arXiv subjects

Yi Yang

Publications and source records attributed to Yi Yang.

At least 487 records · Page 27Linked to original sources

arXiv2024

Collaborative Group: Composed Image Retrieval via Consensus Learning from Noisy Annotations

Composed image retrieval extends content-based image retrieval systems by enabling users to search using reference images and captions that describe their intention. Despite great progress in developing image-text compositors to extract discriminative visual-linguistic features, we identify a hitherto overlooked issue, triplet ambiguity, which impedes robust feature extraction. Triplet ambiguity refers to a type of semantic ambiguity that arises between the reference image, the relative caption, and the target image. It is mainly due to the limited representation of the annotated text, resulting in many noisy triplets where multiple visually dissimilar candidate images can be matched to an identical reference pair (i.e., a reference image + a relative caption). To address this challenge, we propose the Consensus Network (Css-Net), inspired by the psychological concept that groups outperform individuals. Css-Net comprises two core components: (1) a consensus module with four diverse compositors, each generating distinct image-text embeddings, fostering complementary feature extraction and mitigating dependence on any single, potentially biased compositor; (2) a Kullback-Leibler divergence loss that encourages learning of inter-compositor interactions to promote consensual outputs. During evaluation, the decisions of the four compositors are combined through a weighting scheme, enhancing overall agreement. On benchmark datasets, particularly FashionIQ, Css-Net demonstrates marked improvements. Notably, it achieves significant recall gains, with a 2.77% increase in R@10 and 6.67% boost in R@50, underscoring its competitiveness in addressing the fundamental limitations of existing methods.

cs.CV↗

arXiv2024

A cosmic formation site of silicon and sulphur revealed by a new type of supernova explosion

The cores of stars are the cosmic furnaces where light elements are fused into heavier nuclei. The fusion of hydrogen to helium initially powers all stars. The ashes of the fusion reactions are then predicted to serve as fuel in a series of stages, eventually transforming massive stars into a structure of concentric shells. These are composed of natal hydrogen on the outside, and consecutively heavier compositions inside, predicted to be dominated by helium, carbon/oxygen, oxygen/neon/magnesium, and oxygen/silicon/sulphur. Silicon and sulphur are fused into inert iron, leading to the collapse of the core and either a supernova explosion or the direct formation of a black hole. Stripped stars, where the outer hydrogen layer has been removed and the internal He-rich layer (in Wolf-Rayet WN stars) or even the C/O layer below it (in Wolf-Rayet WC/WO stars) are exposed, provide evidence for this shell structure, and the cosmic element production mechanism it reflects. The types of supernova explosions that arise from stripped stars embedded in shells of circumstellar material (most notably Type Ibn supernovae from stars with outer He layers, and Type Icn supernovae from stars with outer C/O layers) confirm this scenario. However, direct evidence for the most interior shells, which are responsible for the production of elements heavier than oxygen, is lacking. Here, we report the discovery of the first-of-its-kind supernova arising from a star peculiarly stripped all the way to the silicon and sulphur-rich internal layer. Whereas the concentric shell structure of massive stars is not under debate, it is the first time that such a thick, massive silicon and sulphur-rich shell, expelled by the progenitor shortly before the SN explosion, has been directly revealed.

astro-ph.HE↗

arXiv2024

Probing the black holes in a dark matter halo of M87 using gravitational wave echoes

Variations at the event horizon structure of a black hole will emit the signals of the gravitational wave echoes associated with the ringdown of the binary black hole merger. In this work, combining mass model of M87 and Einasto profile for dark matter halo, we construct one formal solution of black holes in dark matter halo, and this solution includes the regular black hole for geometric parameter $a < 2M$ and the wormhole for $a \geq 2M$. Then, we test this solution under axial gravitational perturbation and calculate their quasinormal modes (QNM). Our results show that when geometric parameter $a>2M$, a series of gravitational wave echoes appear after the QNM, and one distinctive feature of gravitational wave echoes is the double barrier. Besides, we also study the impacts of shape parameters $α$ of Einasto profile both on the QNM and gravitational wave echoes, and extract their frequencies using WKB method and Prony method. In principle, with the increasing of shape parameter $α$, the frequencies of the QNM and gravitational wave echoes between the different shape parameters must be different. But now there is zero difference of the frequencies between shape parameter $α=0.18$ and $α=0.20$. Zero difference is not allowed, so we give an upper limit for shape parameter $α$, which is approximately $α<0.18$. These signals of gravitational wave echoes in a dark matter halo may be detected in the near future, and these characteristics of gravitational wave echoes may serve as local measurements of dark matter.

gr-qc↗

arXiv2024

TAPVid-3D: A Benchmark for Tracking Any Point in 3D

We introduce a new benchmark, TAPVid-3D, for evaluating the task of long-range Tracking Any Point in 3D (TAP-3D). While point tracking in two dimensions (TAP) has many benchmarks measuring performance on real-world videos, such as TAPVid-DAVIS, three-dimensional point tracking has none. To this end, leveraging existing footage, we build a new benchmark for 3D point tracking featuring 4,000+ real-world videos, composed of three different data sources spanning a variety of object types, motion patterns, and indoor and outdoor environments. To measure performance on the TAP-3D task, we formulate a collection of metrics that extend the Jaccard-based metric used in TAP to handle the complexities of ambiguous depth scales across models, occlusions, and multi-track spatio-temporal smoothness. We manually verify a large sample of trajectories to ensure correct video annotations, and assess the current state of the TAP-3D task by constructing competitive baselines using existing tracking models. We anticipate this benchmark will serve as a guidepost to improve our ability to understand precise 3D motion and surface deformation from monocular video. Code for dataset download, generation, and model evaluation is available at https://tapvid3d.github.io

cs.CV↗

arXiv2024

ZeroMamba: Exploring Visual State Space Model for Zero-Shot Learning

Zero-shot learning (ZSL) aims to recognize unseen classes by transferring semantic knowledge from seen classes to unseen ones, guided by semantic information. To this end, existing works have demonstrated remarkable performance by utilizing global visual features from Convolutional Neural Networks (CNNs) or Vision Transformers (ViTs) for visual-semantic interactions. Due to the limited receptive fields of CNNs and the quadratic complexity of ViTs, however, these visual backbones achieve suboptimal visual-semantic interactions. In this paper, motivated by the visual state space model (i.e., Vision Mamba), which is capable of capturing long-range dependencies and modeling complex visual dynamics, we propose a parameter-efficient ZSL framework called ZeroMamba to advance ZSL. Our ZeroMamba comprises three key components: Semantic-aware Local Projection (SLP), Global Representation Learning (GRL), and Semantic Fusion (SeF). Specifically, SLP integrates semantic embeddings to map visual features to local semantic-related representations, while GRL encourages the model to learn global semantic representations. SeF combines these two semantic representations to enhance the discriminability of semantic features. We incorporate these designs into Vision Mamba, forming an end-to-end ZSL framework. As a result, the learned semantic representations are better suited for classification. Through extensive experiments on four prominent ZSL benchmarks, ZeroMamba demonstrates superior performance, significantly outperforming the state-of-the-art (i.e., CNN-based and ViT-based) methods under both conventional ZSL (CZSL) and generalized ZSL (GZSL) settings. Code is available at: https://anonymous.4open.science/r/ZeroMamba.

cs.CV↗

arXiv2024

Minute-Cadence Observations of the LAMOST Fields with the TMTS: IV -- Catalog of Cataclysmic Variables from the First 3-yr Survey

The Tsinghua University--Ma Huateng Telescopes for Survey (TMTS) started to monitor the LAMOST plates in 2020, leading to the discovery of numerous short-period eclipsing binaries, peculiar pulsators, flare stars, and other variable objects. Here, we present the uninterrupted light curves for a sample of 64 cataclysmic variables (CVs) observed/discovered using the TMTS during its first three-year observations, and we introduce new CVs and new light-variation periods (from known CVs) revealed through the TMTS observations. Thanks to the high-cadence observations of TMTS, diverse light variations, including superhumps, quasi-periodic oscillations, large-amplitude orbital modulations, and rotational modulations, are able to be detected in our CV samples, providing key observational clues for understanding the fast-developing physical processes in various CVs. All of these short-timescale light-curve features help further classify the subtypes of CV systems. We highlight the light-curve features observed in our CV sample and discuss further implications of minute-cadence light curves for CV identifications and classifications. Moreover, we examine the H$α$ emission lines in the spectra from our nonmagnetic CV samples (i.e., dwarf novae and nova-like subclasses) and find that the distribution of H$α$ emission strength shows significant differences between the sources with orbital periods above and below the period gap, which agrees with the trend seen from the SDSS nonmagnetic CV sample.

astro-ph.SR↗

arXiv2024

Model Stealing Attack against Graph Classification with Authenticity, Uncertainty and Diversity

Recent research demonstrates that GNNs are vulnerable to the model stealing attack, a nefarious endeavor geared towards duplicating the target model via query permissions. However, they mainly focus on node classification tasks, neglecting the potential threats entailed within the domain of graph classification tasks. Furthermore, their practicality is questionable due to unreasonable assumptions, specifically concerning the large data requirements and extensive model knowledge. To this end, we advocate following strict settings with limited real data and hard-label awareness to generate synthetic data, thereby facilitating the stealing of the target model. Specifically, following important data generation principles, we introduce three model stealing attacks to adapt to different actual scenarios: MSA-AU is inspired by active learning and emphasizes the uncertainty to enhance query value of generated samples; MSA-AD introduces diversity based on Mixup augmentation strategy to alleviate the query inefficiency issue caused by over-similar samples generated by MSA-AU; MSA-AUD combines the above two strategies to seamlessly integrate the authenticity, uncertainty, and diversity of the generated samples. Finally, extensive experiments consistently demonstrate the superiority of the proposed methods in terms of concealment, query efficiency, and stealing performance.

cs.LG↗

arXiv2024

MePT: Multi-Representation Guided Prompt Tuning for Vision-Language Model

Recent advancements in pre-trained Vision-Language Models (VLMs) have highlighted the significant potential of prompt tuning for adapting these models to a wide range of downstream tasks. However, existing prompt tuning methods typically map an image to a single representation, limiting the model's ability to capture the diverse ways an image can be described. To address this limitation, we investigate the impact of visual prompts on the model's generalization capability and introduce a novel method termed Multi-Representation Guided Prompt Tuning (MePT). Specifically, MePT employs a three-branch framework that focuses on diverse salient regions, uncovering the inherent knowledge within images which is crucial for robust generalization. Further, we employ efficient self-ensemble techniques to integrate these versatile image representations, allowing MePT to learn all conditional, marginal, and fine-grained distributions effectively. We validate the effectiveness of MePT through extensive experiments, demonstrating significant improvements on both base-to-novel class prediction and domain generalization tasks.

cs.CV↗

arXiv2024

UAHOI: Uncertainty-aware Robust Interaction Learning for HOI Detection

This paper focuses on Human-Object Interaction (HOI) detection, addressing the challenge of identifying and understanding the interactions between humans and objects within a given image or video frame. Spearheaded by Detection Transformer (DETR), recent developments lead to significant improvements by replacing traditional region proposals by a set of learnable queries. However, despite the powerful representation capabilities provided by Transformers, existing Human-Object Interaction (HOI) detection methods still yield low confidence levels when dealing with complex interactions and are prone to overlooking interactive actions. To address these issues, we propose a novel approach \textsc{UAHOI}, Uncertainty-aware Robust Human-Object Interaction Learning that explicitly estimates prediction uncertainty during the training process to refine both detection and interaction predictions. Our model not only predicts the HOI triplets but also quantifies the uncertainty of these predictions. Specifically, we model this uncertainty through the variance of predictions and incorporate it into the optimization objective, allowing the model to adaptively adjust its confidence threshold based on prediction variance. This integration helps in mitigating the adverse effects of incorrect or ambiguous predictions that are common in traditional methods without any hand-designed components, serving as an automatic confidence threshold. Our method is flexible to existing HOI detection methods and demonstrates improved accuracy. We evaluate \textsc{UAHOI} on two standard benchmarks in the field: V-COCO and HICO-DET, which represent challenging scenarios for HOI detection. Through extensive experiments, we demonstrate that \textsc{UAHOI} achieves significant improvements over existing state-of-the-art methods, enhancing both the accuracy and robustness of HOI detection.

cs.CV↗

arXiv2024

A model for planar compacta and rational Julia sets

A Peano compactum is a compact metric space having locally connected components such that at most finitely many of them are of diameter greater than any fixed number C>0. Given a compactum K in the extended complex plane, it is known that there is a finest upper semi-continuous decomposition of K into subcontinua such that the resulting quotient space is a Peano compactum. We call this decomposition the core decomposition of K with Peano quotient and its elements atoms of K. We show that for any branched covering f of the extended complex plane onto itself and for any atom d of K, the preimage of d under f has finitely many components each of which is an atom of the preimage of K under f. Since rational functions are branched coverings, our result extends earlier ones that are restricted to more limited cases, requiring that f be a polynomial and K completely invariant under f.

math.DS↗

arXiv2024

Stringy Scaling

We discover a general stringy scaling behavior for 1. All n-point hard string scattering amplitudes (HSSA) and 2. A class of n-point Regge string scattering amplitudes (RSSA) to all string loop orders. The number of independent kinematics variables is found to be reduced by dim M.

hep-th↗

arXiv2024

Prototype Learning for Micro-gesture Classification

In this paper, we briefly introduce the solution developed by our team, HFUT-VUT, for the track of Micro-gesture Classification in the MiGA challenge at IJCAI 2024. The task of micro-gesture classification task involves recognizing the category of a given video clip, which focuses on more fine-grained and subtle body movements compared to typical action recognition tasks. Given the inherent complexity of micro-gesture recognition, which includes large intra-class variability and minimal inter-class differences, we utilize two innovative modules, i.e., the cross-modal fusion module and prototypical refinement module, to improve the discriminative ability of MG features, thereby improving the classification accuracy. Our solution achieved significant success, ranking 1st in the track of Micro-gesture Classification. We surpassed the performance of last year's leading team by a substantial margin, improving Top-1 accuracy by 6.13%.

cs.CV↗

arXiv2024

Extended Shock Breakout and Early Circumstellar Interaction in SN 2024ggi

We present high-cadence photometric and spectroscopic observations of supernova (SN) 2024ggi, a Type II SN with flash spectroscopy features which exploded in the nearby galaxy NGC 3621 at $\sim$7 Mpc. The light-curve evolution over the first 30 hours can be fit by two power law indices with a break after 22 hours, rising from $M_V \approx -12.95$ mag at +0.66 days to $M_V \approx -17.91$ mag after 7 days. In addition, the densely sampled color curve shows a strong blueward evolution over the first few days and then behaves as a normal SN II with a redward evolution as the ejecta cool. Such deviations could be due to interaction with circumstellar material (CSM). Early high- and low-resolution spectra clearly show high-ionization flash features from the first spectrum to +3.42 days after the explosion. From the high-resolution spectra, we calculate the CSM velocity to be 37 $\pm~4~\mathrm{km\,s^{-1}} $. We also see the line strength evolve rapidly from 1.22 to 1.49 days in the earliest high-resolution spectra. Comparison of the low-resolution spectra with CMFGEN models suggests that the pre-explosion mass-loss rate of SN 2024ggi falls in a range of $10^{-3}$ to $10^{-2}$ M$_{\odot}$ yr$^{-1}$, which is similar to that derived for SN 2023ixf. However, the rapid temporal evolution of the narrow lines in the spectra of SN 2024ggi ($R_\mathrm{CSM} \sim 2.7 \times 10^{14} \mathrm{cm}$) could indicate a smaller spatial extent of the CSM than in SN 2023ixf ($R_\mathrm{CSM} \sim 5.4 \times 10^{14} \mathrm{cm}$) which in turn implies lower total CSM mass for SN 2024ggi.

astro-ph.HE↗

arXiv2024

Autonomous LLM-Enhanced Adversarial Attack for Text-to-Motion

Human motion generation driven by deep generative models has enabled compelling applications, but the ability of text-to-motion (T2M) models to produce realistic motions from text prompts raises security concerns if exploited maliciously. Despite growing interest in T2M, few methods focus on safeguarding these models against adversarial attacks, with existing work on text-to-image models proving insufficient for the unique motion domain. In the paper, we propose ALERT-Motion, an autonomous framework leveraging large language models (LLMs) to craft targeted adversarial attacks against black-box T2M models. Unlike prior methods modifying prompts through predefined rules, ALERT-Motion uses LLMs' knowledge of human motion to autonomously generate subtle yet powerful adversarial text descriptions. It comprises two key modules: an adaptive dispatching module that constructs an LLM-based agent to iteratively refine and search for adversarial prompts; and a multimodal information contrastive module that extracts semantically relevant motion information to guide the agent's search. Through this LLM-driven approach, ALERT-Motion crafts adversarial prompts querying victim models to produce outputs closely matching targeted motions, while avoiding obvious perturbations. Evaluations across popular T2M models demonstrate ALERT-Motion's superiority over previous methods, achieving higher attack success rates with stealthier adversarial prompts. This pioneering work on T2M adversarial attacks highlights the urgency of developing defensive measures as motion generation technology advances, urging further research into safe and responsible deployment.

cs.CV↗

arXiv2024

The most distant HI galaxies discovered by the 500 m dish FAST

Neutral hydrogen (HI) is the primary component of the cool interstellar medium (ISM) and is the reservoir of fuel for star formation. Owing to the sensitivity of existing radio telescopes, our understanding of the evolution of the ISM in galaxies remains limited, as it is based on only a few hundred galaxies detected in HI beyond the local Universe. With the high sensitivity of the Five-hundred-meter Aperture Spherical radio Telescope (FAST), we carried out a blind HI search, the FAST Ultra-Deep Survey (FUDS), which extends to redshifts up to 0.42 and a sensitivity of 50 $\rm μJy \cdot beam^{-1}$. Here, we report the first discovery of six galaxies in HI at $z>0.38$. For these galaxies, the FAST angular resolution of $\sim\,4'$ corresponds to a mean linear size of $\sim1.3\,h_{70}^{-1}\,$Mpc. These galaxies are among the most distant HI emission detections known, with one having the most massive HI content ($10^{10.93 \pm 0.04}~h_{70}^{-2}\, \rm M_\odot$). Using recent data from the DESI survey, and new observations with the Hale, BTA, and Keck telescopes, optical counterparts are detected for all galaxies within the 3-$σ$ positional uncertainty ($0.5\,h_{70}^{-1}\,$Mpc) and $\rm 200\,km \cdot s^{-1}$ in recession velocity. Assuming that the dominant source of HI is the identified optical counterpart, we find an evidence of evolution in the HI content of galaxies over the last 4.2 Gyr. Our new high-redshift HI galaxy sample provides the opportunity to better investigate the evolution of cool gas in galaxies. A larger sample size in the future will allow us to refine our knowledge of the formation and evolution of galaxies.

astro-ph.GA↗

arXiv2024

Transferring to Real-World Layouts: A Depth-aware Framework for Scene Adaptation

Scene segmentation via unsupervised domain adaptation (UDA) enables the transfer of knowledge acquired from source synthetic data to real-world target data, which largely reduces the need for manual pixel-level annotations in the target domain. To facilitate domain-invariant feature learning, existing methods typically mix data from both the source domain and target domain by simply copying and pasting the pixels. Such vanilla methods are usually sub-optimal since they do not take into account how well the mixed layouts correspond to real-world scenarios. Real-world scenarios are with an inherent layout. We observe that semantic categories, such as sidewalks, buildings, and sky, display relatively consistent depth distributions, and could be clearly distinguished in a depth map. Based on such observation, we propose a depth-aware framework to explicitly leverage depth estimation to mix the categories and facilitate the two complementary tasks, i.e., segmentation and depth learning in an end-to-end manner. In particular, the framework contains a Depth-guided Contextual Filter (DCF) forndata augmentation and a cross-task encoder for contextual learning. DCF simulates the real-world layouts, while the cross-task encoder further adaptively fuses the complementing features between two tasks. Besides, it is worth noting that several public datasets do not provide depth annotation. Therefore, we leverage the off-the-shelf depth estimation network to generate the pseudo depth. Extensive experiments show that our proposed methods, even with pseudo depth, achieve competitive performance on two widely-used bench-marks, i.e. 77.7 mIoU on GTA to Cityscapes and 69.3 mIoU on Synthia to Cityscapes.

cs.CV↗

arXiv2024

Supernova Polarization Signals From the Interaction with a Dense Circumstellar Disk

There is increasing evidence that massive stars may exhibit an enhanced mass loss shortly before their termination explosion. Some of them also indicate the enhancement of their circumstellar matter (CSM) is not spherically symmetric. Supernova (SN) interacting with aspherical CSM could induce special polarization signals from multiple radiation components that deviate from spherical symmetry. We investigate the time-evolution of the continuum polarization induced by the SN ejecta interacting with a disk/torus-like CSM. Our calculation suggests that the interaction between the SN ejecta and an immediate disk-like CSM with a thin, homogenous density structure would produce a high continuum polarization, which may reach a peak level of $\sim$15\%. The interplay between the evolving geometry of the emitting regions and the time-variant flux ratio between the polar ejecta and the equatorial CSM interaction may produce a double-peaked feature in the polarization time sequence. A similar trend of the time evolution of the polarization is also found for a radially extended CSM disk that exhibits a wind-like density structure, with an overall relatively lower level of continuum polarization ($<2.5\%$) during the interaction process. We also identify a non-uniform temperature distribution along the radial direction of the CSM disk, which yields a strong wavelength dependence of the continuum polarization. These signatures provide a unique geometric diagnostic to explore the interaction process and the associated extreme mass loss of the progenitors of interacting transients.

astro-ph.HE↗

arXiv2024

Slimmable Networks for Contrastive Self-supervised Learning

Self-supervised learning makes significant progress in pre-training large models, but struggles with small models. Mainstream solutions to this problem rely mainly on knowledge distillation, which involves a two-stage procedure: first training a large teacher model and then distilling it to improve the generalization ability of smaller ones. In this work, we introduce another one-stage solution to obtain pre-trained small models without the need for extra teachers, namely, slimmable networks for contrastive self-supervised learning (SlimCLR). A slimmable network consists of a full network and several weight-sharing sub-networks, which can be pre-trained once to obtain various networks, including small ones with low computation costs. However, interference between weight-sharing networks leads to severe performance degradation in self-supervised cases, as evidenced by gradient magnitude imbalance and gradient direction divergence. The former indicates that a small proportion of parameters produce dominant gradients during backpropagation, while the main parameters may not be fully optimized. The latter shows that the gradient direction is disordered, and the optimization process is unstable. To address these issues, we introduce three techniques to make the main parameters produce dominant gradients and sub-networks have consistent outputs. These techniques include slow start training of sub-networks, online distillation, and loss re-weighting according to model sizes. Furthermore, theoretical results are presented to demonstrate that a single slimmable linear layer is sub-optimal during linear evaluation. Thus a switchable linear probe layer is applied during linear evaluation. We instantiate SlimCLR with typical contrastive learning frameworks and achieve better performance than previous arts with fewer parameters and FLOPs. The code is at https://github.com/mzhaoshuai/SlimCLR.

cs.CV↗