arXiv subjects

Mainak Singha

Publications and source records attributed to Mainak Singha.

At least 37 records · Page 2Linked to original sources

arXiv2025

A century of change: new changing-look event in Mrk 1018's past

We investigate the long-term variability of the known Changing Look Active Galactic Nuclei (CL AGN) Mrk 1018, whose second change we discovered as part of the Close AGN Reference Survey (CARS). Collating over a hundred years worth of photometry from scanned photographic plates and five modern surveys we find a historic outburst between ~1935-1960, with variation in Johnson B magnitude of ~0.8 that is consistent with Mrk 1018's brightness before and after its latest changing look event in the early 2010s. Using the combined modern and historic data, a Generalised Lomb-Scargle suggests broad feature with P = 29-47 years. Its width and stability across tests, as well as the turn-on speed and bright phase duration of the historic event suggests a timescale associated with long-term modulation, such as via rapid flickering in the accretion rate caused by the Chaotic Cold Accretion model rather than a strictly periodic CL mechanism driving changes in Mrk 1018. We also use the modern photometry to constrain Mrk 1018's latest turn-off duration to less than ~1.9 years, providing further support for a CL mechanism with rapid transition timescales, such as a changing mode of accretion.

astro-ph.GA↗

arXiv2025

FedMVP: Federated Multimodal Visual Prompt Tuning for Vision-Language Models

In federated learning, textual prompt tuning adapts Vision-Language Models (e.g., CLIP) by tuning lightweight input tokens (or prompts) on local client data, while keeping network weights frozen. After training, only the prompts are shared by the clients with the central server for aggregation. However, textual prompt tuning suffers from overfitting to known concepts, limiting its generalizability to unseen concepts. To address this limitation, we propose Multimodal Visual Prompt Tuning (FedMVP) that conditions the prompts on multimodal contextual information - derived from the input image and textual attribute features of a class. At the core of FedMVP is a PromptFormer module that synergistically aligns textual and visual features through a cross-attention mechanism. The dynamically generated multimodal visual prompts are then input to the frozen vision encoder of CLIP, and trained with a combination of CLIP similarity loss and a consistency loss. Extensive evaluation on 20 datasets, spanning three generalization settings, demonstrates that FedMVP not only preserves performance on in-distribution classes and domains, but also displays higher generalizability to unseen classes and domains, surpassing state-of-the-art methods by a notable margin of +1.57% - 2.26%. Code is available at https://github.com/mainaksingha01/FedMVP.

cs.CV↗

arXiv2025

Gravitational Torques from a Lopsided Young Stellar Component Sustain High Black Hole Accretion Rates in NGC 4593

Supermassive black holes (SMBHs) grow primarily through gas accretion, observed as active galactic nuclei (AGNs). While mergers can drive luminous AGN episodes, secular processes may fuel a substantial portion of cosmic BH growth. Whether these mechanisms can sustain high BH accretion rates remains uncertain. This study aims to identify the secular mechanism driving high BH accretion rates, by targeting a galaxy with moderately massive SMBH, high central gas densities, accretion rates of a few percent of the Eddington limit, and gas kinematics resolved close to black hole-dominated scales. A blind search led to the identification of NGC 4593, which is representative of the AGN population driving BH mass density growth since $z=1$. A prominent single-arm ("$m=1$") molecular gas spiral with ${\rm log}\,M_{\rm mol}/{\rm M}_\odot=8.1\pm0.3$ extends from 1.3$\,$kpc down to the SMBH's sphere of influence ($1.7^{+0.5}_{-0.2}\,{\rm pc}$). Star formation in the spiral is inefficient (${\rm SFR} = 4.9 \times 10^{-2} \,{\rm M}_\odot {\rm /yr}$, $\langle t_{\rm dep}\rangle=3.9 \pm 0.6\,\rm{Gyr}$), whereas inflow rate exceeds the SFR by two orders of magnitude and is sufficient to sustain the current BH accretion rate for $\geq$35$\,$Myr, enabling $\sim$10% SMBH growth. A young, lopsided stellar component (${\rm log}\,M_\star/{\rm M}_\odot=7.5-9.3$) exerts torques on the molecular gas, likely driving the gas inflow. This young stellar component may serve as both a cause and a product of sustained gas funnelling towards the SMBH. These findings provide evidence for the sustained secular $m=1$ feeding mode at high BH accretion rates, linking kpc-scale gas dynamics to the black hole's sphere of influence. This mechanism, consistent with simulation predictions, may represent a key contributor to SMBH growth in luminous AGNs since cosmic noon.

astro-ph.GA↗

arXiv2025

The Close AGN Reference Survey (CARS): A comparison between sub-mm and optical AGN diagnostic diagrams

The $L_{\rm IR}-L_{\rm HCN}$ relation suggests that there is a tight connection between dense gas and star formation. We use data from the Close AGN Reference Survey (CARS) to investigate the dense gas - star formation relation in AGN hosting galaxies, and the use of dense gas as an active galactic nuclei (AGN) diagnostic. Our sample contains five Type-1 (unobscured) AGN that were observed with the Atacama Large Millimeter/submillimeter Array (ALMA) with the aim to detect HCN(4-3), HCO$^+$(4-3) and CS(7-6). We detect the dense gas emission required for this analysis in 3 of the 5 targets. We find that despite the potential impact from the AGN on the line fluxes of these sources, they still follow the $L_{\rm IR}-L_{\rm HCN}$ relation. We then go on to test claims that the HCN/HCO+ and HCN/CS line ratios can be used as a tool to classify AGN in the sub-mm HCN diagram. We produce the classic ionised emission-line ratio diagnostics (the so-called BPT diagrams), using available CARS data from the Multi Unit Spectroscopic Explorer (MUSE). We then compare the BPT classification with the sub-mm classification made using the dense gas tracers. Where it was possible to complete the analysis we find general agreement between optical and sub-mm classified gas excitation mechanisms. This suggests that AGN can contribute to the excitation of both the low density gas in the warm ionised medium and the high density gas in molecular clouds simultaneously, perhaps through X-ray, cosmic ray or shock heating mechanisms.

astro-ph.GA↗

arXiv2025

Jet-mode feedback in NGC 5972: insights from resolved MUSE, GMRT and VLA observations

NGC 5972, a Voorwerp galaxy, features a helical-shaped extended emission-line region (EELR) with a radius > 10 kpc and a S-shaped radio structure spanning about 470 kpc. We use VLT MUSE, GMRT, and VLA to study the stellar and ionized gas kinematics and how the radio jet influences the gas in the galaxy. Our sensitive radio observations detect the southern jet for the first time, roughly coinciding with the southern EELR. The VLA images show a continuous inner jet connected to the outer E-W lobe, confirming the jet origin of the radio emission. Our kinematic analysis shows spatial correlations between the radio jet and the outflowing gas, supporting the jet-driven feedback mechanism. More interestingly, we observe enhanced velocity dispersion in the perpendicular direction along with a shell-like structure. Our BPT analysis shows that the [O III] emission overlapping with the radio jet is consistent with the shock+precursor model, whereas in the perpendicular region, a pure shock model fits well with the observations, indicating jet-induced shocks. Radio observations indicate episodic AGN activity characterized by surface brightness and spectral index discontinuities. Overall, based on our findings, we propose a jet-driven feedback mechanism as one of the key factors in the formation of the EELR in NGC 5972. Future high-resolution radio observations will be crucial to further investigate the origin of the EELR and quantify the extent to which the jet influences its formation and evolution.

astro-ph.GA↗

arXiv2025

OSLoPrompt: Bridging Low-Supervision Challenges and Open-Set Domain Generalization in CLIP

We introduce Low-Shot Open-Set Domain Generalization (LSOSDG), a novel paradigm unifying low-shot learning with open-set domain generalization (ODG). While prompt-based methods using models like CLIP have advanced DG, they falter in low-data regimes (e.g., 1-shot) and lack precision in detecting open-set samples with fine-grained semantics related to training classes. To address these challenges, we propose OSLOPROMPT, an advanced prompt-learning framework for CLIP with two core innovations. First, to manage limited supervision across source domains and improve DG, we introduce a domain-agnostic prompt-learning mechanism that integrates adaptable domain-specific cues and visually guided semantic attributes through a novel cross-attention module, besides being supported by learnable domain- and class-generic visual prompts to enhance cross-modal adaptability. Second, to improve outlier rejection during inference, we classify unfamiliar samples as "unknown" and train specialized prompts with systematically synthesized pseudo-open samples that maintain fine-grained relationships to known classes, generated through a targeted query strategy with off-the-shelf foundation models. This strategy enhances feature learning, enabling our model to detect open samples with varied granularity more effectively. Extensive evaluations across five benchmarks demonstrate that OSLOPROMPT establishes a new state-of-the-art in LSOSDG, significantly outperforming existing methods.

cs.CV↗

arXiv2024

COSMo: CLIP Talks on Open-Set Multi-Target Domain Adaptation

Multi-Target Domain Adaptation (MTDA) entails learning domain-invariant information from a single source domain and applying it to multiple unlabeled target domains. Yet, existing MTDA methods predominantly focus on addressing domain shifts within visual features, often overlooking semantic features and struggling to handle unknown classes, resulting in what is known as Open-Set (OS) MTDA. While large-scale vision-language foundation models like CLIP show promise, their potential for MTDA remains largely unexplored. This paper introduces COSMo, a novel method that learns domain-agnostic prompts through source domain-guided prompt learning to tackle the MTDA problem in the prompt space. By leveraging a domain-specific bias network and separate prompts for known and unknown classes, COSMo effectively adapts across domain and class shifts. To the best of our knowledge, COSMo is the first method to address Open-Set Multi-Target DA (OSMTDA), offering a more realistic representation of real-world scenarios and addressing the challenges of both open-set and multi-target DA. COSMo demonstrates an average improvement of $5.1\%$ across three challenging datasets: Mini-DomainNet, Office-31, and Office-Home, compared to other related DA methods adapted to operate within the OSMTDA setting. Code is available at: https://github.com/munish30monga/COSMo

cs.CV↗

arXiv2024

ESpRESSO -- Forward modeling Roman Space Telescope spectroscopy

We describe the software package $\texttt{ESpRESSO}$ - [E]xtragalactic [Sp]ectroscopic [R]oman [E]mulator and [S]imulator of [S]ynthetic [O]bjects, created to emulate the slitless spectroscopic observing modes of the Nancy Grace Roman Space Telescope (Roman) Wide Field Instrument (WFI). We combine archival Hubble Space Telescope (HST) imaging data of comparable spatial resolution with model spectral energy distributions to create a data-cube of flux density as a function of position and wavelength. This data-cube is used for simulating a nine detector grism observation, producing a crowded background scene which model field angle dependent optical distortions expected for the grism. We also demonstrate the ability to inject custom sources using the described tools and pipelines. In addition, we show that spectral features such as emission line pairs are unlikely to be mistaken as off order contaminating features and vice versa. Our result is a simulation suite of half of the eighteen detector array, with a realistic background scene and injected Ly$α$ emitter (LAE) galaxies, realized at 25 position angles (PAs), 12 with analogous positive and negative dithers, Using an exposure time of 10ks per PA, the full PA set can be used as a mock deep Roman grism survey with high (synthetic) LAE completeness for developing future spectral data analysis tools.

astro-ph.IM↗

arXiv2024

GraphVL: Graph-Enhanced Semantic Modeling via Vision-Language Models for Generalized Class Discovery

Generalized Category Discovery (GCD) aims to cluster unlabeled images into known and novel categories using labeled images from known classes. To address the challenge of transferring features from known to unknown classes while mitigating model bias, we introduce GraphVL, a novel approach for vision-language modeling in GCD, leveraging CLIP. Our method integrates a graph convolutional network (GCN) with CLIP's text encoder to preserve class neighborhood structure. We also employ a lightweight visual projector for image data, ensuring discriminative features through margin-based contrastive losses for image-text mapping. This neighborhood preservation criterion effectively regulates the semantic space, making it less sensitive to known classes. Additionally, we learn textual prompts from known classes and align them to create a more contextually meaningful semantic feature space for the GCN layer using a contextual similarity loss. Finally, we represent unlabeled samples based on their semantic distance to class prompts from the GCN, enabling semi-supervised clustering for class discovery and minimizing errors. Our experiments on seven benchmark datasets consistently demonstrate the superiority of GraphVL when integrated with the CLIP backbone.

cs.CV↗

arXiv2024

AD-CLIP: Adapting Domains in Prompt Space Using CLIP

Although deep learning models have shown impressive performance on supervised learning tasks, they often struggle to generalize well when the training (source) and test (target) domains differ. Unsupervised domain adaptation (DA) has emerged as a popular solution to this problem. However, current DA techniques rely on visual backbones, which may lack semantic richness. Despite the potential of large-scale vision-language foundation models like CLIP, their effectiveness for DA has yet to be fully explored. To address this gap, we introduce \textsc{AD-CLIP}, a domain-agnostic prompt learning strategy for CLIP that aims to solve the DA problem in the prompt space. We leverage the frozen vision backbone of CLIP to extract both image style (domain) and content information, which we apply to learn prompt tokens. Our prompts are designed to be domain-invariant and class-generalizable, by conditioning prompt learning on image style and content features simultaneously. We use standard supervised contrastive learning in the source domain, while proposing an entropy minimization strategy to align domains in the embedding space given the target domain data. We also consider a scenario where only target domain samples are available during testing, without any source domain data, and propose a cross-domain style mapping network to hallucinate domain-agnostic tokens. Our extensive experiments on three benchmark DA datasets demonstrate the effectiveness of \textsc{AD-CLIP} compared to existing literature. Code is available at \url{https://github.com/mainaksingha01/AD-CLIP}

cs.CV↗

arXiv2024

Elevating All Zero-Shot Sketch-Based Image Retrieval Through Multimodal Prompt Learning

We address the challenges inherent in sketch-based image retrieval (SBIR) across various settings, including zero-shot SBIR, generalized zero-shot SBIR, and fine-grained zero-shot SBIR, by leveraging the vision-language foundation model CLIP. While recent endeavors have employed CLIP to enhance SBIR, these approaches predominantly follow uni-modal prompt processing and overlook to exploit CLIP's integrated visual and textual capabilities fully. To bridge this gap, we introduce SpLIP, a novel multi-modal prompt learning scheme designed to operate effectively with frozen CLIP backbones. We diverge from existing multi-modal prompting methods that treat visual and textual prompts independently or integrate them in a limited fashion, leading to suboptimal generalization. SpLIP implements a bi-directional prompt-sharing strategy that enables mutual knowledge exchange between CLIP's visual and textual encoders, fostering a more cohesive and synergistic prompt processing mechanism that significantly reduces the semantic gap between the sketch and photo embeddings. In addition to pioneering multi-modal prompt learning, we propose two innovative strategies for further refining the embedding space. The first is an adaptive margin generation for the sketch-photo triplet loss, regulated by CLIP's class textual embeddings. The second introduces a novel task, termed conditional cross-modal jigsaw, aimed at enhancing fine-grained sketch-photo alignment by implicitly modeling sketches' viable patch arrangement using knowledge of unshuffled photos. Our comprehensive experimental evaluations across multiple benchmarks demonstrate the superior performance of SpLIP in all three SBIR scenarios. Project page: https://mainaksingha01.github.io/SpLIP/ .

cs.CV↗

arXiv2024

Chandra detects low-luminosity AGN with $M_\mathrm{BH}=10^{4}-10^{6}~M_\mathrm{\odot}$ in nearby ($z<0.5$), dwarf and star-forming galaxies

We searched the Chandra and XMM archives for observations of 900 green pea galaxies to find AGN signatures. Green peas are low-mass galaxies with prominent emission lines, similar in size and star formation rate to high-redshift dwarf galaxies. Of the 29 observations found, 9 show X-ray detections with $S/N>3$. The 2-10 keV X-ray luminosity for these 9 sources exceeds $10^{40}~\mathrm{erg~s}^{-1}$, with 2 sources exceeding $10^{41}~\mathrm{erg~s}^{-1}$, suggesting the presence of intermediate-mass black holes (IMBH) or low-luminosity AGN (LLAGN) with BH masses between $100-10^6M_\mathrm{\odot}$. All X-ray detected sources (plus 6 additional sources) show He~II$\lambda4686$ emission and a broad component of the H$α$ emission line, indicating winds. The line widths of the broad H$α$ and He II$\lambda4686$ emitting gas clouds are weakly correlated ($R^{2}=0.15$), suggesting He II$\lambda4686$ emission is inconsistent with winds from super-Eddington accretors. However, the ratio of X-ray luminosity to star formation rate shows an anti-correlation with metallicity in 5 out of 9 X-ray detected sources, implying ultraluminous X-ray sources are key contributors to the observed X-ray luminosity. This could be due to super-Eddington accretors or IMBH. The X-ray emission is much higher than that produced by Wolf-Rayet stars and supernovae-driven winds. Thus, the X-ray luminosity in these 9 sources can only be explained by black holes with masses over $100~M_\mathrm{\odot}$. Our findings suggest the presence of LLAGN in these galaxies, with broad H$α$ line widths implying BH masses of $10^4-10^6M_\mathrm{\odot}$. Given Green Peas' role as significant Lyman Continuum leakers, LLAGN in these galaxies could have contributed significantly to cosmic reionization.

astro-ph.GA↗

arXiv2024

CDAD-Net: Bridging Domain Gaps in Generalized Category Discovery

In Generalized Category Discovery (GCD), we cluster unlabeled samples of known and novel classes, leveraging a training dataset of known classes. A salient challenge arises due to domain shifts between these datasets. To address this, we present a novel setting: Across Domain Generalized Category Discovery (AD-GCD) and bring forth CDAD-NET (Class Discoverer Across Domains) as a remedy. CDAD-NET is architected to synchronize potential known class samples across both the labeled (source) and unlabeled (target) datasets, while emphasizing the distinct categorization of the target data. To facilitate this, we propose an entropy-driven adversarial learning strategy that accounts for the distance distributions of target samples relative to source-domain class prototypes. Parallelly, the discriminative nature of the shared space is upheld through a fusion of three metric learning objectives. In the source domain, our focus is on refining the proximity between samples and their affiliated class prototypes, while in the target domain, we integrate a neighborhood-centric contrastive learning mechanism, enriched with an adept neighborsmining approach. To further accentuate the nuanced feature interrelation among semantically aligned images, we champion the concept of conditional image inpainting, underscoring the premise that semantically analogous images prove more efficacious to the task than their disjointed counterparts. Experimentally, CDAD-NET eclipses existing literature with a performance increment of 8-15% on three AD-GCD benchmarks we present.

cs.CV↗

arXiv2024

Unknown Prompt, the only Lacuna: Unveiling CLIP's Potential for Open Domain Generalization

We delve into Open Domain Generalization (ODG), marked by domain and category shifts between training's labeled source and testing's unlabeled target domains. Existing solutions to ODG face limitations due to constrained generalizations of traditional CNN backbones and errors in detecting target open samples in the absence of prior knowledge. Addressing these pitfalls, we introduce ODG-CLIP, harnessing the semantic prowess of the vision-language model, CLIP. Our framework brings forth three primary innovations: Firstly, distinct from prevailing paradigms, we conceptualize ODG as a multi-class classification challenge encompassing both known and novel categories. Central to our approach is modeling a unique prompt tailored for detecting unknown class samples, and to train this, we employ a readily accessible stable diffusion model, elegantly generating proxy images for the open class. Secondly, aiming for domain-tailored classification (prompt) weights while ensuring a balance of precision and simplicity, we devise a novel visual stylecentric prompt learning mechanism. Finally, we infuse images with class-discriminative knowledge derived from the prompt space to augment the fidelity of CLIP's visual embeddings. We introduce a novel objective to safeguard the continuity of this infused semantic intel across domains, especially for the shared classes. Through rigorous testing on diverse datasets, covering closed and open-set DG contexts, ODG-CLIP demonstrates clear supremacy, consistently outpacing peers with performance boosts between 8%-16%. Code will be available at https://github.com/mainaksingha01/ODG-CLIP.

cs.CV↗

arXiv2023

StyLIP: Multi-Scale Style-Conditioned Prompt Learning for CLIP-based Domain Generalization

Large-scale foundation models, such as CLIP, have demonstrated impressive zero-shot generalization performance on downstream tasks, leveraging well-designed language prompts. However, these prompt learning techniques often struggle with domain shift, limiting their generalization capabilities. In our study, we tackle this issue by proposing StyLIP, a novel approach for Domain Generalization (DG) that enhances CLIP's classification performance across domains. Our method focuses on a domain-agnostic prompt learning strategy, aiming to disentangle the visual style and content information embedded in CLIP's pre-trained vision encoder, enabling effortless adaptation to novel domains during inference. To achieve this, we introduce a set of style projectors that directly learn the domain-specific prompt tokens from the extracted multi-scale style features. These generated prompt embeddings are subsequently combined with the multi-scale visual content features learned by a content projector. The projectors are trained in a contrastive manner, utilizing CLIP's fixed vision and text backbones. Through extensive experiments conducted in five different DG settings on multiple benchmark datasets, we consistently demonstrate that StyLIP outperforms the current state-of-the-art (SOTA) methods.

cs.CV↗

arXiv2023

C-SAW: Self-Supervised Prompt Learning for Image Generalization in Remote Sensing

We focus on domain and class generalization problems in analyzing optical remote sensing images, using the large-scale pre-trained vision-language model (VLM), CLIP. While contrastively trained VLMs show impressive zero-shot generalization performance, their effectiveness is limited when dealing with diverse domains during training and testing. Existing prompt learning techniques overlook the importance of incorporating domain and content information into the prompts, which results in a drop in performance while dealing with such multi-domain data. To address these challenges, we propose a solution that ensures domain-invariant prompt learning while enhancing the expressiveness of visual features. We observe that CLIP's vision encoder struggles to identify contextual image information, particularly when image patches are jumbled up. This issue is especially severe in optical remote sensing images, where land-cover classes exhibit well-defined contextual appearances. To this end, we introduce C-SAW, a method that complements CLIP with a self-supervised loss in the visual space and a novel prompt learning technique that emphasizes both visual domain and content-specific features. We keep the CLIP backbone frozen and introduce a small set of projectors for both the CLIP encoders to train C-SAW contrastively. Experimental results demonstrate the superiority of C-SAW across multiple remote sensing benchmarks and different generalization tasks.

cs.CV↗

arXiv2023

HAVE-Net: Hallucinated Audio-Visual Embeddings for Few-Shot Classification with Unimodal Cues

Recognition of remote sensing (RS) or aerial images is currently of great interest, and advancements in deep learning algorithms added flavor to it in recent years. Occlusion, intra-class variance, lighting, etc., might arise while training neural networks using unimodal RS visual input. Even though joint training of audio-visual modalities improves classification performance in a low-data regime, it has yet to be thoroughly investigated in the RS domain. Here, we aim to solve a novel problem where both the audio and visual modalities are present during the meta-training of a few-shot learning (FSL) classifier; however, one of the modalities might be missing during the meta-testing stage. This problem formulation is pertinent in the RS domain, given the difficulties in data acquisition or sensor malfunctioning. To mitigate, we propose a novel few-shot generative framework, Hallucinated Audio-Visual Embeddings-Network (HAVE-Net), to meta-train cross-modal features from limited unimodal data. Precisely, these hallucinated features are meta-learned from base classes and used for few-shot classification on novel classes during the inference phase. The experimental results on the benchmark ADVANCE and AudioSetZSL datasets show that our hallucinated modality augmentation strategy for few-shot classification outperforms the classifier performance trained with the real multimodal information at least by 0.8-2%.

cs.CV↗

arXiv2023

GOPro: Generate and Optimize Prompts in CLIP using Self-Supervised Learning

Large-scale foundation models, such as CLIP, have demonstrated remarkable success in visual recognition tasks by embedding images in a semantically rich space. Self-supervised learning (SSL) has also shown promise in improving visual recognition by learning invariant features. However, the combination of CLIP with SSL is found to face challenges due to the multi-task framework that blends CLIP's contrastive loss and SSL's loss, including difficulties with loss weighting and inconsistency among different views of images in CLIP's output space. To overcome these challenges, we propose a prompt learning-based model called GOPro, which is a unified framework that ensures similarity between various augmented views of input images in a shared image-text embedding space, using a pair of learnable image and text projectors atop CLIP, to promote invariance and generalizability. To automatically learn such prompts, we leverage the visual content and style primitives extracted from pre-trained CLIP and adapt them to the target task. In addition to CLIP's cross-domain contrastive loss, we introduce a visual contrastive loss and a novel prompt consistency loss, considering the different views of the images. GOPro is trained end-to-end on all three loss objectives, combining the strengths of CLIP and SSL in a principled manner. Empirical evaluations demonstrate that GOPro outperforms the state-of-the-art prompting techniques on three challenging domain generalization tasks across multiple benchmarks by a significant margin. Our code is available at https://github.com/mainaksingha01/GOPro.

cs.CV↗