Recent advances in flow matching models, particularly with reinforcement learning (RL), have significantly enhanced human preference alignment in few-step text-to-image generators. However, existing RL-based approaches for flow matching models typically rely on numerous denoising steps, while suffering from sparse and imprecise reward signals that often lead to suboptimal alignment. To address these limitations, we propose Temperature-Annealed Few-step Sampling with Group Relative Policy Optimization (TAFS-GRPO), a novel framework for training flow matching text-to-image models into efficient few-step generators well aligned with human preferences. Our method iteratively injects adaptive time-dependent noise into one-step clean predictions. By repeatedly annealing the model's sampled outputs, it introduces stochasticity into the sampling process while preserving the semantic integrity of each generated image. Moreover, its step-aware advantage integration mechanism combines GRPO with temperature-annealed sampling to eliminate the need for a differentiable reward function and provide dense, step-specific rewards for stable policy optimization. Extensive experiments demonstrate that TAFS-GRPO achieves strong performance in few-step text-to-image generation and significantly improves the alignment of generated images with human preferences. The code and models of this work will be available to facilitate further research.
Active Diffusion Matching: Score-based Iterative Alignment of Cross-Modal Retinal Images
ASRI, Dept. of ECE, Seoul National University（首尔大学电子与计算机工程系ASRI）；Dept. of Ophthalmology, Kangbuk Samsung Hospital, Sungkyunkwan University（成均馆大学三星首尔医院眼科）；School of Electrical Engineering, Kookmin University（国民大学电气工程学院）
Value Gradient Guidance for Flow Matching Alignment
The Chinese University of Hong Kong (Shenzhen)（香港中文大学（深圳））；University of Tübingen（图宾根大学）；Microsoft Research（微软研究院）；The Chinese University of Hong Kong（香港中文大学）；Mila – Quebec AI Institute（魁北克AI研究所）
Joint Alignment and Distillation for Video Generation via Sample-Guided Distribution Matching
Tsinghua University（清华大学）；Kuaishou Technology（快手科技）；Harbin Institute of Technology (ShenZhen)（哈尔滨工业大学（深圳））；Beijing University of Posts and Telecommunications（北京邮电大学）
STORK: Faster Diffusion And Flow Matching Sampling By Resolving Both Stiffness And Structure-Dependence
Department of Mathematics, University of California, Los Angeles（数学系，加州大学洛杉矶分校）；Department of Computer Science, University of California, Los Angeles（计算机科学系，加州大学洛杉矶分校）
TMPO: Trajectory Matching Policy Optimization for Diverse and Efficient Diffusion Alignment
Huazhong University of Science and Technology（华中科技大学）；Kuaishou Technology（快手科技）；Nanyang Technological University（南洋理工大学）；Wuhan University（武汉大学）；Tsinghua University（清华大学）
Image-text matching plays a central role in bridging the semantic gap between vision and language. The key point to achieve precise visual-semantic alignment lies in capturing the fine-grained cross-modal correspondence between image and text. Most previous methods rely on single-step reasoning to discover the visual-semantic interactions, which lacks the ability of exploiting the multi-level information to locate the hierarchical fine-grained relevance. Different from them, in this work, we propose a step-wise hierarchical alignment network (SHAN) that decomposes image-text matching into mult…
Facial alignment involves finding a set of landmark points on an image with a known semantic meaning. However, this semantic meaning of landmark points is often lost in 2D approaches where landmarks are either moved to visible boundaries or ignored as the pose of the face changes. In order to extract consistent alignment points across large poses, the 3D structure of the face must be considered in the alignment step. However, extracting a 3D structure from a single 2D image usually requires alignment in the first place. We present our novel approach to simultaneously extract the 3D shape of th…
Geometric matching is a key step in computer vision tasks. Previous learning-based methods for geometric matching concentrate more on improving alignment quality, while we argue the importance of naturalness issue simultaneously. To deal with this, firstly, Pearson correlation is applied to handle large intra-class variations of features in feature matching stage. Then, we parametrize homography transformation with 9 parameters in full connected layer of our network, to better characterize large viewpoint variations compared with affine transformation. Furthermore, a novel loss function with G…
GraphAlign: Enhancing Accurate Feature Alignment by Graph matching for Multi-Modal 3D Object Detection
School of Computer and Information Technology, Beijing Jiaotong University（北京交通大学计算机与信息技术学院）；School of Information Science and Engineering, Hebei University of Science and Technology（河北科技大学信息科学与工程学院）；State Key Laboratory of Automotive Safety and Energy, Tsinghua University（清华大学汽车安全与节能国家重点实验室）
Huazhong University of Science and Technology（华中科技大学）
Image feature point matching is a key step in Structure from Motion(SFM). However, it is becoming more and more time consuming because the number of images is getting larger and larger. In this paper, we proposed a GPU accelerated image matching method with improved Cascade Hashing. Firstly, we propose a Disk-Memory-GPU data exchange strategy and optimize the load order of data, so that the proposed method can deal with big data. Next, we parallelize the Cascade Hashing method on GPU. An improved parallel reduction and an improved parallel hashing ranking are proposed to fulfill this task. Fin…
RoMa v2: Harder Better Faster Denser Feature Matching
Linköping University（_linköping大学）；Chalmers University of Technology（_chalmers技术大学）；University of Amsterdam（_阿姆斯特丹大学）；Centre for Mathematical Sciences, Lund University（_数学科学中心，吕勒奥大学）
Bio-Key International Inc.（Bio-Key国际公司）；Capella University（卡佩拉大学）
A novel minutia-based fingerprint matching algorithm is proposed that employs iterative global alignment on two minutia sets. The matcher considers all possible minutia pairings and iteratively aligns the two sets until the number of minutia pairs does not exceed the maximum number of allowable one-to-one pairings. The optimal alignment parameters are derived analytically via linear least squares. The first alignment establishes a region of overlap between the two minutia sets, which is then (iteratively) refined by each successive alignment. After each alignment, minutia pairs that exhibit we…
Multi-Order Matching Network for Alignment-Free Depth Super-Resolution
PCA Lab, School of Computer Science and Engineering, Nanjing University of Science and Technology（计算机科学与工程学院PCA实验室，南京理工大学）；School of Computing, National University of Singapore（新加坡国立大学计算机学院）；School of Computer Science, Nankai University（南开大学计算机学院）；PCA Lab, School of Intelligence Science and Technology, Nanjing University（智能科学与技术学院PCA实验室，南京大学）
Partial person re-identification involves matching pedestrian frames where only a part of a body is visible in corresponding images. This reflects practical CCTV surveillance scenario, where full person views are often not available. Missing body parts make the comparison very challenging due to significant misalignment and varying scale of the views. We propose Partial Matching Net (PMN) that detects body joints, aligns partial views and hallucinates the missing parts based on the information present in the frame and a learned model of a person. The aligned and reconstructed views are then co…
Latent fingerprint matching is a very important but unsolved problem. As a key step of fingerprint matching, fingerprint registration has a great impact on the recognition performance. Existing latent fingerprint registration approaches are mainly based on establishing correspondences between minutiae, and hence will certainly fail when there are no sufficient number of extracted minutiae due to small fingerprint area or poor image quality. Minutiae extraction has become the bottleneck of latent fingerprint registration. In this paper, we propose a non-minutia latent fingerprint registration m…
Dalian University of Technology（大连理工大学）；Tencent AI Lab（腾讯人工智能实验室）；Meituan（美团）
Image-text matching plays a critical role in bridging the vision and language, and great progress has been made by exploiting the global alignment between image and sentence, or local alignments between regions and words. However, how to make the most of these alignments to infer more accurate matching scores is still underexplored. In this paper, we propose a novel Similarity Graph Reasoning and Attention Filtration (SGRAF) network for image-text matching. Specifically, the vector-based similarity representations are firstly learned to characterize the local and global alignments in a more co…
A widely used method for determining the similarity of two labeled trees is to compute a maximum agreement subtree of the two trees. Previous work on this similarity measure is only concerned with the comparison of labeled trees of two special kinds, namely, uniformly labeled trees (i.e., trees with all their nodes labeled by the same symbol) and evolutionary trees (i.e., leaf-labeled trees with distinct symbols for distinct leaves). This paper presents an algorithm for comparing trees that are labeled in an arbitrary manner. In addition to this generality, this algorithm is faster than the pr…
University of Surrey（萨里大学）；Adobe Research（奥多比研究院）；University of California, San Diego（加州大学圣地亚哥分校）
We propose VADER, a spatio-temporal matching, alignment, and change summarization method to help fight misinformation spread via manipulated videos. VADER matches and coarsely aligns partial video fragments to candidate videos using a robust visual descriptor and scalable search over adaptively chunked video content. A transformer-based alignment module then refines the temporal localization of the query fragment within the matched video. A space-time comparator module identifies regions of manipulation between aligned content, invariant to any changes due to any residual temporal misalignment…
Deep learning for object classification relies heavily on convolutional models. While effective, CNNs are rarely interpretable after the fact. An attention mechanism can be used to highlight the area of the image that the model focuses on thus offering a narrow view into the mechanism of classification. We expand on this idea by forcing the method to explicitly align images to be classified to reference images representing the classes. The mechanism of alignment is learned and therefore does not require that the reference objects are anything like those being classified. Beyond explanation, ou…
Beyond Trajectory Matching: Reflow with Marginal Distribution Alignment
Department of Statistics and Data Science, Tsinghua University（统计与数据科学系，清华大学）；Department of Computer Science and Technology, Tsinghua University（计算机科学与技术系，清华大学）；Bytedance Inc（字节跳动公司）
Laval University（拉瓦尔大学）；University Hassan First（哈桑一世大学）
We propose a new method for shape recognition and retrieval based on dynamic programming. Our approach uses the dynamic programming algorithm to compute the optimal score and to find the optimal alignment between two strings. First, each contour of shape is represented by a set of points. After alignment and matching between two shapes, the contours are transformed into a string of symbols and numbers. Finally we find the best alignment of two complete strings and compute the optimal cost of similarity. In general, dynamic programming has two phases: the forward phase and the backward phase. I…
In this paper, we propose a novel domain adaptation method for the source-free setting. In this setting, we cannot access source data during adaptation, while unlabeled target data and a model pretrained with source data are given. Due to lack of source data, we cannot directly match the data distributions between domains unlike typical domain adaptation algorithms. To cope with this problem, we propose utilizing batch normalization statistics stored in the pretrained model to approximate the distribution of unobserved source data. Specifically, we fix the classifier part of the model during a…
College of Computer and Information Sciences, King Saud University（沙特国王大学计算机与信息科学学院）
The existing automatic fingerprint verification methods are designed to work under the assumption that the same sensor is installed for enrollment and authentication (regular matching). There is a remarkable decrease in efficiency when one type of contact-based sensor is employed for enrolment and another type of contact-based sensor is used for authentication (cross-matching or fingerprint sensor interoperability problem,). The ridge orientation patterns in a fingerprint are invariant to sensor type. Based on this observation, we propose a robust fingerprint descriptor called the co-occurrenc…
We present a convex mixed-integer programming formulation for non-rigid shape matching. To this end, we propose a novel shape deformation model based on an efficient low-dimensional discrete model, so that finding a globally optimal solution is tractable in (most) practical cases. Our approach combines several favourable properties: it is independent of the initialisation, it is much more efficient to solve to global optimality compared to analogous quadratic assignment problem formulations, and it is highly flexible in terms of the variants of matching problems it can handle. Experimentally w…
Duke University（杜克大学）；Microsoft Dynamics 365 AI Research（微软 Dynamics 365 人工智能研究院）
Cross-domain alignment between two sets of entities (e.g., objects in an image, words in a sentence) is fundamental to both computer vision and natural language processing. Existing methods mainly focus on designing advanced attention mechanisms to simulate soft alignment, with no training signals to explicitly encourage alignment. The learned attention matrices are also dense and lacks interpretability. We propose Graph Optimal Transport (GOT), a principled framework that germinates from recent advances in Optimal Transport (OT). In GOT, cross-domain alignment is formulated as a graph matchin…
ISTI-CNR（意大利国家研究委员会信息科学与技术研究所）；Univ. of Modena and Reggio Emilia（摩德纳和雷焦艾米利亚大学）
Image-text matching is gaining a leading role among tasks involving the joint understanding of vision and language. In literature, this task is often used as a pre-training objective to forge architectures able to jointly deal with images and texts. Nonetheless, it has a direct downstream application: cross-modal retrieval, which consists in finding images related to a given query text or vice-versa. Solving this task is of critical importance in cross-modal search engines. Many recent methods proposed effective solutions to the image-text matching problem, mostly using recent large vision-lan…
Few-shot object detection (FSOD) aims to detect objects using only a few examples. How to adapt state-of-the-art object detectors to the few-shot domain remains challenging. Object proposal is a key ingredient in modern object detectors. However, the quality of proposals generated for few-shot classes using existing methods is far worse than that of many-shot classes, e.g., missing boxes for few-shot classes due to misclassification or inaccurate spatial locations with respect to true objects. To address the noisy proposal problem, we propose a novel meta-learning based FSOD model by jointly o…
