arXiv subjects

Anjan Dutta

Publications and source records attributed to Anjan Dutta.

At least 37 records · Page 2Linked to original sources

arXiv2023

Torque reversal and cyclotron absorption feature in HMXB 4U 1538-522

We present a comprehensive timing and spectral analysis of the HMXB 4U 1538-522 by using the Nuclear Spectroscopic Telescope Array (NuSTAR) observatory data. Using three archived observations made between 2019 and 2021, we have detected $\sim $ 526 s coherent pulsations up to 60 keV. We have found an instantaneous spin-down rate of $\dot{P} = 6.6_{-6.0}^{+2.4} \times 10^{-6}$ s s$^{-1}$ during the first observation. The pulse profiles had a double peaked structure consisting of a broad primary peak and an energy dependent, weak secondary peak. We have also analysed the long-term spin-period evolution of 4U 1538-522 from data spanning more than four decades, including the data from Fermi/GBM. Based on the recent spin trends, we have found that the third torque reversal in 4U 1538-522 happened around MJD 58800. The source is currently spinning up with $\dot{P} = -1.9(1) \times 10^{-9}$ s s$^{-1}$. We also report a periodic fluctuation in the spin-period of 4U 1538-522. The broad-band persistent spectra can be described with a blackbody component and either powerlaw or Comptonization component along with a Fe K$_α$ line at 6.4 keV and a cyclotron absorption feature around 22 keV. We have also found a relatively weak absorption feature around 27 keV in the persistent spectra of 4U 1538-522 in all three observations. We have estimated a magnetic field strength of $1.84_{-0.06}^{+0.04} (1+z) \times 10^{12}$ and $2.33_{-0.24}^{+0.15} (1+z) \times 10^{12}$ G for the two features, respectively.

astro-ph.HE↗

arXiv2023

Data-Free Sketch-Based Image Retrieval

Rising concerns about privacy and anonymity preservation of deep learning models have facilitated research in data-free learning (DFL). For the first time, we identify that for data-scarce tasks like Sketch-Based Image Retrieval (SBIR), where the difficulty in acquiring paired photos and hand-drawn sketches limits data-dependent cross-modal learning algorithms, DFL can prove to be a much more practical paradigm. We thus propose Data-Free (DF)-SBIR, where, unlike existing DFL problems, pre-trained, single-modality classification models have to be leveraged to learn a cross-modal metric-space for retrieval without access to any training data. The widespread availability of pre-trained classification models, along with the difficulty in acquiring paired photo-sketch datasets for SBIR justify the practicality of this setting. We present a methodology for DF-SBIR, which can leverage knowledge from models independently trained to perform classification on photos and sketches. We evaluate our model on the Sketchy, TU-Berlin, and QuickDraw benchmarks, designing a variety of baselines based on state-of-the-art DFL literature, and observe that our method surpasses all of them by significant margins. Our method also achieves mAPs competitive with data-dependent approaches, all the while requiring no training data. Implementation is available at \url{https://github.com/abhrac/data-free-sbir}.

cs.CV↗

arXiv2022

Cross-Modal Fusion Distillation for Fine-Grained Sketch-Based Image Retrieval

Representation learning for sketch-based image retrieval has mostly been tackled by learning embeddings that discard modality-specific information. As instances from different modalities can often provide complementary information describing the underlying concept, we propose a cross-attention framework for Vision Transformers (XModalViT) that fuses modality-specific information instead of discarding them. Our framework first maps paired datapoints from the individual photo and sketch modalities to fused representations that unify information from both modalities. We then decouple the input space of the aforementioned modality fusion network into independent encoders of the individual modalities via contrastive and relational cross-modal knowledge distillation. Such encoders can then be applied to downstream tasks like cross-modal retrieval. We demonstrate the expressive capacity of the learned representations by performing a wide range of experiments and achieving state-of-the-art results on three fine-grained sketch-based image retrieval benchmarks: Shoe-V2, Chair-V2 and Sketchy. Implementation is available at https://github.com/abhrac/xmodal-vit.

cs.CV↗

arXiv2022

Relational Proxies: Emergent Relationships as Fine-Grained Discriminators

Fine-grained categories that largely share the same set of parts cannot be discriminated based on part information alone, as they mostly differ in the way the local parts relate to the overall global structure of the object. We propose Relational Proxies, a novel approach that leverages the relational information between the global and local views of an object for encoding its semantic label. Starting with a rigorous formalization of the notion of distinguishability between fine-grained categories, we prove the necessary and sufficient conditions that a model must satisfy in order to learn the underlying decision boundaries in the fine-grained setting. We design Relational Proxies based on our theoretical findings and evaluate it on seven challenging fine-grained benchmark datasets and achieve state-of-the-art results on all of them, surpassing the performance of all existing works with a margin exceeding 4% in some cases. We also experimentally validate our theory on fine-grained distinguishability and obtain consistent results across multiple benchmarks. Implementation is available at https://github.com/abhrac/relational-proxies.

cs.CV↗

arXiv2022

Broad-band spectral analysis of LMXB 2S 0921-63 with Suzaku

We present the broad-band spectral analysis of the low-mass X-ray binary 2S 0921-63 by using the Suzaku archival data covering the orbital phase between 0.31 and 1.16 during four close observations. It is the first time that a broad-band spectral analysis of 2S 0921-63 has been done up to 25 keV. The 0.5-10 keV XIS count rate varied between $\sim$ 1 and $\sim$ 5 counts s$^{-1}$ during the observations. A partial X-ray eclipse and broad post-eclipse intensity dip were observed during the observations. The X-ray emission hardened marginally during the intensity dip. We have modelled the source spectra by simultaneously fitting the XIS and HXD-PIN spectra for each of the four observations. The broad-band spectra of the source can be described by a model comprising a very hot blackbody having temperature, $kT_{\rm BB} \approx$ 1.66 - 2.13 keV, a high-energy cutoff power law, and an Fe emission line at $E_{\rm line} \sim$ 6.7 keV. A second model, accounting for the Comptonization of the thermal emission from accretion disc along with an Fe emission line, describes the broad-band spectra of 2S 0921-63 equally well.

astro-ph.HE↗

arXiv2022

Abstracting Sketches through Simple Primitives

Humans show high-level of abstraction capabilities in games that require quickly communicating object information. They decompose the message content into multiple parts and communicate them in an interpretable protocol. Toward equipping machines with such capabilities, we propose the Primitive-based Sketch Abstraction task where the goal is to represent sketches using a fixed set of drawing primitives under the influence of a budget. To solve this task, our Primitive-Matching Network (PMN), learns interpretable abstractions of a sketch in a self supervised manner. Specifically, PMN maps each stroke of a sketch to its most similar primitive in a given set, predicting an affine transformation that aligns the selected primitive to the target stroke. We learn this stroke-to-primitive mapping end-to-end with a distance-transform loss that is minimal when the original sketch is precisely reconstructed with the predicted primitives. Our PMN abstraction empirically achieves the highest performance on sketch recognition and sketch-based image retrieval given a communication budget, while at the same time being highly interpretable. This opens up new possibilities for sketch analysis, such as comparing sketches by extracting the most relevant primitives that define an object category. Code is available at https://github.com/ExplainableML/sketch-primitives.

cs.CV↗

arXiv2022

Discovery of cyclotron and narrow Fe K$_α$ lines in HMXB GRO J1750-27

We report on timing and spectral analysis of transient Be X-ray pulsar GRO J1750-27 by using the Nuclear Spectroscopic Telescope Array (NuSTAR) observation from September 2021. This is the fourth outburst of the system since 1995. The NuSTAR observation was performed during the rising phase of the outburst. Pulsations at a period of 4.450710(1) s were observed in the 3-60 keV energy range. The average pulse profile comprised of a broad peak with a weak secondary peak which evolved with energy. We did not find any appreciable variation in the X-ray emission during this observation. The broad-band phase-averaged spectrum is described by a blackbody, a powerlaw or Comptonization component. We report discovery of Fe K$_α$ line at 6.4 keV along with presence of two cyclotron resonant scattering features around 36 and 42 keV. These lines indicate a magnetic field strength of $3.7_{-0.3}^{+0.1} \times 10^{12}$ and $4.4 \pm 0.1 \times 10^{12}$ G for the neutron star. We have estimated a source distance of $\sim$ 13.6-16.4 kpc based on the accretion-disc torque models.

astro-ph.HE↗

arXiv2022

BDA-SketRet: Bi-Level Domain Adaptation for Zero-Shot SBIR

The efficacy of zero-shot sketch-based image retrieval (ZS-SBIR) models is governed by two challenges. The immense distributions-gap between the sketches and the images requires a proper domain alignment. Moreover, the fine-grained nature of the task and the high intra-class variance of many categories necessitates a class-wise discriminative mapping among the sketch, image, and the semantic spaces. Under this premise, we propose BDA-SketRet, a novel ZS-SBIR framework performing a bi-level domain adaptation for aligning the spatial and semantic features of the visual data pairs progressively. In order to highlight the shared features and reduce the effects of any sketch or image-specific artifacts, we propose a novel symmetric loss function based on the notion of information bottleneck for aligning the semantic features while a cross-entropy-based adversarial loss is introduced to align the spatial feature maps. Finally, our CNN-based model confirms the discriminativeness of the shared latent space through a novel topology-preserving semantic projection network. Experimental results on the extended Sketchy, TU-Berlin, and QuickDraw datasets exhibit sharp improvements over the literature.

cs.CV↗

arXiv2021

Timing and Spectral Analysis of HMXB OAO 1657-415 with NuSTAR

This work presents a comprehensive timing and spectral analysis of high-mass X-ray binary pulsar, OAO 1657-415 by using the observation made with Nuclear Spectroscopic Telescope Array (NuSTAR) on June 2019. During this observation, OAO 1657-415 exhibited X-ray variability by a factor of about 3. X-ray pulsations at 37.03322(14) s were observed up to 70 keV. OAO 1657-415 was undergoing a spin-down phase with $\dot{P} = 9(1) \times 10^{-8}$ s s$^{-1}$. This is an order of about 100 larger than the long-term spin-up rate. The pulse profile evolved marginally during the observation. We have discussed the long-term pulse period history of the source spanning a time-base of 43 years, including the latest Fermi/GBM data. The 3-70 keV source spectrum is described by a partially covered cutoff power-law, an Fe K$_α$ line at 6.4 keV and a Compton shoulder at 6.3 keV. We report the presence of a cyclotron absorption feature around 40 keV, which is indicative of a surface magnetic field strength of $3.59 \pm 0.06 \ (1 + z)^{-1} \times 10^{12}$ and $3.29_{-0.22}^{+0.23} \ (1 + z)^{-1} \times 10^{12}$ G. This work shows the first robust presence of cyclotron absorption feature in the source.

astro-ph.HE↗

arXiv2021

Implicit and Explicit Attention for Zero-Shot Learning

Most of the existing Zero-Shot Learning (ZSL) methods focus on learning a compatibility function between the image representation and class attributes. Few others concentrate on learning image representation combining local and global features. However, the existing approaches still fail to address the bias issue towards the seen classes. In this paper, we propose implicit and explicit attention mechanisms to address the existing bias problem in ZSL models. We formulate the implicit attention mechanism with a self-supervised image angle rotation task, which focuses on specific image features aiding to solve the task. The explicit attention mechanism is composed with the consideration of a multi-headed self-attention mechanism via Vision Transformer model, which learns to map image features to semantic space during the training stage. We conduct comprehensive experiments on three popular benchmarks: AWA2, CUB and SUN. The performance of our proposed attention mechanisms has proved its effectiveness, and has achieved the state-of-the-art harmonic mean on all the three datasets.

cs.CV↗

arXiv2021

Concurrent Discrimination and Alignment for Self-Supervised Feature Learning

Existing self-supervised learning methods learn representation by means of pretext tasks which are either (1) discriminating that explicitly specify which features should be separated or (2) aligning that precisely indicate which features should be closed together, but ignore the fact how to jointly and principally define which features to be repelled and which ones to be attracted. In this work, we combine the positive aspects of the discriminating and aligning methods, and design a hybrid method that addresses the above issue. Our method explicitly specifies the repulsion and attraction mechanism respectively by discriminative predictive task and concurrently maximizing mutual information between paired views sharing redundant information. We qualitatively and quantitatively show that our proposed model learns better features that are more effective for the diverse downstream tasks ranging from classification to semantic segmentation. Our experiments on nine established benchmarks show that the proposed model consistently outperforms the existing state-of-the-art results of self-supervised and transfer learning protocol.

cs.CV↗

arXiv2021

Multi-Head Self-Attention via Vision Transformer for Zero-Shot Learning

Zero-Shot Learning (ZSL) aims to recognise unseen object classes, which are not observed during the training phase. The existing body of works on ZSL mostly relies on pretrained visual features and lacks the explicit attribute localisation mechanism on images. In this work, we propose an attention-based model in the problem settings of ZSL to learn attributes useful for unseen class recognition. Our method uses an attention mechanism adapted from Vision Transformer to capture and learn discriminative attributes by splitting images into small patches. We conduct experiments on three popular ZSL benchmarks (i.e., AWA2, CUB and SUN) and set new state-of-the-art harmonic mean results {on all the three datasets}, which illustrate the effectiveness of our proposed method.

cs.CV↗

arXiv2021

Broad-band spectral study of LMXB black hole candidate 4U 1957+11 with NuSTAR

We present here the results of broadband spectral analysis of low-mass X-ray binary and a black hole candidate 4U 1957+11. The source was observed nine times with the Nuclear Spectroscopic Telescope Array (NuSTAR) between 2018 September and 2019 November. During these observations, the spectral state of 4U 1957+11 evolved marginally. The disc dominant spectra are well described with a hot, multicolour disc blackbody with disc temperature varying in the range $kT_{\rm in} \sim$ 1.35-1.86 keV and a non-thermal component having a steep slope ($Γ=$ 2-3). A broad Fe emission line feature (5-8 keV) was observed in the spectra of all the observations. The relativistic disc model was used to study the effect of distance, inclination, and the black hole mass on its spin. Simulations indicate a higher spin for smaller distances and lower black hole mass. At smaller distances and higher mass, spin is maximum and almost independent of the distance. An inverse correlation exists between the spin and the spectral hardening factor for all the cases. The system prefers a moderate spin of about 0.85 for black hole masses between 4-6 M_sun for a 7 kpc distance.

astro-ph.HE↗

arXiv2020

Bookworm continual learning: beyond zero-shot learning and continual learning

We propose bookworm continual learning(BCL), a flexible setting where unseen classes can be inferred via a semantic model, and the visual model can be updated continually. Thus BCL generalizes both continual learning (CL) and zero-shot learning (ZSL). We also propose the bidirectional imagination (BImag) framework to address BCL where features of both past and future classes are generated. We observe that conditioning the feature generator on attributes can actually harm the continual learning ability, and propose two variants (joint class-attribute conditioning and asymmetric generation) to alleviate this problem.

cs.CV↗

arXiv2020

Doodle to Search: Practical Zero-Shot Sketch-based Image Retrieval

In this paper, we investigate the problem of zero-shot sketch-based image retrieval (ZS-SBIR), where human sketches are used as queries to conduct retrieval of photos from unseen categories. We importantly advance prior arts by proposing a novel ZS-SBIR scenario that represents a firm step forward in its practical application. The new setting uniquely recognizes two important yet often neglected challenges of practical ZS-SBIR, (i) the large domain gap between amateur sketch and photo, and (ii) the necessity for moving towards large-scale retrieval. We first contribute to the community a novel ZS-SBIR dataset, QuickDraw-Extended, that consists of 330,000 sketches and 204,000 photos spanning across 110 categories. Highly abstract amateur human sketches are purposefully sourced to maximize the domain gap, instead of ones included in existing datasets that can often be semi-photorealistic. We then formulate a ZS-SBIR framework to jointly model sketches and photos into a common embedding space. A novel strategy to mine the mutual information among domains is specifically engineered to alleviate the domain gap. External semantic knowledge is further embedded to aid semantic transfer. We show that, rather surprisingly, retrieval performance significantly outperforms that of state-of-the-art on existing datasets that can already be achieved using a reduced version of our model. We further demonstrate the superior performance of our full model by comparing with a number of alternatives on the newly proposed dataset. The new dataset, plus all training and testing code of our model, will be publicly released to facilitate future research

cs.CV↗

arXiv2020

Semantically Tied Paired Cycle Consistency for Any-Shot Sketch-based Image Retrieval

Low-shot sketch-based image retrieval is an emerging task in computer vision, allowing to retrieve natural images relevant to hand-drawn sketch queries that are rarely seen during the training phase. Related prior works either require aligned sketch-image pairs that are costly to obtain or inefficient memory fusion layer for mapping the visual information to a semantic space. In this paper, we address any-shot, i.e. zero-shot and few-shot, sketch-based image retrieval (SBIR) tasks, where we introduce the few-shot setting for SBIR. For solving these tasks, we propose a semantically aligned paired cycle-consistent generative adversarial network (SEM-PCYC) for any-shot SBIR, where each branch of the generative adversarial network maps the visual information from sketch and image to a common semantic space via adversarial training. Each of these branches maintains cycle consistency that only requires supervision at the category level, and avoids the need of aligned sketch-image pairs. A classification criteria on the generators' outputs ensures the visual to semantic space mapping to be class-specific. Furthermore, we propose to combine textual and hierarchical side information via an auto-encoder that selects discriminating side information within a same end-to-end model. Our results demonstrate a significant boost in any-shot SBIR performance over the state-of-the-art on the extended version of the challenging Sketchy, TU-Berlin and QuickDraw datasets.

cs.CV↗

arXiv2020

Broad-band spectral analysis of LMXB XTE J1710-281 with Suzaku

This work presents the broad-band time-averaged spectral analysis of neutron star low-mass X-ray binary, XTE J1710-281 by using the Suzaku archival data. The source was in a hard or an intermediate spectral state during this observation. This is the first time that a detailed spectral analysis of the persistent emission spectra of XTE J1710-281 has been done up to 30 keV with improved constraints on its spectral parameters. By simultaneously fitting the XIS (0.6-9.0 keV) and the HXD-PIN (15.0-30.0 keV) data, we have modelled the persistent spectrum of the source with models comprising a soft component from accretion disc and/or neutron star surface/boundary layer and a hard Comptonizing component. The 0.6-30 keV continuum with neutral absorber can be described by a multi-colour disc blackbody with an inner disc temperature of $kT_{\rm disc} = 0.28$ keV, which is significantly Comptonized by the hot electron cloud with electron temperature of $kT_{\rm e} \approx 5$ keV and described by photon index $Γ= 1.86$. A more complex three-component model comprising a multi-colour disc blackbody $\approx 0.30$ keV, single temperature blackbody $\approx 0.65$ keV and Comptonization from the disc, partially absorbed (about 38 per cent) by an ionized absorber (log($ξ$) $\approx$ 4) describes the broad-band spectrum equally well.

astro-ph.HE↗

arXiv2020

Learning Robust Representations via Multi-View Information Bottleneck

The information bottleneck principle provides an information-theoretic method for representation learning, by training an encoder to retain all information which is relevant for predicting the label while minimizing the amount of other, excess information in the representation. The original formulation, however, requires labeled data to identify the superfluous information. In this work, we extend this ability to the multi-view unsupervised setting, where two views of the same underlying entity are provided but the label is unknown. This enables us to identify superfluous information as that not shared by both views. A theoretical analysis leads to the definition of a new multi-view model that produces state-of-the-art results on the Sketchy dataset and label-limited versions of the MIR-Flickr dataset. We also extend our theory to the single-view setting by taking advantage of standard data augmentation techniques, empirically showing better generalization capabilities when compared to common unsupervised approaches for representation learning.

cs.LG↗