Searcharxiv⌕ Search

arXiv subjects

Jianfeng Wang

Publications and source records attributed to Jianfeng Wang.

At least 73 records · Page 4Linked to original sources
arXiv2023

DEsignBench: Exploring and Benchmarking DALL-E 3 for Imagining Visual Design

We introduce DEsignBench, a text-to-image (T2I) generation benchmark tailored for visual design scenarios. Recent T2I models like DALL-E 3 and others, have demonstrated remarkable capabilities in generating photorealistic images that align closely with textual inputs. While the allure of creating visually captivating images is undeniable, our emphasis extends beyond mere aesthetic pleasure. We aim to investigate the potential of using these powerful models in authentic design contexts. In pursuit of this goal, we develop DEsignBench, which incorporates test samples designed to assess T2I models on both "design technical capability" and "design application scenario." Each of these two dimensions is supported by a diverse set of specific design categories. We explore DALL-E 3 together with other leading T2I models on DEsignBench, resulting in a comprehensive visual gallery for side-by-side comparisons. For DEsignBench benchmarking, we perform human evaluations on generated images in DEsignBench gallery, against the criteria of image-text alignment, visual aesthetic, and design creativity. Our evaluation also considers other specialized design capabilities, including text rendering, layout composition, color harmony, 3D design, and medium style. In addition to human evaluations, we introduce the first automatic image generation evaluator powered by GPT-4V. This evaluator provides ratings that align well with human judgments, while being easily replicable and cost-efficient. A high-resolution version is available at https://github.com/design-bench/design-bench.github.io/raw/main/designbench.pdf?download=

cs.CV↗
arXiv2023

The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)

Large multimodal models (LMMs) extend large language models (LLMs) with multi-sensory skills, such as visual understanding, to achieve stronger generic intelligence. In this paper, we analyze the latest model, GPT-4V(ision), to deepen the understanding of LMMs. The analysis focuses on the intriguing tasks that GPT-4V can perform, containing test samples to probe the quality and genericity of GPT-4V's capabilities, its supported inputs and working modes, and the effective ways to prompt the model. In our approach to exploring GPT-4V, we curate and organize a collection of carefully designed qualitative samples spanning a variety of domains and tasks. Observations from these samples demonstrate that GPT-4V's unprecedented ability in processing arbitrarily interleaved multimodal inputs and the genericity of its capabilities together make GPT-4V a powerful multimodal generalist system. Furthermore, GPT-4V's unique capability of understanding visual markers drawn on input images can give rise to new human-computer interaction methods such as visual referring prompting. We conclude the report with in-depth discussions on the emerging application scenarios and the future research directions for GPT-4V-based systems. We hope that this preliminary exploration will inspire future research on the next-generation multimodal task formulation, new ways to exploit and enhance LMMs to solve real-world problems, and gaining better understanding of multimodal foundation models. Finally, we acknowledge that the model under our study is solely the product of OpenAI's innovative work, and they should be fully credited for its development. Please see the GPT-4V contributions paper for the authorship and credit attribution: https://cdn.openai.com/contributions/gpt-4v.pdf

cs.CV↗
arXiv2023

On distance-balanced generalized Petersen graphs

A connected graph $G$ of diameter ${\rm diam}(G) \ge \ell$ is $\ell$-distance-balanced if $|W_{xy}|=|W_{yx}|$ for every $x,y\in V(G)$ with $d_{G}(x,y)=\ell$, where $W_{xy}$ is the set of vertices of $G$ that are closer to $x$ than to $y$. We prove that the generalized Petersen graph $GP(n,k)$ is ${\rm diam}(GP(n,k))$-distance-balanced provided that $n$ is large enough relative to $k$. This partially solves a conjecture posed by Miklavič and Šparl \cite{Miklavic:2018}. We also determine ${\rm diam}(GP(n,k))$ when $n$ is large enough relative to $k$.

math.CO↗
arXiv2023

Non-$\ell$-distance-balanced generalized Petersen graphs $GP(n,3)$ and $GP(n,4)$

A connected graph $G$ of diameter ${\rm diam}(G) \ge \ell$ is $\ell$-distance-balanced if $|W_{xy}|=|W_{yx}|$ for every $x,y\in V(G)$ with $d_{G}(x,y)=\ell$, where $W_{xy}$ is the set of vertices of $G$ that are closer to $x$ than to $y$. We prove that the generalized Petersen graph $GP(n,3)$ where $n>16$ is not $\ell$-distance-balanced for any $1\le \ell < {\rm diam}(GP(n,3))$, and $GP(n,4)$ where $n>24$ is not $\ell$-distance-balanced for any $1\le \ell < {\rm diam}(GP(n,4))$. This partially solves a conjecture posed by Š. Miklavič and P. Šparl (Discrete Appl. Math. 244:143-154, 2018).

math.CO↗
arXiv2023

Towards Layer-Selective Quantum Spin Hall Channels in Weak Topological Insulator Bi4Br2I2

Weak topological insulators, constructed by stacking quantum spin Hall insulators with weak interlayer coupling, offer promising quantum electronic applications through topologically nontrivial edge channels. However, the currently available weak topological insulators are stacks of the same quantum spin Hall layer with translational symmetry in the out-of-plane direction, leading to the absence of the channel degree of freedom for edge states. Here, we study a candidate weak topological insulator, Bi4Br2I2, which is alternately stacked by three different quantum spin Hall insulators, each with tunable topologically non-trivial edge states. Our angle-resolved photoemission spectroscopy and first-principles calculations show that an energy gap opens at the crossing points of different Dirac cones correlated with different layers due to the interlayer interaction. This is essential to achieve the tunability of topological edge states as controlled by varying the chemical potential. Our work offers a perspective for the construction of tunable quantized conductance devices for future spintronic applications.

cond-mat.mtrl-sci↗
arXiv2023

NP-SemiSeg: When Neural Processes meet Semi-Supervised Semantic Segmentation

Semi-supervised semantic segmentation involves assigning pixel-wise labels to unlabeled images at training time. This is useful in a wide range of real-world applications where collecting pixel-wise labels is not feasible in time or cost. Current approaches to semi-supervised semantic segmentation work by predicting pseudo-labels for each pixel from a class-wise probability distribution output by a model. If the predicted probability distribution is incorrect, however, this leads to poor segmentation results, which can have knock-on consequences in safety critical systems, like medical images or self-driving cars. It is, therefore, important to understand what a model does not know, which is mainly achieved by uncertainty quantification. Recently, neural processes (NPs) have been explored in semi-supervised image classification, and they have been a computationally efficient and effective method for uncertainty quantification. In this work, we move one step forward by adapting NPs to semi-supervised semantic segmentation, resulting in a new model called NP-SemiSeg. We experimentally evaluated NP-SemiSeg on the public benchmarks PASCAL VOC 2012 and Cityscapes, with different training settings, and the results verify its effectiveness.

cs.CV↗
arXiv2023

Spatial-Frequency U-Net for Denoising Diffusion Probabilistic Models

In this paper, we study the denoising diffusion probabilistic model (DDPM) in wavelet space, instead of pixel space, for visual synthesis. Considering the wavelet transform represents the image in spatial and frequency domains, we carefully design a novel architecture SFUNet to effectively capture the correlation for both domains. Specifically, in the standard denoising U-Net for pixel data, we supplement the 2D convolutions and spatial-only attention layers with our spatial frequency-aware convolution and attention modules to jointly model the complementary information from spatial and frequency domains in wavelet data. Our new architecture can be used as a drop-in replacement to the pixel-based network and is compatible with the vanilla DDPM training process. By explicitly modeling the wavelet signals, we find our model is able to generate images with higher quality on CIFAR-10, FFHQ, LSUN-Bedroom, and LSUN-Church datasets, than the pixel-based counterpart.

cs.CV↗
arXiv2023

Segment Everything Everywhere All at Once

In this work, we present SEEM, a promptable and interactive model for segmenting everything everywhere all at once in an image, as shown in Fig.1. In SEEM, we propose a novel decoding mechanism that enables diverse prompting for all types of segmentation tasks, aiming at a universal segmentation interface that behaves like large language models (LLMs). More specifically, SEEM is designed with four desiderata: i) Versatility. We introduce a new visual prompt to unify different spatial queries including points, boxes, scribbles and masks, which can further generalize to a different referring image; ii) Compositionality. We learn a joint visual-semantic space between text and visual prompts, which facilitates the dynamic composition of two prompt types required for various segmentation tasks; iii) Interactivity. We further incorporate learnable memory prompts into the decoder to retain segmentation history through mask-guided cross-attention from decoder to image features; and iv) Semantic-awareness. We use a text encoder to encode text queries and mask labels into the same semantic space for open-vocabulary segmentation. We conduct a comprehensive empirical study to validate the effectiveness of SEEM across diverse segmentation tasks. Notably, our single SEEM model achieves competitive performance across interactive segmentation, generic segmentation, referring segmentation, and video object segmentation on 9 datasets with minimum 1/100 supervision. Furthermore, SEEM showcases a remarkable capacity for generalization to novel prompts or their combinations, rendering it a readily universal image segmentation interface.

cs.CV↗
arXiv2023

NP-Match: Towards a New Probabilistic Model for Semi-Supervised Learning

Semi-supervised learning (SSL) has been widely explored in recent years, and it is an effective way of leveraging unlabeled data to reduce the reliance on labeled data. In this work, we adjust neural processes (NPs) to the semi-supervised image classification task, resulting in a new method named NP-Match. NP-Match is suited to this task for two reasons. Firstly, NP-Match implicitly compares data points when making predictions, and as a result, the prediction of each unlabeled data point is affected by the labeled data points that are similar to it, which improves the quality of pseudo-labels. Secondly, NP-Match is able to estimate uncertainty that can be used as a tool for selecting unlabeled samples with reliable pseudo-labels. Compared with uncertainty-based SSL methods implemented with Monte-Carlo (MC) dropout, NP-Match estimates uncertainty with much less computational overhead, which can save time at both the training and the testing phases. We conducted extensive experiments on five public datasets under three semi-supervised image classification settings, namely, the standard semi-supervised image classification, the imbalanced semi-supervised image classification, and the multi-label semi-supervised image classification, and NP-Match outperforms state-of-the-art (SOTA) approaches or achieves competitive results on them, which shows the effectiveness of NP-Match and its potential for SSL. The codes are at https://github.com/Jianf-Wang/NP-Match

cs.CV↗
arXiv2023

Scheduling Network Function Chains Under Sub-Millisecond Latency SLOs

Network Function Virtualization (NFV) seeks to replace hardware middleboxes with software-based Network Functions (NFs). NFV systems are seeing greater deployment in the cloud and at the edge. However, especially at the edge, there is a mismatch between the traditional focus on NFV throughput and the need to meet very low latency SLOs, as edge services inherently require low latency. Moreover, cloud-based NFV systems need to achieve such low latency while minimizing CPU core usage. We find that real-world traffic exhibits burstiness that causes latency spikes of up to 10s of milliseconds in existing NFV systems. To address this, we built NetBlaze, which achieves sub-millisecond p99 latency SLOs, even for adversarial traffic, using a novel multi-scale core-scaling strategy. NetBlaze makes traffic-to-core allocation decisions at rack, server, and core-spatial scales, and at increasingly finer timescales, to accommodate multi-timescale bursts. In comparison with state-of-the-art approaches, NetBlaze is the only one capable of achieving sub-millisecond p99 latency SLOs while using a comparable number of cores.

cs.NI↗
arXiv2023

On the divisibility of H-shape trees and their spectral determination

A graph $G$ is divisible by a graph $H$ if the characteristic polynomial of $G$ is divisible by that of $H$. In this paper, a necessary and sufficient condition for recursive graphs to be divisible by a path is used to show that the H-shape graph $P_{2,2;n-4}^{2,n-7}$, known to be (for $n$ large enough) the minimizer of the spectral radius among the graphs of order $n$ and diameter $n-5$, is determined by its adjacency spectrum if and only if $n \neq 10,13,15$.

math.CO↗
arXiv2023

Giant Bulk Electro-photovoltaic Effect in Hetero-nodal-line Systems

Realization of giant and continuously tunable second-order photocurrent is desired for many nonlinear optical (NLO) and optoelectronic applications, which remains to be a great challenge. Here, based on a simple two-band model, we propose a concept of bulk electro-photovoltaic effect, that is, an out-of-plane external electric-field ($E_{ext}$) can continuously tune in-plane shift current along with its sign flip in a hetero-nodal-line (HNL) system. While strong linear optical transition around the nodal-loop may potentially generate giant shift current, an $E_{ext}$ can effectively control the radius of nodal-loop, which can continuously modulate the shift-vector components inside and outside nodal-loop holding opposite signs. This concept has been demonstrated in the HNL HSnN/MoS$_2$ system using first-principles calculations. The HSnN/MoS$_2$ hetero-bilayer not only can produce giant shift current with 1~2 magnitude order larger than other reported systems, but also can realize a giant bulk electro-photovoltaic effect. Our finding opens new routes to create and manipulate giant NLO responses in 2D materials.

cond-mat.mtrl-sci↗
arXiv2023

Detection Hub: Unifying Object Detection Datasets via Query Adaptation on Language Embedding

Combining multiple datasets enables performance boost on many computer vision tasks. But similar trend has not been witnessed in object detection when combining multiple datasets due to two inconsistencies among detection datasets: taxonomy difference and domain gap. In this paper, we address these challenges by a new design (named Detection Hub) that is dataset-aware and category-aligned. It not only mitigates the dataset inconsistency but also provides coherent guidance for the detector to learn across multiple datasets. In particular, the dataset-aware design is achieved by learning a dataset embedding that is used to adapt object queries as well as convolutional kernels in detection heads. The categories across datasets are semantically aligned into a unified space by replacing one-hot category representations with word embedding and leveraging the semantic coherence of language embedding. Detection Hub fulfills the benefits of large data on object detection. Experiments demonstrate that joint training on multiple datasets achieves significant performance gains over training on each dataset alone. Detection Hub further achieves SoTA performance on UODB benchmark with wide variety of datasets.

cs.CV↗
arXiv2023

NUWA-XL: Diffusion over Diffusion for eXtremely Long Video Generation

In this paper, we propose NUWA-XL, a novel Diffusion over Diffusion architecture for eXtremely Long video generation. Most current work generates long videos segment by segment sequentially, which normally leads to the gap between training on short videos and inferring long videos, and the sequential generation is inefficient. Instead, our approach adopts a ``coarse-to-fine'' process, in which the video can be generated in parallel at the same granularity. A global diffusion model is applied to generate the keyframes across the entire time range, and then local diffusion models recursively fill in the content between nearby frames. This simple yet effective strategy allows us to directly train on long videos (3376 frames) to reduce the training-inference gap, and makes it possible to generate all segments in parallel. To evaluate our model, we build FlintstonesHD dataset, a new benchmark for long video generation. Experiments show that our model not only generates high-quality long videos with both global and local coherence, but also decreases the average inference time from 7.55min to 26s (by 94.26\%) at the same hardware setting when generating 1024 frames. The homepage link is \url{https://msra-nuwa.azurewebsites.net/}

cs.CV↗
arXiv2023

MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action

We propose MM-REACT, a system paradigm that integrates ChatGPT with a pool of vision experts to achieve multimodal reasoning and action. In this paper, we define and explore a comprehensive list of advanced vision tasks that are intriguing to solve, but may exceed the capabilities of existing vision and vision-language models. To achieve such advanced visual intelligence, MM-REACT introduces a textual prompt design that can represent text descriptions, textualized spatial coordinates, and aligned file names for dense visual signals such as images and videos. MM-REACT's prompt design allows language models to accept, associate, and process multimodal information, thereby facilitating the synergetic combination of ChatGPT and various vision experts. Zero-shot experiments demonstrate MM-REACT's effectiveness in addressing the specified capabilities of interests and its wide application in different scenarios that require advanced visual understanding. Furthermore, we discuss and compare MM-REACT's system paradigm with an alternative approach that extends language models for multimodal scenarios through joint finetuning. Code, demo, video, and visualization are available at https://multimodal-react.github.io/

cs.CV↗
arXiv2023

Learning 3D Photography Videos via Self-supervised Diffusion on Single Images

3D photography renders a static image into a video with appealing 3D visual effects. Existing approaches typically first conduct monocular depth estimation, then render the input frame to subsequent frames with various viewpoints, and finally use an inpainting model to fill those missing/occluded regions. The inpainting model plays a crucial role in rendering quality, but it is normally trained on out-of-domain data. To reduce the training and inference gap, we propose a novel self-supervised diffusion model as the inpainting module. Given a single input image, we automatically construct a training pair of the masked occluded image and the ground-truth image with random cycle-rendering. The constructed training samples are closely aligned to the testing instances, without the need of data annotation. To make full use of the masked images, we design a Masked Enhanced Block (MEB), which can be easily plugged into the UNet and enhance the semantic conditions. Towards real-world animation, we present a novel task: out-animation, which extends the space and time of input objects. Extensive experiments on real datasets show that our method achieves competitive results with existing SOTA methods.

cs.CV↗
arXiv2023

Prompting GPT-3 To Be Reliable

Large language models (LLMs) show impressive abilities via few-shot prompting. Commercialized APIs such as OpenAI GPT-3 further increase their use in real-world language applications. However, the crucial problem of how to improve the reliability of GPT-3 is still under-explored. While reliability is a broad and vaguely defined term, we decompose reliability into four main facets that correspond to the existing framework of ML safety and are well-recognized to be important: generalizability, social biases, calibration, and factuality. Our core contribution is to establish simple and effective prompts that improve GPT-3's reliability as it: 1) generalizes out-of-distribution, 2) balances demographic distribution and uses natural language instructions to reduce social biases, 3) calibrates output probabilities, and 4) updates the LLM's factual knowledge and reasoning chains. With appropriate prompts, GPT-3 is more reliable than smaller-scale supervised models on all these facets. We release all processed datasets, evaluation scripts, and model predictions. Our systematic empirical study not only sheds new insights on the reliability of prompting LLMs, but more importantly, our prompting strategies can help practitioners more reliably use LLMs like GPT-3.

cs.CL↗