. Alongside its potential benefits, this powerful technology introduces notable risks, including voice fraud and speaker impersonation. Unlike the conventional approach of solely relying on passive methods for detecting synthetic data, watermarking presents a proactive and robust defence mechanism against these looming risks. This paper introduces an innovative audio watermarking framework that encodes up to 32 bits of watermark within a mere 1-second audio snippet. The watermark is imperceptible to human senses and exhibits strong resilience against various attacks. It can serve as an effective identifier for synthesized voices and holds potential for broader applications in audio copyright protection. Moreover, this framework boasts high flexibility, allowing for the combination of multiple watermark segments to achieve heightened robustness and expanded capacity. Utilizing 10 to 20-second audio as the host, our approach demonstrates an average Bit Error Rate (BER) of 0.48\% across ten common attacks, a remarkable reduction of over 2800\% in BER compared to the state-of-the-art watermarking tool. See https://aka.ms/wavmark for demos of our work.

cs.SD↗

arXiv2023

DVIS++: Improved Decoupled Framework for Universal Video Segmentation

We present the \textbf{D}ecoupled \textbf{VI}deo \textbf{S}egmentation (DVIS) framework, a novel approach for the challenging task of universal video segmentation, including video instance segmentation (VIS), video semantic segmentation (VSS), and video panoptic segmentation (VPS). Unlike previous methods that model video segmentation in an end-to-end manner, our approach decouples video segmentation into three cascaded sub-tasks: segmentation, tracking, and refinement. This decoupling design allows for simpler and more effective modeling of the spatio-temporal representations of objects, especially in complex scenes and long videos. Accordingly, we introduce two novel components: the referring tracker and the temporal refiner. These components track objects frame by frame and model spatio-temporal representations based on pre-aligned features. To improve the tracking capability of DVIS, we propose a denoising training strategy and introduce contrastive learning, resulting in a more robust framework named DVIS++. Furthermore, we evaluate DVIS++ in various settings, including open vocabulary and using a frozen pre-trained backbone. By integrating CLIP with DVIS++, we present OV-DVIS++, the first open-vocabulary universal video segmentation framework. We conduct extensive experiments on six mainstream benchmarks, including the VIS, VSS, and VPS datasets. Using a unified architecture, DVIS++ significantly outperforms state-of-the-art specialized methods on these benchmarks in both close- and open-vocabulary settings. Code:~\url{https://github.com/zhang-tao-whu/DVIS_Plus}.

cs.CV↗

arXiv2023

Joint Trading and Scheduling among Coupled Carbon-Electricity-Heat-Gas Industrial Clusters

This paper presents a carbon-energy coupling management framework for an industrial park, where the carbon flow model accompanying multi-energy flows is adopted to track and suppress carbon emissions on the user side. To deal with the quadratic constraint of gas flows, a bound tightening algorithm for constraints relaxation is adopted. The synergies among the carbon capture, energy storage, power-to-gas further consume renewable energy and reduce carbon emissions. Aiming at carbon emissions disparities and supply-demand imbalances, this paper proposes a carbon trading ladder reward and punishment mechanism and an energy trading and scheduling method based on Lyapunov optimization and matching game to maximize the long-term benefits of each industrial cluster without knowing the prior information of random variables. Case studies show that our proposed trading method can reduce overall costs and carbon emissions while relieving energy pressure, which is important for Environmental, Social and Governance (ESG).

eess.SY↗

arXiv2023

DETER: Detecting Edited Regions for Deterring Generative Manipulations

Generative AI capabilities have grown substantially in recent years, raising renewed concerns about potential malicious use of generated data, or "deep fakes". However, deep fake datasets have not kept up with generative AI advancements sufficiently to enable the development of deep fake detection technology which can meaningfully alert human users in real-world settings. Existing datasets typically use GAN-based models and introduce spurious correlations by always editing similar face regions. To counteract the shortcomings, we introduce DETER, a large-scale dataset for DETEcting edited image Regions and deterring modern advanced generative manipulations. DETER includes 300,000 images manipulated by four state-of-the-art generators with three editing operations: face swapping (a standard coarse image manipulation), inpainting (a novel manipulation for deep fake datasets), and attribute editing (a subtle fine-grained manipulation). While face swapping and attribute editing are performed on similar face regions such as eyes and nose, the inpainting operation can be performed on random image regions, removing the spurious correlations of previous datasets. Careful image post-processing is performed to ensure deep fakes in DETER look realistic, and human studies confirm that human deep fake detection rate on DETER is 20.4% lower than on other fake datasets. Equipped with the dataset, we conduct extensive experiments and break-down analysis using our rich annotations and improved benchmark protocols, revealing future directions and the next set of challenges in developing reliable regional fake detection models.

cs.CV↗

arXiv2023

Giant Correlators at Quantum Level

We compute four-point functions with two maximal giant gravitons and two chiral primary operators at three-loop order in planar $\mathcal{N}=4$ Super-Yang-Mills theory. The Lagrangian insertion method, together with symmetries of the theory fix the integrand up to a few constants, which can be determined by lower loop data. The final result can be written in terms of the known three-loop conformal integrals. From the four-point function, we extract the OPE coefficients of two giant gravitons and one non-BPS twist-2 operator with arbitrary spin at three-loops, given in terms of harmonic sums. We observe an intriguingly simple relation between the giant graviton OPE coefficients and the OPE coefficients of three single-trace operators.

hep-th↗

arXiv2023

SIRe-IR: Inverse Rendering for BRDF Reconstruction with Shadow and Illumination Removal in High-Illuminance Scenes

Implicit neural representation has opened up new possibilities for inverse rendering. However, existing implicit neural inverse rendering methods struggle to handle strongly illuminated scenes with significant shadows and indirect illumination. The existence of shadows and reflections can lead to an inaccurate understanding of scene geometry, making precise factorization difficult. To this end, we present SIRe-IR, an implicit neural inverse rendering approach that uses non-linear mapping and regularized visibility estimation to decompose the scene into environment map, albedo, and roughness. By accurately modeling the indirect radiance field, normal, visibility, and direct light simultaneously, we are able to remove both shadows and indirect illumination in materials without imposing strict constraints on the scene. Even in the presence of intense illumination, our method recovers high-quality albedo and roughness with no shadow interference. SIRe-IR outperforms existing methods in both quantitative and qualitative evaluations.

cs.CV↗

arXiv2023

Revisit Weakly-Supervised Audio-Visual Video Parsing from the Language Perspective

We focus on the weakly-supervised audio-visual video parsing task (AVVP), which aims to identify and locate all the events in audio/visual modalities. Previous works only concentrate on video-level overall label denoising across modalities, but overlook the segment-level label noise, where adjacent video segments (i.e., 1-second video clips) may contain different events. However, recognizing events in the segment is challenging because its label could be any combination of events that occur in the video. To address this issue, we consider tackling AVVP from the language perspective, since language could freely describe how various events appear in each segment beyond fixed labels. Specifically, we design language prompts to describe all cases of event appearance for each video. Then, the similarity between language prompts and segments is calculated, where the event of the most similar prompt is regarded as the segment-level label. In addition, to deal with the mislabeled segments, we propose to perform dynamic re-weighting on the unreliable segments to adjust their labels. Experiments show that our simple yet effective approach outperforms state-of-the-art methods by a large margin.

cs.CV↗

arXiv2023

RIO: A Benchmark for Reasoning Intention-Oriented Objects in Open Environments

Intention-oriented object detection aims to detect desired objects based on specific intentions or requirements. For instance, when we desire to "lie down and rest", we instinctively seek out a suitable option such as a "bed" or a "sofa" that can fulfill our needs. Previous work in this area is limited either by the number of intention descriptions or by the affordance vocabulary available for intention objects. These limitations make it challenging to handle intentions in open environments effectively. To facilitate this research, we construct a comprehensive dataset called Reasoning Intention-Oriented Objects (RIO). In particular, RIO is specifically designed to incorporate diverse real-world scenarios and a wide range of object categories. It offers the following key features: 1) intention descriptions in RIO are represented as natural sentences rather than a mere word or verb phrase, making them more practical and meaningful; 2) the intention descriptions are contextually relevant to the scene, enabling a broader range of potential functionalities associated with the objects; 3) the dataset comprises a total of 40,214 images and 130,585 intention-object pairs. With the proposed RIO, we evaluate the ability of some existing models to reason intention-oriented objects in open environments.

cs.CV↗

arXiv2023

Ultralow lattice thermal transport and considerable wave-like phonon tunneling in chalcogenide perovskite BaZrS$_3$

Chalcogenide perovskites provide a promising avenue for non-toxic, stable thermoelectric materials. Here, thermal transport and thermoelectric properties of BaZrS$_3$ as a typical orthorhombic perovskite are investigated. An extremely low lattice thermal conductivity $κ_L$ of 1.84 W/mK at 300 K is revealed for BaZrS$_3$, due to the softening effect of Ba atoms on the lattice and the strong anharmonicity caused by the twisted structure. We demonstrate that coherence contributions to $κ_L$, arising from wave-like phonon tunneling, leading to a 18 \% thermal transport contribution at 300 K. The increasing temperature softens the phonons, thus reducing the group velocity of materials and increasing the scattering phase space. However, it simultaneously reduces the anharmonicity, which is dominant in BaZrS$_3$ and ultimately improves the particle-like thermal transport. Further, by replacing S atom with Se and Ti-alloying strategy, $ZT$ value of BaZrS$_3$ is significantly increased from 0.58 to 0.91 at 500 K, making it an important candidate for thermoelectric applications.

cond-mat.mtrl-sci↗

arXiv2023

LAMASSU: Streaming Language-Agnostic Multilingual Speech Recognition and Translation Using Neural Transducers

Automatic speech recognition (ASR) and speech translation (ST) can both use neural transducers as the model structure. It is thus possible to use a single transducer model to perform both tasks. In real-world applications, such joint ASR and ST models may need to be streaming and do not require source language identification (i.e. language-agnostic). In this paper, we propose LAMASSU, a streaming language-agnostic multilingual speech recognition and translation model using neural transducers. Based on the transducer model structure, we propose four methods, a unified joint and prediction network for multilingual output, a clustered multilingual encoder, target language identification for encoder, and connectionist temporal classification regularization. Experimental results show that LAMASSU not only drastically reduces the model size but also reaches the performances of monolingual ASR and bilingual ST models.

cs.CL↗

arXiv2023

Boundary Guided Learning-Free Semantic Control with Diffusion Models

Applying pre-trained generative denoising diffusion models (DDMs) for downstream tasks such as image semantic editing usually requires either fine-tuning DDMs or learning auxiliary editing networks in the existing literature. In this work, we present our BoundaryDiffusion method for efficient, effective and light-weight semantic control with frozen pre-trained DDMs, without learning any extra networks. As one of the first learning-free diffusion editing works, we start by seeking a comprehensive understanding of the intermediate high-dimensional latent spaces by theoretically and empirically analyzing their probabilistic and geometric behaviors in the Markov chain. We then propose to further explore the critical step for editing in the denoising trajectory that characterizes the convergence of a pre-trained DDM and introduce an automatic search method. Last but not least, in contrast to the conventional understanding that DDMs have relatively poor semantic behaviors, we prove that the critical latent space we found already exhibits semantic subspace boundaries at the generic level in unconditional DDMs, which allows us to do controllable manipulation by guiding the denoising trajectory towards the targeted boundary via a single-step operation. We conduct extensive experiments on multiple DPMs architectures (DDPM, iDDPM) and datasets (CelebA, CelebA-HQ, LSUN-church, LSUN-bedroom, AFHQ-dog) with different resolutions (64, 256), achieving superior or state-of-the-art performance in various task scenarios (image semantic editing, text-based editing, unconditional semantic control) to demonstrate the effectiveness.

cs.CV↗