arXiv subjects

Xiaojun Chang

Publications and source records attributed to Xiaojun Chang.

At least 91 records · Page 5Linked to original sources

arXiv2024

StoryAgent: Customized Storytelling Video Generation via Multi-Agent Collaboration

The advent of AI-Generated Content (AIGC) has spurred research into automated video generation to streamline conventional processes. However, automating storytelling video production, particularly for customized narratives, remains challenging due to the complexity of maintaining subject consistency across shots. While existing approaches like Mora and AesopAgent integrate multiple agents for Story-to-Video (S2V) generation, they fall short in preserving protagonist consistency and supporting Customized Storytelling Video Generation (CSVG). To address these limitations, we propose StoryAgent, a multi-agent framework designed for CSVG. StoryAgent decomposes CSVG into distinct subtasks assigned to specialized agents, mirroring the professional production process. Notably, our framework includes agents for story design, storyboard generation, video creation, agent coordination, and result evaluation. Leveraging the strengths of different models, StoryAgent enhances control over the generation process, significantly improving character consistency. Specifically, we introduce a customized Image-to-Video (I2V) method, LoRA-BE, to enhance intra-shot temporal consistency, while a novel storyboard generation pipeline is proposed to maintain subject consistency across shots. Extensive experiments demonstrate the effectiveness of our approach in synthesizing highly consistent storytelling videos, outperforming state-of-the-art methods. Our contributions include the introduction of StoryAgent, a versatile framework for video generation tasks, and novel techniques for preserving protagonist consistency.

cs.CV↗

arXiv2024

RealignDiff: Boosting Text-to-Image Diffusion Model with Coarse-to-fine Semantic Re-alignment

Recent advances in text-to-image diffusion models have achieved remarkable success in generating high-quality, realistic images from textual descriptions. However, these approaches have faced challenges in precisely aligning the generated visual content with the textual concepts described in the prompts. In this paper, we propose a two-stage coarse-to-fine semantic re-alignment method, named RealignDiff, aimed at improving the alignment between text and images in text-to-image diffusion models. In the coarse semantic re-alignment phase, a novel caption reward, leveraging the BLIP-2 model, is proposed to evaluate the semantic discrepancy between the generated image caption and the given text prompt. Subsequently, the fine semantic re-alignment stage employs a local dense caption generation module and a re-weighting attention modulation module to refine the previously generated images from a local semantic view. Experimental results on the MS-COCO and ViLG-300 datasets demonstrate that the proposed two-stage coarse-to-fine semantic re-alignment method outperforms other baseline re-alignment techniques by a substantial margin in both visual quality and semantic similarity with the input prompt.

cs.CV↗

arXiv2024

ContextDet: Temporal Action Detection with Adaptive Context Aggregation

Temporal action detection (TAD), which locates and recognizes action segments, remains a challenging task in video understanding due to variable segment lengths and ambiguous boundaries. Existing methods treat neighboring contexts of an action segment indiscriminately, leading to imprecise boundary predictions. We introduce a single-stage ContextDet framework, which makes use of large-kernel convolutions in TAD for the first time. Our model features a pyramid adaptive context aggragation (ACA) architecture, capturing long context and improving action discriminability. Each ACA level consists of two novel modules. The context attention module (CAM) identifies salient contextual information, encourages context diversity, and preserves context integrity through a context gating block (CGB). The long context module (LCM) makes use of a mixture of large- and small-kernel convolutions to adaptively gather long-range context and fine-grained local features. Additionally, by varying the length of these large kernels across the ACA pyramid, our model provides lightweight yet effective context aggregation and action discrimination. We conducted extensive experiments and compared our model with a number of advanced TAD methods on six challenging TAD benchmarks: MultiThumos, Charades, FineAction, EPIC-Kitchens 100, Thumos14, and HACS, demonstrating superior accuracy at reduced inference speed.

cs.CV↗

arXiv2024

Act Like a Radiologist: Radiology Report Generation across Anatomical Regions

Automating radiology report generation can ease the reporting workload for radiologists. However, existing works focus mainly on the chest area due to the limited availability of public datasets for other regions. Besides, they often rely on naive data-driven approaches, e.g., a basic encoder-decoder framework with captioning loss, which limits their ability to recognise complex patterns across diverse anatomical regions. To address these issues, we propose X-RGen, a radiologist-minded report generation framework across six anatomical regions. In X-RGen, we seek to mimic the behaviour of human radiologists, breaking them down into four principal phases: 1) initial observation, 2) cross-region analysis, 3) medical interpretation, and 4) report formation. Firstly, we adopt an image encoder for feature extraction, akin to a radiologist's preliminary review. Secondly, we enhance the recognition capacity of the image encoder by analysing images and reports across various regions, mimicking how radiologists gain their experience and improve their professional ability from past cases. Thirdly, just as radiologists apply their expertise to interpret radiology images, we introduce radiological knowledge of multiple anatomical regions to further analyse the features from a clinical perspective. Lastly, we generate reports based on the medical-aware features using a typical auto-regressive text decoder. Both natural language generation (NLG) and clinical efficacy metrics show the effectiveness of X-RGen on six X-ray datasets. Our code and checkpoints are available at: https://github.com/YtongXie/X-RGen.

cs.CV↗

arXiv2024

Normalized ground state solutions of Schrödinger-KdV system in $\mathbb{R}^3$

In this paper, we study the coupled Schrödinger-KdV system \begin{align*} \begin{cases} -Δu +λ_1 u=u^3+βuv~~&\text{in}~~\mathbb{R}^{3}, \\-Δv +λ_2 v=\frac{1}{2}v^2+\frac{1}{2}βu^2~~&\text{in}~~\mathbb{R}^{3} \end{cases} \end{align*} subject to the mass constraints \begin{equation*} \int_{\mathbb{R}^{3}}|u|^2 dx=a,\quad \int_{\mathbb{R}^{3}}|v|^2 dx=b, \end{equation*} where $a, b>0$ are given constants, $β>0$, and the frequencies $λ_1,λ_2$ arise as Lagrange multipliers. The system exhibits $L^2$-supercritical growth. Using a novel constraint minimization approach, we demonstrate the existence of a local minimum solution to the system. Furthermore, we establish the existence of normalized ground state solutions.

math.AP↗

arXiv2024

Efficient Training of Large Vision Models via Advanced Automated Progressive Learning

The rapid advancements in Large Vision Models (LVMs), such as Vision Transformers (ViTs) and diffusion models, have led to an increasing demand for computational resources, resulting in substantial financial and environmental costs. This growing challenge highlights the necessity of developing efficient training methods for LVMs. Progressive learning, a training strategy in which model capacity gradually increases during training, has shown potential in addressing these challenges. In this paper, we present an advanced automated progressive learning (AutoProg) framework for efficient training of LVMs. We begin by focusing on the pre-training of LVMs, using ViTs as a case study, and propose AutoProg-One, an AutoProg scheme featuring momentum growth (MoGrow) and a one-shot growth schedule search. Beyond pre-training, we extend our approach to tackle transfer learning and fine-tuning of LVMs. We expand the scope of AutoProg to cover a wider range of LVMs, including diffusion models. First, we introduce AutoProg-Zero, by enhancing the AutoProg framework with a novel zero-shot unfreezing schedule search, eliminating the need for one-shot supernet training. Second, we introduce a novel Unique Stage Identifier (SID) scheme to bridge the gap during network growth. These innovations, integrated with the core principles of AutoProg, offer a comprehensive solution for efficient training across various LVM scenarios. Extensive experiments show that AutoProg accelerates ViT pre-training by up to 1.85x on ImageNet and accelerates fine-tuning of diffusion models by up to 2.86x, with comparable or even higher performance. This work provides a robust and scalable approach to efficient training of LVMs, with potential applications in a wide range of vision tasks. Code: https://github.com/changlin31/AutoProg-Zero

cs.CV↗

arXiv2024

Normalized solutions of $L^2$-supercritical Kirchhoff equations in bounded domains

In this paper, we investigate the existence of normalized solutions for the following nonlinear Kirchhoff type problem \begin{equation*} \begin{cases} -(a+b\int_Ω\vert\nabla u\vert^2dx)Δu+λu=\vert u\vert^{p-2}u & \text{ in }Ω,\\ u=0 & \text{ on }\partialΩ\end{cases} \end{equation*} subject to the constraint $\int_Ω\vert u\vert^2dx=c$. Here, $a$ and $b$ are positive constants, $Ω$ is a smooth bounded domain in $\mathbb{R}^N$ with $1\leq N\leq3$, $c>0$ is a prescribed value, and $λ\in \mathbb{R}$ is a Lagrange multiplier. In the $L^2$-supercritical regime $2+\frac{8}{N}<p<2^*$, we establish the existence of mountain pass-type normalized solutions. Our approach relies on utilizing a parameterized version of the minimax theorem with Morse index information for constraint functionals, and developing a blow-up analysis for the nonlinear Kirchhoff equations. Furthermore, we explore the asymptotic behavior of these solutions as $b\rightarrow0$.

math.AP↗

arXiv2024

Normalized ground states for nonlinear Schrödinger equations with general Sobolev critical nonlinearities

In this paper, we study the existence of normalized solutions to the following nonlinear Schrödinger equation \begin{equation*} \left\{ \begin{aligned} &-Δu=f(u)+ λu\quad \mbox{in}\ \mathbb{R}^{N},\\ &u\in H^1(\mathbb{R}^N), ~~~\int_{\mathbb{R}^N}|u|^2dx=c, \end{aligned} \right. \end{equation*} where $N\ge3$, $c>0$, $λ\in \mathbb{R}$ and $f$ has a Sobolev critical growth at infinity but does not satisfies the Ambrosetti-Rabinowitz condition. By analysing the monotonicity of the ground state energy with respect to $c$, we develop a constrained minimization approach to establish the existence of normalized ground state solutions for all $c>0$.

math.AP↗

arXiv2024

Disentangled Representation Learning with Transmitted Information Bottleneck

Encoding only the task-related information from the raw data, \ie, disentangled representation learning, can greatly contribute to the robustness and generalizability of models. Although significant advances have been made by regularizing the information in representations with information theory, two major challenges remain: 1) the representation compression inevitably leads to performance drop; 2) the disentanglement constraints on representations are in complicated optimization. To these issues, we introduce Bayesian networks with transmitted information to formulate the interaction among input and representations during disentanglement. Building upon this framework, we propose \textbf{DisTIB} (\textbf{T}ransmitted \textbf{I}nformation \textbf{B}ottleneck for \textbf{Dis}entangled representation learning), a novel objective that navigates the balance between information compression and preservation. We employ variational inference to derive a tractable estimation for DisTIB. This estimation can be simply optimized via standard gradient descent with a reparameterization trick. Moreover, we theoretically prove that DisTIB can achieve optimal disentanglement, underscoring its superior efficacy. To solidify our claims, we conduct extensive experiments on various downstream tasks to demonstrate the appealing efficacy of DisTIB and validate our theoretical analyses.

cs.CV↗

arXiv2024

Disentangled Noisy Correspondence Learning

Cross-modal retrieval is crucial in understanding latent correspondences across modalities. However, existing methods implicitly assume well-matched training data, which is impractical as real-world data inevitably involves imperfect alignments, i.e., noisy correspondences. Although some works explore similarity-based strategies to address such noise, they suffer from sub-optimal similarity predictions influenced by modality-exclusive information (MEI), e.g., background noise in images and abstract definitions in texts. This issue arises as MEI is not shared across modalities, thus aligning it in training can markedly mislead similarity predictions. Moreover, although intuitive, directly applying previous cross-modal disentanglement methods suffers from limited noise tolerance and disentanglement efficacy. Inspired by the robustness of information bottlenecks against noise, we introduce DisNCL, a novel information-theoretic framework for feature Disentanglement in Noisy Correspondence Learning, to adaptively balance the extraction of MII and MEI with certifiable optimal cross-modal disentanglement efficacy. DisNCL then enhances similarity predictions in modality-invariant subspace, thereby greatly boosting similarity-based alleviation strategy for noisy correspondences. Furthermore, DisNCL introduces soft matching targets to model noisy many-to-many relationships inherent in multi-modal input for noise-robust and accurate cross-modal alignment. Extensive experiments confirm DisNCL's efficacy by 2% average recall improvement. Mutual information estimation and visualization results show that DisNCL learns meaningful MII/MEI subspaces, validating our theoretical analyses.

cs.CV↗

arXiv2024

LongVLM: Efficient Long Video Understanding via Large Language Models

Empowered by Large Language Models (LLMs), recent advancements in Video-based LLMs (VideoLLMs) have driven progress in various video understanding tasks. These models encode video representations through pooling or query aggregation over a vast number of visual tokens, making computational and memory costs affordable. Despite successfully providing an overall comprehension of video content, existing VideoLLMs still face challenges in achieving detailed understanding due to overlooking local information in long-term videos. To tackle this challenge, we introduce LongVLM, a simple yet powerful VideoLLM for long video understanding, building upon the observation that long videos often consist of sequential key events, complex actions, and camera movements. Our approach proposes to decompose long videos into multiple short-term segments and encode local features for each segment via a hierarchical token merging module. These features are concatenated in temporal order to maintain the storyline across sequential short-term segments. Additionally, we propose to integrate global semantics into each local feature to enhance context understanding. In this way, we encode video representations that incorporate both local and global information, enabling the LLM to generate comprehensive responses for long-term videos. Experimental results on the VideoChatGPT benchmark and zero-shot video question-answering datasets demonstrate the superior capabilities of our model over the previous state-of-the-art methods. Qualitative examples show that our model produces more precise responses for long video understanding. Code is available at https://github.com/ziplab/LongVLM.

cs.CV↗

arXiv2024

Contrastive Learning with Counterfactual Explanations for Radiology Report Generation

Due to the common content of anatomy, radiology images with their corresponding reports exhibit high similarity. Such inherent data bias can predispose automatic report generation models to learn entangled and spurious representations resulting in misdiagnostic reports. To tackle these, we propose a novel \textbf{Co}unter\textbf{F}actual \textbf{E}xplanations-based framework (CoFE) for radiology report generation. Counterfactual explanations serve as a potent tool for understanding how decisions made by algorithms can be changed by asking ``what if'' scenarios. By leveraging this concept, CoFE can learn non-spurious visual representations by contrasting the representations between factual and counterfactual images. Specifically, we derive counterfactual images by swapping a patch between positive and negative samples until a predicted diagnosis shift occurs. Here, positive and negative samples are the most semantically similar but have different diagnosis labels. Additionally, CoFE employs a learnable prompt to efficiently fine-tune the pre-trained large language model, encapsulating both factual and counterfactual content to provide a more generalizable prompt representation. Extensive experiments on two benchmarks demonstrate that leveraging the counterfactual explanations enables CoFE to generate semantically coherent and factually complete reports and outperform in terms of language generation and clinical efficacy metrics.

cs.CV↗

arXiv2024

Label-anticipated Event Disentanglement for Audio-Visual Video Parsing

Audio-Visual Video Parsing (AVVP) task aims to detect and temporally locate events within audio and visual modalities. Multiple events can overlap in the timeline, making identification challenging. While traditional methods usually focus on improving the early audio-visual encoders to embed more effective features, the decoding phase -- crucial for final event classification, often receives less attention. We aim to advance the decoding phase and improve its interpretability. Specifically, we introduce a new decoding paradigm, \underline{l}abel s\underline{e}m\underline{a}ntic-based \underline{p}rojection (LEAP), that employs labels texts of event categories, each bearing distinct and explicit semantics, for parsing potentially overlapping events.LEAP works by iteratively projecting encoded latent features of audio/visual segments onto semantically independent label embeddings. This process, enriched by modeling cross-modal (audio/visual-label) interactions, gradually disentangles event semantics within video segments to refine relevant label embeddings, guaranteeing a more discriminative and interpretable decoding process. To facilitate the LEAP paradigm, we propose a semantic-aware optimization strategy, which includes a novel audio-visual semantic similarity loss function. This function leverages the Intersection over Union of audio and visual events (EIoU) as a novel metric to calibrate audio-visual similarities at the feature level, accommodating the varied event densities across modalities. Extensive experiments demonstrate the superiority of our method, achieving new state-of-the-art performance for AVVP and also enhancing the relevant audio-visual event localization task.

cs.AI↗

arXiv2024

SWAP-NAS: Sample-Wise Activation Patterns for Ultra-fast NAS

Training-free metrics (a.k.a. zero-cost proxies) are widely used to avoid resource-intensive neural network training, especially in Neural Architecture Search (NAS). Recent studies show that existing training-free metrics have several limitations, such as limited correlation and poor generalisation across different search spaces and tasks. Hence, we propose Sample-Wise Activation Patterns and its derivative, SWAP-Score, a novel high-performance training-free metric. It measures the expressivity of networks over a batch of input samples. The SWAP-Score is strongly correlated with ground-truth performance across various search spaces and tasks, outperforming 15 existing training-free metrics on NAS-Bench-101/201/301 and TransNAS-Bench-101. The SWAP-Score can be further enhanced by regularisation, which leads to even higher correlations in cell-based search space and enables model size control during the search. For example, Spearman's rank correlation coefficient between regularised SWAP-Score and CIFAR-100 validation accuracies on NAS-Bench-201 networks is 0.90, significantly higher than 0.80 from the second-best metric, NWOT. When integrated with an evolutionary algorithm for NAS, our SWAP-NAS achieves competitive performance on CIFAR-10 and ImageNet in approximately 6 minutes and 9 minutes of GPU time respectively.

cs.LG↗

arXiv2024

Teaching with Uncertainty: Unleashing the Potential of Knowledge Distillation in Object Detection

Knowledge distillation (KD) is a widely adopted and effective method for compressing models in object detection tasks. Particularly, feature-based distillation methods have shown remarkable performance. Existing approaches often ignore the uncertainty in the teacher model's knowledge, which stems from data noise and imperfect training. This limits the student model's ability to learn latent knowledge, as it may overly rely on the teacher's imperfect guidance. In this paper, we propose a novel feature-based distillation paradigm with knowledge uncertainty for object detection, termed "Uncertainty Estimation-Discriminative Knowledge Extraction-Knowledge Transfer (UET)", which can seamlessly integrate with existing distillation methods. By leveraging the Monte Carlo dropout technique, we introduce knowledge uncertainty into the training process of the student model, facilitating deeper exploration of latent knowledge. Our method performs effectively during the KD process without requiring intricate structures or extensive computational resources. Extensive experiments validate the effectiveness of our proposed approach across various distillation strategies, detectors, and backbone architectures. Specifically, following our proposed paradigm, the existing FGD method achieves state-of-the-art (SoTA) performance, with ResNet50-based GFL achieving 44.1% mAP on the COCO dataset, surpassing the baselines by 3.9%.

cs.CV↗

arXiv2024

Predicting Genetic Mutation from Whole Slide Images via Biomedical-Linguistic Knowledge Enhanced Multi-label Classification

Predicting genetic mutations from whole slide images is indispensable for cancer diagnosis. However, existing work training multiple binary classification models faces two challenges: (a) Training multiple binary classifiers is inefficient and would inevitably lead to a class imbalance problem. (b) The biological relationships among genes are overlooked, which limits the prediction performance. To tackle these challenges, we innovatively design a Biological-knowledge enhanced PathGenomic multi-label Transformer to improve genetic mutation prediction performances. BPGT first establishes a novel gene encoder that constructs gene priors by two carefully designed modules: (a) A gene graph whose node features are the genes' linguistic descriptions and the cancer phenotype, with edges modeled by genes' pathway associations and mutation consistencies. (b) A knowledge association module that fuses linguistic and biomedical knowledge into gene priors by transformer-based graph representation learning, capturing the intrinsic relationships between different genes' mutations. BPGT then designs a label decoder that finally performs genetic mutation prediction by two tailored modules: (a) A modality fusion module that firstly fuses the gene priors with critical regions in WSIs and obtains gene-wise mutation logits. (b) A comparative multi-label loss that emphasizes the inherent comparisons among mutation status to enhance the discrimination capabilities. Sufficient experiments on The Cancer Genome Atlas benchmark demonstrate that BPGT outperforms the state-of-the-art.

cs.CV↗

arXiv2024

Two-stream Multi-level Dynamic Point Transformer for Two-person Interaction Recognition

As a fundamental aspect of human life, two-person interactions contain meaningful information about people's activities, relationships, and social settings. Human action recognition serves as the foundation for many smart applications, with a strong focus on personal privacy. However, recognizing two-person interactions poses more challenges due to increased body occlusion and overlap compared to single-person actions. In this paper, we propose a point cloud-based network named Two-stream Multi-level Dynamic Point Transformer for two-person interaction recognition. Our model addresses the challenge of recognizing two-person interactions by incorporating local-region spatial information, appearance information, and motion information. To achieve this, we introduce a designed frame selection method named Interval Frame Sampling (IFS), which efficiently samples frames from videos, capturing more discriminative information in a relatively short processing time. Subsequently, a frame features learning module and a two-stream multi-level feature aggregation module extract global and partial features from the sampled frames, effectively representing the local-region spatial information, appearance information, and motion information related to the interactions. Finally, we apply a transformer to perform self-attention on the learned features for the final classification. Extensive experiments are conducted on two large-scale datasets, the interaction subsets of NTU RGB+D 60 and NTU RGB+D 120. The results show that our network outperforms state-of-the-art approaches in most standard evaluation settings.

cs.CV↗

arXiv2024

Knowledge Distillation via the Target-aware Transformer

Knowledge distillation becomes a de facto standard to improve the performance of small neural networks. Most of the previous works propose to regress the representational features from the teacher to the student in a one-to-one spatial matching fashion. However, people tend to overlook the fact that, due to the architecture differences, the semantic information on the same spatial location usually vary. This greatly undermines the underlying assumption of the one-to-one distillation approach. To this end, we propose a novel one-to-all spatial matching knowledge distillation approach. Specifically, we allow each pixel of the teacher feature to be distilled to all spatial locations of the student features given its similarity, which is generated from a target-aware transformer. Our approach surpasses the state-of-the-art methods by a significant margin on various computer vision benchmarks, such as ImageNet, Pascal VOC and COCOStuff10k. Code is available at https://github.com/sihaoevery/TaT.

cs.CV↗