Search

In autonomous driving, deep models have shown remarkable performance across various visual perception tasks with the demand of high-quality and huge-diversity training datasets. Such datasets are expected to cover various driving scenarios with adverse weather, lighting conditions and diverse moving objects. However, manually collecting these data presents huge challenges and expensive cost. With the rapid development of large generative models, we propose DriveDiTFit, a novel method for efficiently generating autonomous Driving data by Fine-tuning pre-trained Diffusion Transformers (DiTs). Specifically, DriveDiTFit utilizes a gap-driven modulation technique to carefully select and efficiently fine-tune a few parameters in DiTs according to the discrepancy between the pre-trained source data and the target driving data. Additionally, DriveDiTFit develops an effective weather and lighting condition embedding module to ensure diversity in the generated data, which is initialized by a nearest-semantic-similarity initialization approach. Through progressive tuning scheme to refined the process of detail generation in early diffusion process and enlarging the weights corresponding to small objects in training loss, DriveDiTFit ensures high-quality generation of small moving objects in the generated data. Extensive experiments conducted on driving datasets confirm that our method could efficiently produce diverse real driving data. The source codes will be available at https://github.com/TtuHamg/DriveDiTFit.

The metal content of galaxies is a direct probe of the baryon cycle. A hallmark example is the relationship between a galaxy's stellar mass, star formation rate (SFR), and gas-phase metallicity: the Fundamental Metallicity Relation (FMR). While low-redshift ($z\lesssim4$) observational studies suggest that the FMR is redshift-invariant, recent JWST data indicate deviations from this model. In this study, we utilize the FMR to predict the evolution of the normalisation of the mass-metallicity relation (MZR) using the cosmological simulations Illustris, IllustrisTNG, EAGLE, and SIMBA. Our findings demonstrate that a $z = 0$ calibrated FMR struggles to predict the evolution in the MZR of each simulation. To quantify the divergence of the predictions, we introduce the concepts of a ''static'' FMR, where the role of the SFR in setting the normalization of the MZR does not change with redshift, and a ''dynamic'' FMR, where the role of SFR evolves over time. We find static FMRs in Illustris and SIMBA and dynamic FMRs in IllustrisTNG and EAGLE. We suggest that the differences between these models likely points to the subtle differences in the implementation of the baryon cycle. Moreover, we echo recent JWST results at $z > 4$ by finding significant offsets from the FMR in IllustrisTNG and EAGLE, suggesting that the observed FMR may be dynamic as well. Overall, our findings imply that the current FMR framework neglects important variations in the baryon cycle through cosmic time., Comment: Submitted to MNRAS. 17 pages, 8 Figures. See also paper one of series (arXiv:2403.08856). Comments welcome

Incremental Learning (IL) aims to learn deep models on sequential tasks continually, where each new task includes a batch of new classes and deep models have no access to task-ID information at the inference time. Recent vast pre-trained models (PTMs) have achieved outstanding performance by prompt technique in practical IL without the old samples (rehearsal-free) and with a memory constraint (memory-constrained): Prompt-extending and Prompt-fixed methods. However, prompt-extending methods need a large memory buffer to maintain an ever-expanding prompt pool and meet an extra challenging prompt selection problem. Prompt-fixed methods only learn a single set of prompts on one of the incremental tasks and can not handle all the incremental tasks effectively. To achieve a good balance between the memory cost and the performance on all the tasks, we propose a Parameter-Efficient Cross-Task Prompt (PECTP) framework with Prompt Retention Module (PRM) and classifier Head Retention Module (HRM). To make the final learned prompts effective on all incremental tasks, PRM constrains the evolution of cross-task prompts' parameters from Outer Prompt Granularity and Inner Prompt Granularity. Besides, we employ HRM to inherit old knowledge in the previously learned classifier heads to facilitate the cross-task prompts' generalization ability. Extensive experiments show the effectiveness of our method. The source codes will be available at \url{https://github.com/RAIAN08/PECTP}.

Using adaptive optics with the Multi-Unit Spectroscopic Explorer (MUSE) on the Very Large Telescope (VLT), the Middle Ages Galaxy Properties with Integral Field Spectroscopy (MAGPI) survey allows us to study the spatially resolved Universe at a crucial time of ~4 Gyr ago ($z$ ~ 0.3) when simulations predict the greatest diversity in evolutionary pathways for galaxies. We investigate the radial trends in the star formation (SF) activity and luminosity-weighted stellar ages as a function of offset from the star-forming main sequence (SFMS) for a total of 294 galaxies. Using both H$\alpha$ emission and the 4000 Angstrom break (i.e., D4000) as star formation rate (SFR) tracers, we find overall flat radial profiles for galaxies lying on and above the SFMS, suggestive of physical processes that enhance/regulate SF throughout the entire galaxy disc. However, for galaxies lying below the SFMS, we find positive gradients in SF suggestive of inside-out quenching. Placing our results in context with results from other redshift regimes suggests an evolution in radial trends at $z$ ~ 0.3 for SF galaxies above the SFMS, from uniformly enhanced SF at $z$ ~ 1 and $z$ ~ 0.3 to centrally enhanced SF at $z$ ~ 0 (when averaged over a wide range of mass). We also capture higher local SFRs for galaxies below the SFMS compared to that of $z$ ~ 0, which can be explained by a larger population of quenched satellites in the local Universe and/or different treatments of limitations set by the D4000-sSFR relation., Comment: 19 pages, 15 figures, 4 tables, accepted for publication in MNRAS

The scatter about the mass-metallicity relation (MZR) has a correlation with the star formation rate (SFR) of galaxies. The lack of evidence of evolution in correlated scatter at $z\lesssim2.5$ leads many to refer to the relationship between mass, metallicity, and SFR as the Fundamental Metallicity Relation (FMR). Yet, recent high-redshift (z>3) JWST observations have challenged the fundamental (i.e., redshift-invariant) nature of the FMR. In this work, we show that the cosmological simulations Illustris, IllustrisTNG, and EAGLE all predict MZRs that exhibit scatter with a secondary dependence on SFR up to $z=8$. We introduce the concept of a "strong" FMR, where the strength of correlated scatter does not evolve with time, and a "weak" FMR, where there is some time evolution. We find that each simulation analysed has a weak FMR -- there is non-negligible evolution in the strength of the correlation with SFR. Furthermore, we show that the scatter is reduced an additional ~10-40% at $z\gtrsim3$ when using a weak FMR, compared to assuming a strong FMR. These results highlight the importance of avoiding coarse redshift binning when assessing the FMR., Comment: 10 pages, 5 figures (Figure 5 is summary). Accepted to MNRAS

Wasserstein Gradient Flows (WGF) with respect to specific functionals have been widely used in the machine learning literature. Recently, neural networks have been adopted to approximate certain intractable parts of the underlying Wasserstein gradient flow and result in efficient inference procedures. In this paper, we introduce the Neural Sinkhorn Gradient Flow (NSGF) model, which parametrizes the time-varying velocity field of the Wasserstein gradient flow w.r.t. the Sinkhorn divergence to the target distribution starting a given source distribution. We utilize the velocity field matching training scheme in NSGF, which only requires samples from the source and target distribution to compute an empirical velocity field approximation. Our theoretical analyses show that as the sample size increases to infinity, the mean-field limit of the empirical approximation converges to the true underlying velocity field. To further enhance model efficiency on high-dimensional tasks, a two-phase NSGF++ model is devised, which first follows the Sinkhorn flow to approach the image manifold quickly ($\le 5$ NFEs) and then refines the samples along a simple straight flow. Numerical experiments with synthetic and real-world benchmark datasets support our theoretical results and demonstrate the effectiveness of the proposed methods.

Particle-based Variational Inference (ParVI) methods approximate the target distribution by iteratively evolving finite weighted particle systems. Recent advances of ParVI methods reveal the benefits of accelerated position update strategies and dynamic weight adjustment approaches. In this paper, we propose the first ParVI framework that possesses both accelerated position update and dynamical weight adjustment simultaneously, named the General Accelerated Dynamic-Weight Particle-based Variational Inference (GAD-PVI) framework. Generally, GAD-PVI simulates the semi-Hamiltonian gradient flow on a novel Information-Fisher-Rao space, which yields an additional decrease on the local functional dissipation. GAD-PVI is compatible with different dissimilarity functionals and associated smoothing approaches under three information metrics. Experiments on both synthetic and real-world data demonstrate the faster convergence and reduced approximation error of GAD-PVI methods over the state-of-the-art.

Spiral structures are important drivers of the secular evolution of disc galaxies, however, the origin of spiral arms and their effects on the development of galaxies remain mysterious. In this work, we present two three-armed spiral galaxies at z~0.3 in the Middle Age Galaxy Properties with Integral Field Spectroscopy (MAGPI) survey. Taking advantage of the high spatial resolution (~0.6'') of the Multi-Unit Spectroscopic Unit (MUSE), we investigate the two-dimensional distributions of different spectral parameters: Halpha, gas-phase metallicity, and D4000. We notice significant offsets in Halpha (~0.2 dex) as well as gas-phase metallicities (~0.05 dex) among the spiral arms, downstream and upstream of MAGPI1202197197 (SG1202). This observational signature suggests the spiral structure in SG1202 is consistent with arising from density wave theory. No azimuthal variation in Halpha or gas-phase metallicities is observed in MAGPI1204198199 (SG1204), which can be attributed to the tighter spiral arms in SG1204 than SG1202, coming with stronger mixing effects in the disc. The absence of azimuthal D4000 variation in both galaxies suggests the stars at different ages are well-mixed between the spiral arms and distributed around the disc regions. The different azimuthal distributions in Halpha and D4000 highlight the importance of time scales traced by various spectral parameters when studying 2D distributions in spiral galaxies. This work demonstrates the feasibility of constraining spiral structures by tracing interstellar medium (ISM) and stellar population at z~0.3, with a plan to expand the study to the full MAGPI survey., Comment: 15 pages, 11 figures, 2 tables, accepted for publication in MNRAS

The vulnerability of deep neural network models to adversarial example attacks is a practical challenge in many artificial intelligence applications. A recent line of work shows that the use of randomization in adversarial training is the key to find optimal strategies against adversarial example attacks. However, in a fully randomized setting where both the defender and the attacker can use randomized strategies, there are no efficient algorithm for finding such an optimal strategy. To fill the gap, we propose the first algorithm of its kind, called FRAT, which models the problem with a new infinite-dimensional continuous-time flow on probability distribution spaces. FRAT maintains a lightweight mixture of models for the defender, with flexibility to efficiently update mixing weights and model parameters at each iteration. Furthermore, FRAT utilizes lightweight sampling subroutines to construct a random strategy for the attacker. We prove that the continuous-time limit of FRAT converges to a mixed Nash equilibria in a zero-sum game formed by a defender and an attacker. Experimental results also demonstrate the efficiency of FRAT on CIFAR-10 and CIFAR-100 datasets., Comment: Extended version of paper https://doi.org/10.1609/aaai.v37i9.26247 which appeared in AAAI 2023

In this paper, we propose the first fully push-forward-based Distributional Reinforcement Learning algorithm, called Push-forward-based Actor-Critic EncourageR (PACER). Specifically, PACER establishes a stochastic utility value policy gradient theorem and simultaneously leverages the push-forward operator in the construction of both the actor and the critic. Moreover, based on maximum mean discrepancies (MMD), a novel sample-based encourager is designed to incentivize exploration. Experimental evaluations on various continuous control benchmarks demonstrate the superiority of our algorithm over the state-of-the-art.

Nowadays, algorithms with fast convergence, small memory footprints, and low per-iteration complexity are particularly favorable for artificial intelligence applications. In this paper, we propose a doubly stochastic algorithm with a novel accelerating multi-momentum technique to solve large scale empirical risk minimization problem for learning tasks. While enjoying a provably superior convergence rate, in each iteration, such algorithm only accesses a mini batch of samples and meanwhile updates a small block of variable coordinates, which substantially reduces the amount of memory reference when both the massive sample size and ultra-high dimensionality are involved. Empirical studies on huge scale datasets are conducted to illustrate the efficiency of our method in practice., Comment: Accepted to IJCAI 2017. Corresponding author: Hui Qian

Wasserstein Barycenter Problem (WBP) has recently received much attention in the field of artificial intelligence. In this paper, we focus on the decentralized setting for WBP and propose an asynchronous decentralized algorithm (A$^2$DWB). A$^2$DWB is induced by a novel stochastic block coordinate descent method to optimize the dual of entropy regularized WBP. To our knowledge, A$^2$DWB is the first asynchronous decentralized algorithm for WBP. Unlike its synchronous counterpart, it updates local variables in a manner that only relies on the stale neighbor information, which effectively alleviate the waiting overhead, and thus substantially improve the time efficiency. Empirical results validate its superior performance compared to the latest synchronous algorithm.

Bars play an important role in mixing material in the inner regions of galaxies and stimulating radial migration. Previous observations have found evidence for the impact of a bar on metallicity gradients but the effect is still inconclusive. We use the TYPHOON/PrISM survey to investigate the metallicity gradients along and beyond the bar region across the entire star-forming disk of five nearby galaxies. Using emission line diagrams to identify star-forming spaxels, we recover the global metallicity gradients ranging from -0.0162 to -0.073 dex/kpc with evidence that the galactic bars act as an agent in affecting in-situ star formation as well as the motions of gas and stars. We observe cases with a `shallow-steep' metallicity radial profile, with evidence of the bar flattening the metallicity gradients inside the bar region (NGC~5068 and NGC~1566) and also note instances where the bar appears to drive a steeper metallicity gradient producing `steep-shallow' metallicity profiles (NGC~1365 and NGC~1744). For NGC~2835, a `steep-shallow' metallicity gradient break occurs at a distance $\sim$ 4 times the bar radius, which is more likely driven by gas accretion to the outskirt of the galaxy instead of the bar. The variation of metallicity gradients around the bar region traces the fluctuations of star formation rate surface density in NGC~1365, NGC~1566 and NGC~1744. A larger sample combined with hydrodynamical simulations is required to further explore the diversity and the relative importance of different ISM mixing mechanisms on the gas-phase metallicity gradients in local galaxies., Comment: 17 pages, 6 figures, 2 tables, published on MNRAS

We present radial gas-phase metallicity profiles, gradients, and break radii at redshift $z = 0 - 3$ from the TNG50-1 star-forming galaxy population. These metallicity profiles are characterized by an emphasis on identifying the steep inner gradient and flat outer gradient. From this, the break radius, $r_{\rm Break}$, is defined as the region where the transition occurs. We observe the break radius having a positive trend with mass that weakens with redshift. When normalized by the stellar half-mass radius, the break radius has a weaker relation with both mass and redshift. To test if our results are dependent on the resolution or adopted physics of TNG50-1, the same analysis is performed in TNG50-2 and Illustris-1. We find general agreement between each of the simulations in their qualitative trends; however, the adopted physics between TNG and Illustris differ and therefore the breaks, normalized by galaxy size, deviate by a factor of $\sim$2. In order to understand where the break comes from, we define two relevant time-scales: an enrichment time-scale and a radial gas mixing time-scale. We find that $r_{\rm Break}$ occurs where the gas mixing time-scale is $\sim$10 times as long as the enrichment time-scale in all three simulation runs, with some weak mass and redshift dependence. This implies that galactic disks can be thought of in two-parts: a star-forming inner disk with a steep gradient and a mixing-dominated outer disk with a flat gradient, with the break radius marking the region of transition between them., Comment: 17 pages, 11 figures, submitted to MNRAS

Image restoration tasks have achieved tremendous performance improvements with the rapid advancement of deep neural networks. However, most prevalent deep learning models perform inference statically, ignoring that different images have varying restoration difficulties and lightly degraded images can be well restored by slimmer subnetworks. To this end, we propose a new solution pipeline dubbed ClassPruning that utilizes networks with different capabilities to process images with varying restoration difficulties. In particular, we use a lightweight classifier to identify the image restoration difficulty, and then the sparse subnetworks with different capabilities can be sampled based on predicted difficulty by performing dynamic N:M fine-grained structured pruning on base restoration networks. We further propose a novel training strategy along with two additional loss terms to stabilize training and improve performance. Experiments demonstrate that ClassPruning can help existing methods save approximately 40% FLOPs while maintaining performance.

Image dehazing is an active topic in low-level vision, and many image dehazing networks have been proposed with the rapid development of deep learning. Although these networks' pipelines work fine, the key mechanism to improving image dehazing performance remains unclear. For this reason, we do not target to propose a dehazing network with fancy modules; rather, we make minimal modifications to popular U-Net to obtain a compact dehazing network. Specifically, we swap out the convolutional blocks in U-Net for residual blocks with the gating mechanism, fuse the feature maps of main paths and skip connections using the selective kernel, and call the resulting U-Net variant gUNet. As a result, with a significantly reduced overhead, gUNet is superior to state-of-the-art methods on multiple image dehazing datasets. Finally, we verify these key designs to the performance gain of image dehazing networks through extensive ablation studies.

Image dehazing is a representative low-level vision task that estimates latent haze-free images from hazy images. In recent years, convolutional neural network-based methods have dominated image dehazing. However, vision Transformers, which has recently made a breakthrough in high-level vision tasks, has not brought new dimensions to image dehazing. We start with the popular Swin Transformer and find that several of its key designs are unsuitable for image dehazing. To this end, we propose DehazeFormer, which consists of various improvements, such as the modified normalization layer, activation function, and spatial information aggregation scheme. We train multiple variants of DehazeFormer on various datasets to demonstrate its effectiveness. Specifically, on the most frequently used SOTS indoor set, our small model outperforms FFA-Net with only 25% #Param and 5% computational cost. To the best of our knowledge, our large model is the first method with the PSNR over 40 dB on the SOTS indoor set, dramatically outperforming the previous state-of-the-art methods. We also collect a large-scale realistic remote sensing dehazing dataset for evaluating the method's capability to remove highly non-homogeneous haze.