텍스트-이미지 확산 모델(Text-to-image diffusion models)은 단일 개념을 잘 생성하지만, 여러 개념이 주어질 경우 개념을 누락하거나 잘못 병합하는 경우가 많습니다. 본 논문에서는 이러한 실패의 원인을 초기 조정 병목 현상(early coordination bottleneck)에서 찾았습니다. 즉, 노이즈 제거(denoising)가 시작되기 전에 프롬프트 조건부 어텐션(prompt-conditioned attention)이 서로 다른 개념들을 강하게 겹치는 공간적 지지 영역에 할당할 수 있으며, 이는 노이즈 제거가 진행됨에 따라 이들의 어텐션이 결합된 상태를 유지하게 만들 수 있습니다. 이러한 관찰은 조합형 생성(compositional generation)을 지속적으로 진화하는 궤적을 제어하는 방식 대신 경계 조건 문제(boundary-condition problem)로 다루도록 동기를 부여합니다. 이를 위해, 표준 노이즈 제거 이전에 초기 할당을 한 번 수정하는 학습 불필요(training-free) 프레임워크인 Rectify-then-Diffuse(RTD)를 제안합니다. 첫째로, 파일럿 개념 맵 간의 정규화된 중첩을 미분 가능하고 레이아웃에 구애받지 않는 분리 목적으로 변환하는 Soft-Overlap Disentanglement(SOD)를 제안합니다. 둘째로, SOD 그래디언트를 정규화하고 프롬프트 및 초기화 전반에 걸쳐 일관된 스케일로 유계 잠재 변위(bounded latent displacement)를 적용하는 Isotropic Gradient Rectification(IGR)을 도입합니다. 광범위한 실험을 통해 RTD가 최고 수준의 조합 충실도(compositional fidelity)와 강건한 성능 향상을 달성함을 보여줍니다. AE-Bench 객체 쌍 서브셋에서 RTD는 CO3 대비 2.3배 더 빠르게 실행되면서도 BLIP-VQA를 45.8%, ImageReward를 19.6% 향상시킵니다. 코드는 https://github.com/Z-yiwei/rectify-then-diffuse 에서 공개될 예정입니다.
확산 멀티모달 대규모 언어 모델(dMLLM)은 종종 의미 표류(semantic drift)와 반복으로 손상된 장문 출력을 생성하며, 출력 길이가 길어질수록 품질이 일반적으로 저하된다. 우리는 이러한 실패의 주요 원인으로 기존 디코딩 방법의 두 가지 구조적 결함을 밝힌다. 신뢰도 기반 채점은 디코딩된 이웃(neighbor) 지원을 무시하고, 블록 분할은 고준비(high-readiness) 의미 앵커(semantic anchor)에 대한 접근을 막아, 토큰이 지역 문맥이 충분히 확립되기 전에 확정(commit)되게 한다. 우리는 CACD(Context-Aware Cluster Decoding, 문맥 인식 클러스터 디코딩)를 제안한다. 이는 학습 없이(training-free) 적용하는 디코딩 방법으로, 각 마스크된 위치를 소프트맥스 신뢰도와 이웃 근접도의 곱셈적 복합 지표로 채점하여, 문맥적으로 준비된 토큰을 고립된 후보보다 우선시하고 낮은 신뢰도의 위치 노이즈를 억제하며, 블록 없이(block-free) 동작하여 고준비 앵커를 전역적으로 접근 가능하게 유지한다. CACD는 다양한 시각 통합 전략으로 유발되는 신뢰도 이질성을 처리하기 위해 아키텍처 인식(architecture-aware) 보정을 추가로 적용한다. 세 가지 dMLLM과 네 가지 벤치마크에 대한 실험은 Original 대비 일관된 품질 향상과 환각(hallucination) 감소를 보여 주며, 여러 장문 생성 설정에서 더 큰 이득을 보인다. 이는 향후 dMLLM 디코딩 방법 설계에서 이웃 지원과 시각 통합 전략의 중요성을 강조한다. 코드는 https://github.com/zhaoyk-sysu/CACD-dMLLM 에서 공개되어 있다.
With the increasing demand to efficiently deploy DNNs on mobile edge devices, it becomes much more important to reduce unnecessary computation and increase the execution speed. Prior methods towards this goal, including model compression and network architecture search (NAS), are largely performed independently and do not fully consider compiler-level optimizations which is a must-do for mobile acceleration. In this work, we first propose (i) a general category of fine-grained structured pruning applicable to various DNN layers, and (ii) a comprehensive, compiler automatic code generation framework supporting different DNNs and different pruning schemes, which bridge the gap of model compression and NAS. We further propose NPAS, a compiler-aware unified network pruning, and architecture search. To deal with large search space, we propose a meta-modeling procedure based on reinforcement learning with fast evaluation and Bayesian optimization, ensuring the total number of training epochs comparable with representative NAS frameworks. Our framework achieves 6.7ms, 5.9ms, 3.9ms ImageNet inference times with 78.2%, 75% (MobileNet-V3 level), and 71% (MobileNet-V2 level) Top-1 accuracy respectively on an off-the-shelf mobile phone, consistently outperforming prior work.
The statefulness property of network protocol implementations poses a unique challenge for testing and verification techniques, including Fuzzing. Stateful fuzzers tackle this challenge by leveraging state models to partition the state space and assist the test generation process. Since not all states are equally important and fuzzing campaigns have time limits, fuzzers need effective state selection algorithms to prioritize progressive states over others. Several state selection algorithms have been proposed but they were implemented and evaluated separately on different platforms, making it hard to achieve conclusive findings. In this work, we evaluate an extensive set of state selection algorithms on the same fuzzing platform that is AFLNet, a state-of-the-art fuzzer for network servers. The algorithm set includes existing ones supported by AFLNet and our novel and principled algorithm called AFLNetLegion. The experimental results on the ProFuzzBench benchmark show that (i) the existing state selection algorithms of AFLNet achieve very similar code coverage, (ii) AFLNetLegion clearly outperforms these algorithms in selected case studies, but (iii) the overall improvement appears insignificant. These are unexpected yet interesting findings. We identify problems and share insights that could open opportunities for future research on this topic.
Recent high-performing Human-Object Interaction (HOI) detection techniques have been highly influenced by Transformer-based object detector (i.e., DETR). Nevertheless, most of them directly map parametric interaction queries into a set of HOI predictions through vanilla Transformer in a one-stage manner. This leaves rich inter- or intra-interaction structure under-exploited. In this work, we design a novel Transformer-style HOI detector, i.e., Structure-aware Transformer over Interaction Proposals (STIP), for HOI detection. Such design decomposes the process of HOI set prediction into two subsequent phases, i.e., an interaction proposal generation is first performed, and then followed by transforming the non-parametric interaction proposals into HOI predictions via a structure-aware Transformer. The structure-aware Transformer upgrades vanilla Transformer by encoding additionally the holistically semantic structure among interaction proposals as well as the locally spatial structure of human/object within each interaction proposal, so as to strengthen HOI predictions. Extensive experiments conducted on V-COCO and HICO-DET benchmarks have demonstrated the effectiveness of STIP, and superior results are reported when comparing with the state-of-the-art HOI detectors. Source code is available at \url{https://github.com/zyong812/STIP}.
Compared to the existing function-based models in deep generative modeling, the recently proposed diffusion models have achieved outstanding performance with a stochastic-process-based approach. But a long sampling time is required for this approach due to many timesteps for discretization. Schr\"odinger bridge (SB)-based models attempt to tackle this problem by training bidirectional stochastic processes between distributions. However, they still have a slow sampling speed compared to generative models such as generative adversarial networks. And due to the training of the bidirectional stochastic processes, they require a relatively long training time. Therefore, this study tried to reduce the number of timesteps and training time required and proposed regularization terms to the existing SB models to make the bidirectional stochastic processes consistent and stable with a reduced number of timesteps. Each regularization term was integrated into a single term to enable more efficient training in computation time and memory usage. Applying this regularized stochastic process to various generation tasks, the desired translations between different distributions were obtained, and accordingly, the possibility of generative modeling based on a stochastic process with faster sampling speed could be confirmed. The code is available at https://github.com/KiUngSong/RSB.
This paper presents a rapid-prototype Model Predictive Control (MPC) tool based on the gPROMS platform, with the support for the whole MPC design workflow. The gPROMS-MPC tool can not only directly interact with a first-principle-based gPROMS model for closed-loop simulations but also utilizes its mathematical information to derive simplified control-oriented models, basically via linearization techniques. It can inherit the interpretability of the first-principle-based gPROMS model, unlike the PAROC framework in which the control-oriented models are obtained from black-box system identification based on gPROMS simulation data. The gPROMS-MPC tool allows users to choose when to linearize such as at each sampling time (successive linearization) or some specific points to obtain one or multiple good linear models. The gPROMS-MPC tool implements our previous construction-free CDAL and the online parametric active-set qpOASES algorithms to solve sparse or condensed MPC problem formulations, respectively, for possible successive linearization or high state-dimension cases. Our CDAL algorithm is also matrix-free and library-free, thus supporting embedded C-code generation. After many example validations of the tool, here we only show one example to investigate the performance of different MPC schemes.
Although current deep learning-based methods have gained promising performance in the blind single image super-resolution (SISR) task, most of them mainly focus on heuristically constructing diverse network architectures and put less emphasis on the explicit embedding of the physical generation mechanism between blur kernels and high-resolution (HR) images. To alleviate this issue, we propose a model-driven deep neural network, called KXNet, for blind SISR. Specifically, to solve the classical SISR model, we propose a simple-yet-effective iterative algorithm. Then by unfolding the involved iterative steps into the corresponding network module, we naturally construct the KXNet. The main specificity of the proposed KXNet is that the entire learning process is fully and explicitly integrated with the inherent physical mechanism underlying this SISR task. Thus, the learned blur kernel has clear physical patterns and the mutually iterative process between blur kernel and HR image can soundly guide the KXNet to be evolved in the right direction. Extensive experiments on synthetic and real data finely demonstrate the superior accuracy and generality of our method beyond the current representative state-of-the-art blind SISR methods. Code is available at: https://github.com/jiahong-fu/KXNet.
Methane (CH$_4$) is the chief contributor to global climate change. Recent Airborne Visible-Infrared Imaging Spectrometer-Next Generation (AVIRIS-NG) has been very useful in quantitative mapping of methane emissions. Existing methods for analyzing this data are sensitive to local terrain conditions, often require manual inspection from domain experts, prone to significant error and hence are not scalable. To address these challenges, we propose a novel end-to-end spectral absorption wavelength aware transformer network, MethaneMapper, to detect and quantify the emissions. MethaneMapper introduces two novel modules that help to locate the most relevant methane plume regions in the spectral domain and uses them to localize these accurately. Thorough evaluation shows that MethaneMapper achieves 0.63 mAP in detection and reduces the model size (by 5x) compared to the current state of the art. In addition, we also introduce a large-scale dataset of methane plume segmentation mask for over 1200 AVIRIS-NG flight lines from 2015-2022. It contains over 4000 methane plume sites. Our dataset will provide researchers the opportunity to develop and advance new methods for tackling this challenging green-house gas detection problem with significant broader social impact. Dataset and source code are public
In this paper, we introduce a new sequence-to-sequence learning framework for RGB-based and multi-modal object tracking. First, we present SeqTrack for RGB-based tracking. It casts visual tracking as a sequence generation task, forecasting object bounding boxes in an autoregressive manner. This differs from previous trackers, which depend on the design of intricate head networks, such as classification and regression heads. SeqTrack employs a basic encoder-decoder transformer architecture. The encoder utilizes a bidirectional transformer for feature extraction, while the decoder generates bounding box sequences autoregressively using a causal transformer. The loss function is a plain cross-entropy. Second, we introduce SeqTrackv2, a unified sequence-to-sequence framework for multi-modal tracking tasks. Expanding upon SeqTrack, SeqTrackv2 integrates a unified interface for auxiliary modalities and a set of task-prompt tokens to specify the task. This enables it to manage multi-modal tracking tasks using a unified model and parameter set. This sequence learning paradigm not only simplifies the tracking framework, but also showcases superior performance across 14 challenging benchmarks spanning five single- and multi-modal tracking tasks. The code and models are available at https://github.com/chenxin-dlut/SeqTrackv2.
Domain adaptation (DA) aims to transfer knowledge from a fully labeled source to a scarcely labeled or totally unlabeled target under domain shift. Recently, semi-supervised learning-based (SSL) techniques that leverage pseudo labeling have been increasingly used in DA. Despite the competitive performance, these pseudo labeling methods rely heavily on the source domain to generate pseudo labels for the target domain and therefore still suffer considerably from source data bias. Moreover, class distribution bias in the target domain is also often ignored in the pseudo label generation and thus leading to further deterioration of performance. In this paper, we propose GeT that learns a non-bias target embedding distribution with high quality pseudo labels. Specifically, we formulate an online target generative classifier to induce the target distribution into distinctive Gaussian components weighted by their class priors to mitigate source data bias and enhance target class discriminability. We further propose a structure similarity regularization framework to alleviate target class distribution bias and further improve target class discriminability. Experimental results show that our proposed GeT is effective and achieves consistent improvements under various DA settings with and without class distribution bias. Our code is available at: https://lulusindazc.github.io/getproject/.
A diffusion model, which is formulated to produce an image using thousands of denoising steps, usually suffers from a slow inference speed. Existing acceleration algorithms simplify the sampling by skipping most steps yet exhibit considerable performance degradation. By viewing the generation of diffusion models as a discretized integrating process, we argue that the quality drop is partly caused by applying an inaccurate integral direction to a timestep interval. To rectify this issue, we propose a timestep aligner that helps find a more accurate integral direction for a particular interval at the minimum cost. Specifically, at each denoising step, we replace the original parameterization by conditioning the network on a new timestep, which is obtained by aligning the sampling distribution to the real distribution. Extensive experiments show that our plug-in design can be trained efficiently and boost the inference performance of various state-of-the-art acceleration methods, especially when there are few denoising steps. For example, when using 10 denoising steps on the popular LSUN Bedroom dataset, we improve the FID of DDIM from 9.65 to 6.07, simply by adopting our method for a more appropriate set of timesteps. Code will be made publicly available.
The registration of pathological images plays an important role in medical applications. Despite its significance, most researchers in this field primarily focus on the registration of normal tissue into normal tissue. The negative impact of focal tissue, such as the loss of spatial correspondence information and the abnormal distortion of tissue, are rarely considered. In this paper, we propose GIRNet, a novel unsupervised approach for pathological image registration by incorporating segmentation and inpainting through the principles of Generation, Inpainting, and Registration (GIR). The registration, segmentation, and inpainting modules are trained simultaneously in a co-learning manner so that the segmentation of the focal area and the registration of inpainted pairs can improve collaboratively. Overall, the registration of pathological images is achieved in a completely unsupervised learning framework. Experimental results on multiple datasets, including Magnetic Resonance Imaging (MRI) of T1 sequences, demonstrate the efficacy of our proposed method. Our results show that our method can accurately achieve the registration of pathological images and identify lesions even in challenging imaging modalities. Our unsupervised approach offers a promising solution for the efficient and cost-effective registration of pathological images. Our code is available at https://github.com/brain-intelligence-lab/GIRNet.
The diffusion model has been proven a powerful generative model in recent years, yet remains a challenge in generating visual text. Several methods alleviated this issue by incorporating explicit text position and content as guidance on where and what text to render. However, these methods still suffer from several drawbacks, such as limited flexibility and automation, constrained capability of layout prediction, and restricted style diversity. In this paper, we present TextDiffuser-2, aiming to unleash the power of language models for text rendering. Firstly, we fine-tune a large language model for layout planning. The large language model is capable of automatically generating keywords for text rendering and also supports layout modification through chatting. Secondly, we utilize the language model within the diffusion model to encode the position and texts at the line level. Unlike previous methods that employed tight character-level guidance, this approach generates more diverse text images. We conduct extensive experiments and incorporate user studies involving human participants as well as GPT-4V, validating TextDiffuser-2's capacity to achieve a more rational text layout and generation with enhanced diversity. The code and model will be available at \url{https://aka.ms/textdiffuser-2}.
Task planning for embodied AI has been one of the most challenging problems where the community does not meet a consensus in terms of formulation. In this paper, we aim to tackle this problem with a unified framework consisting of an end-to-end trainable method and a planning algorithm. Particularly, we propose a task-agnostic method named 'planning as in-painting'. In this method, we use a Denoising Diffusion Model (DDM) for plan generation, conditioned on both language instructions and perceptual inputs under partially observable environments. Partial observation often leads to the model hallucinating the planning. Therefore, our diffusion-based method jointly models both state trajectory and goal estimation to improve the reliability of the generated plan, given the limited available information at each step. To better leverage newly discovered information along the plan execution for a higher success rate, we propose an on-the-fly planning algorithm to collaborate with the diffusion-based planner. The proposed framework achieves promising performances in various embodied AI tasks, including vision-language navigation, object manipulation, and task planning in a photorealistic virtual environment. The code is available at: https://github.com/joeyy5588/planning-as-inpainting.
This paper presents a new exploration into a category of diffusion models built upon state space architecture. We endeavor to train diffusion models for image data, wherein the traditional U-Net backbone is supplanted by a state space backbone, functioning on raw patches or latent space. Given its notable efficacy in accommodating long-range dependencies, Diffusion State Space Models (DiS) are distinguished by treating all inputs including time, condition, and noisy image patches as tokens. Our assessment of DiS encompasses both unconditional and class-conditional image generation scenarios, revealing that DiS exhibits comparable, if not superior, performance to CNN-based or Transformer-based U-Net architectures of commensurate size. Furthermore, we analyze the scalability of DiS, gauged by the forward pass complexity quantified in Gflops. DiS models with higher Gflops, achieved through augmentation of depth/width or augmentation of input tokens, consistently demonstrate lower FID. In addition to demonstrating commendable scalability characteristics, DiS-H/2 models in latent space achieve performance levels akin to prior diffusion models on class-conditional ImageNet benchmarks at the resolution of 256$\times$256 and 512$\times$512, while significantly reducing the computational burden. The code and models are available at: https://github.com/feizc/DiS.
Advancements in 3D Gaussian Splatting have significantly accelerated 3D reconstruction and generation. However, it may require a large number of Gaussians, which creates a substantial memory footprint. This paper introduces GES (Generalized Exponential Splatting), a novel representation that employs Generalized Exponential Function (GEF) to model 3D scenes, requiring far fewer particles to represent a scene and thus significantly outperforming Gaussian Splatting methods in efficiency with a plug-and-play replacement ability for Gaussian-based utilities. GES is validated theoretically and empirically in both principled 1D setup and realistic 3D scenes. It is shown to represent signals with sharp edges more accurately, which are typically challenging for Gaussians due to their inherent low-pass characteristics. Our empirical analysis demonstrates that GEF outperforms Gaussians in fitting natural-occurring signals (e.g. squares, triangles, and parabolic signals), thereby reducing the need for extensive splitting operations that increase the memory footprint of Gaussian Splatting. With the aid of a frequency-modulated loss, GES achieves competitive performance in novel-view synthesis benchmarks while requiring less than half the memory storage of Gaussian Splatting and increasing the rendering speed by up to 39%. The code is available on the project website https://abdullahamdi.com/ges .
Teaching robots new skills quickly and conveniently is crucial for the broader adoption of robotic systems. In this work, we address the problem of one-shot imitation from a single human demonstration, given by an RGB-D video recording. We propose a two-stage process. In the first stage we extract the demonstration trajectory offline. This entails segmenting manipulated objects and determining their relative motion in relation to secondary objects such as containers. In the online trajectory generation stage, we first re-detect all objects, then warp the demonstration trajectory to the current scene and execute it on the robot. To complete these steps, our method leverages several ancillary models, including those for segmentation, relative object pose estimation, and grasp prediction. We systematically evaluate different combinations of correspondence and re-detection methods to validate our design decision across a diverse range of tasks. Specifically, we collect and quantitatively test on demonstrations of ten different tasks including pick-and-place tasks as well as articulated object manipulation. Finally, we perform extensive evaluations on a real robot system to demonstrate the effectiveness and utility of our approach in real-world scenarios. We make the code publicly available at http://ditto.cs.uni-freiburg.de.
Large Language Models (LLMs) have demonstrated remarkable capabilities in various domains, including data augmentation and synthetic data generation. This work explores the use of LLMs to generate rich textual descriptions for motion sequences, encompassing both actions and walking patterns. We leverage the expressive power of LLMs to align motion representations with high-level linguistic cues, addressing two distinct tasks: action recognition and retrieval of walking sequences based on appearance attributes. For action recognition, we employ LLMs to generate textual descriptions of actions in the BABEL-60 dataset, facilitating the alignment of motion sequences with linguistic representations. In the domain of gait analysis, we investigate the impact of appearance attributes on walking patterns by generating textual descriptions of motion sequences from the DenseGait dataset using LLMs. These descriptions capture subtle variations in walking styles influenced by factors such as clothing choices and footwear. Our approach demonstrates the potential of LLMs in augmenting structured motion attributes and aligning multi-modal representations. The findings contribute to the advancement of comprehensive motion understanding and open up new avenues for leveraging LLMs in multi-modal alignment and data augmentation for motion analysis. We make the code publicly available at https://github.com/Radu1999/WalkAndText
Automatic live video commenting is with increasing attention due to its significance in narration generation, topic explanation, etc. However, the diverse sentiment consideration of the generated comments is missing from the current methods. Sentimental factors are critical in interactive commenting, and lack of research so far. Thus, in this paper, we propose a Sentiment-oriented Transformer-based Variational Autoencoder (So-TVAE) network which consists of a sentiment-oriented diversity encoder module and a batch attention module, to achieve diverse video commenting with multiple sentiments and multiple semantics. Specifically, our sentiment-oriented diversity encoder elegantly combines VAE and random mask mechanism to achieve semantic diversity under sentiment guidance, which is then fused with cross-modal features to generate live video comments. Furthermore, a batch attention module is also proposed in this paper to alleviate the problem of missing sentimental samples, caused by the data imbalance, which is common in live videos as the popularity of videos varies. Extensive experiments on Livebot and VideoIC datasets demonstrate that the proposed So-TVAE outperforms the state-of-the-art methods in terms of the quality and diversity of generated comments. Related code is available at https://github.com/fufy1024/So-TVAE.