arXiv subjects

Zekang Zhang

Publications and source records attributed to Zekang Zhang.

7 recordsLinked to original sources

arXiv2026

FlowSeg: Dynamic Semantic Guidance for LLM-Conditioned Segmentation

LLM-conditioned segmentation has recently advanced rapidly by coupling large language models with iterative mask generation frameworks. However, we identify a persistent failure mode in current propose-then-select pipelines. Although high-quality mask candidates are often generated, the final prediction may fail to match the given linguistic condition. This failure arises because language semantics are typically used as static prompts or post-hoc matching signals, rather than participating in the iterative mask generation process. Through systematic analysis, we show that many errors stem from semantic misalignment rather than poor mask quality. To address this issue, we propose FlowSeg, which introduces dynamic semantic guidance via a bidirectional semantic flow between intermediate decoding states and LLM-derived condition embeddings throughout the generation process. Language conditions actively guide mask refinement at each stage, while condition embeddings are progressively updated by emerging visual evidence. This design yields semantically grounded mask representations and visually aligned language conditions, enabling more reliable matching. We further incorporate a lightweight boundary-aware refinement to selectively enhance uncertain regions without perturbing confident interiors. Extensive experiments on referring expression segmentation and reasoning segmentation tasks demonstrate that FlowSeg consistently improves language-mask alignment and achieves state-of-the-art performance. Project page: https://zkzhang98.github.io/FlowSeg_page

cs.CV↗

arXiv2025

Emulating redshift mixing due to blending in weak gravitational lensing

Galaxies whose images overlap in the focal plane of a telescope, commonly referred to as blends, are often located at different redshifts. Blending introduces a challenge to weak-lensing cosmology probes since such blends are subject to shear signals from multiple redshifts. This effect can be described by joining shear bias and redshift characterisation in the effective redshift distribution, $n_{\gamma}(z)$, which includes the response of apparent shapes of detected objects to shear of galaxies at redshift, $z$. In this work, we propose a novel method to correct $n_{\gamma}(z)$ for redshift-mixed blending by emulating the shear response to neighbouring galaxies. We designed a `half-sky-shearing' simulation with Subaru Hyper Suprime Cam (HSC) wide-like specifications, which allowed us to extract the response of a detected object's measured ellipticity to the shearing of neighbouring galaxies among numerous galaxy pairs. We demonstrate the feasibility of accurately emulating these pairwise responses and validate the robustness of our approach under varying observing conditions and galaxy population uncertainties. We find that the effective redshift of sources at the high-redshift tail of the distribution is about 0.05 lower than expected when the effect is not modelled. Given adequately processed image simulations, our correction method can be readily incorporated into future cosmological analyses to mitigate this source of systematic error.

astro-ph.CO↗

arXiv2024

Forklens: Accurate weak-lensing shear measurement with deep learning

Weak gravitational lensing is one of the most important probes of the nature of dark matter and dark energy. In order to extract cosmological information from next-generation weak lensing surveys (e.g., Euclid, Roman, LSST, and CSST) as much as possible, accurate measurements of weak lensing shear are required. There are existing algorithms to measure the weak lensing shear on imaging data, which have been successfully applied in previous surveys. In the meantime, machine learning (ML) has been widely recognized in various astrophysics applications in modeling and observations. In this work, we present a fully deep-learning-based approach to measuring weak lensing shear accurately. Our approach comprises two modules. The first one contains a convolutional neural network (CNN) with two branches for taking galaxy images and point spread function (PSF) simultaneously, and the output of this module includes the galaxy's magnitude, size, and shape. The second module includes a multiple-layer neural network (NN) to calibrate weak-lensing shear measurements. We name the program Forklens and make it publicly available online. Applying Forklens to CSST-like mock images, we achieve consistent accuracy with traditional approaches (such as moment-based measurement and forward model fitting) on the sources with high signal-to-noise ratios (S/N, > 20). For the sources with S/N < 10, Forklens exhibits an $\sim 36\%$ higher Pearson coefficient on galaxy ellipticity measurements. After adopting galaxy weighting, the shear measurements with Forklens deliver accuracy levels to $0.2\%$. The whole procedure of Forklens is automated and costs about $0.7$ milliseconds per galaxy, which is appropriate for adequately taking advantage of the sky coverage and depth of the upcoming weak lensing surveys.

astro-ph.CO↗

arXiv2023

CoinSeg: Contrast Inter- and Intra- Class Representations for Incremental Segmentation

Class incremental semantic segmentation aims to strike a balance between the model's stability and plasticity by maintaining old knowledge while adapting to new concepts. However, most state-of-the-art methods use the freeze strategy for stability, which compromises the model's plasticity.In contrast, releasing parameter training for plasticity could lead to the best performance for all categories, but this requires discriminative feature representation.Therefore, we prioritize the model's plasticity and propose the Contrast inter- and intra-class representations for Incremental Segmentation (CoinSeg), which pursues discriminative representations for flexible parameter tuning. Inspired by the Gaussian mixture model that samples from a mixture of Gaussian distributions, CoinSeg emphasizes intra-class diversity with multiple contrastive representation centroids. Specifically, we use mask proposals to identify regions with strong objectness that are likely to be diverse instances/centroids of a category. These mask proposals are then used for contrastive representations to reinforce intra-class diversity. Meanwhile, to avoid bias from intra-class diversity, we also apply category-level pseudo-labels to enhance category-level consistency and inter-category diversity. Additionally, CoinSeg ensures the model's stability and alleviates forgetting through a specific flexible tuning strategy. We validate CoinSeg on Pascal VOC 2012 and ADE20K datasets with multiple incremental scenarios and achieve superior results compared to previous state-of-the-art methods, especially in more challenging and realistic long-term scenarios. Code is available at https://github.com/zkzhang98/CoinSeg.

cs.CV↗

arXiv2023

HybPSF: Hybrid PSF reconstruction for the observed JWST NIRCam image

The James Webb Space Telescope (JWST) ushers in a new era of astronomical observation and discovery, offering unprecedented precision in a variety of measurements such as photometry, astrometry, morphology, and shear measurement. Accurate point spread function (PSF) models are crucial for many of these measurements. In this paper, we introduce a hybrid PSF construction method called HybPSF for JWST NIRCam imaging data. HybPSF combines the WebbPSF software, which simulates the PSF for JWST, with observed data to produce more accurate and reliable PSF models. We apply this method to the SMACS J0723 imaging data and construct supplementary structures from residuals obtained by subtracting the WebbPSF PSF model from the data. Our results show that HybPSF significantly reduces discrepancies between the PSF model and the data compared to WebbPSF. Specifically, the PSF shape parameter ellipticity and size comparisons indicate that HybPSF improves precision by a factor of approximately 10 for \$R^2\$ and \$50\%\$ for \$e\$. This improvement has important implications for astronomical measurements using JWST NIRCam imaging data.

astro-ph.IM↗

arXiv2023

Mining Unseen Classes via Regional Objectness: A Simple Baseline for Incremental Segmentation

Incremental or continual learning has been extensively studied for image classification tasks to alleviate catastrophic forgetting, a phenomenon that earlier learned knowledge is forgotten when learning new concepts. For class incremental semantic segmentation, such a phenomenon often becomes much worse due to the background shift, i.e., some concepts learned at previous stages are assigned to the background class at the current training stage, therefore, significantly reducing the performance of these old concepts. To address this issue, we propose a simple yet effective method in this paper, named Mining unseen Classes via Regional Objectness for Segmentation (MicroSeg). Our MicroSeg is based on the assumption that background regions with strong objectness possibly belong to those concepts in the historical or future stages. Therefore, to avoid forgetting old knowledge at the current training stage, our MicroSeg first splits the given image into hundreds of segment proposals with a proposal generator. Those segment proposals with strong objectness from the background are then clustered and assigned newly-defined labels during the optimization. In this way, the distribution characterizes of old concepts in the feature space could be better perceived, relieving the catastrophic forgetting caused by the background shift accordingly. Extensive experiments on Pascal VOC and ADE20K datasets show competitive results with state-of-the-art, well validating the effectiveness of the proposed MicroSeg.

cs.CV↗

arXiv2022

Impact of the turnover in the high-z galaxy luminosity function on the 21-cm signal during Cosmic Dawn and Epoch of Reionization

The shape of the faint-end of the high-z galaxy luminosity function (LF) informs early star formation and reionization physics during the Cosmic Dawn and Epoch of Reionization. Until recently, based on the strong gravitational lensing cluster deep surveys, the Hubble Frontier Fields (HFF) has found a potential turnover in the ultraviolet (UV) LF at z$\sim$6. In this paper, we analyze the contribution of extremely faint galaxies with the magnitude larger than the turnover magnitude in LF to cosmic reionization. We apply the measurement from HFF to our suppressed star formation efficiency model, including three free parameters: halo mass threshold $M_t$, curvature parameter $β$ and a UV conversion factor $l_{\rm UV}$. According to our fit of 68\% confidence level, the high-redshift star formation in haloes smaller than $ M_t=1.82^{+2.86}_{-1.08}\times10^{10} \rm M_{\odot}$ is found to be dampened. The turnover magnitude $\rm \gtrsim -13.99-2.45$, correspondingly the halo mass $\lesssim(4.57+20.03)\times10^{9} \rm M_{\odot}$. We find that the absorption trough in the global 21-cm signal is sensitive to our SFE model parameters. Together with ($β$, $l_{\rm UV}$) = ($2.17^{+2.42}_{-1.72}$, $9.33^{+0.43}_{-0.42} \rm ~erg~yr ~s^{-1}M_{\odot}^{-1})$, the trough locates at $\sim$ $134^{+10}_{-17}$ $\rm MHz$ with an amplitude of $\sim$ $-237^{-6}_{+7}$ $\rm mK$, compared to (106\rm MHz, -212\rm mK) in the absence of turnover. Besides, we find that the star formation of faint galaxies has also an impact on the 21-cm power spectra. The best fitting peak power decreases by $\sim4\%$ and shifts towards smaller scales from $0.88 h \rm Mpc^{-1}$ to $0.91 h \rm Mpc^{-1}$. According to our calculation, such impact is distinguishable with the forthcoming Square Kilometre Array.

astro-ph.GA↗