arXiv subjects

Chao Ma

Publications and source records attributed to Chao Ma.

At least 91 records · Page 5Linked to original sources

arXiv2024

Cross-View Consistency Regularisation for Knowledge Distillation

Knowledge distillation (KD) is an established paradigm for transferring privileged knowledge from a cumbersome model to a lightweight and efficient one. In recent years, logit-based KD methods are quickly catching up in performance with their feature-based counterparts. However, previous research has pointed out that logit-based methods are still fundamentally limited by two major issues in their training process, namely overconfident teacher and confirmation bias. Inspired by the success of cross-view learning in fields such as semi-supervised learning, in this work we introduce within-view and cross-view regularisations to standard logit-based distillation frameworks to combat the above cruxes. We also perform confidence-based soft label mining to improve the quality of distilling signals from the teacher, which further mitigates the confirmation bias problem. Despite its apparent simplicity, the proposed Consistency-Regularisation-based Logit Distillation (CRLD) significantly boosts student learning, setting new state-of-the-art results on the standard CIFAR-100, Tiny-ImageNet, and ImageNet datasets across a diversity of teacher and student architectures, whilst introducing no extra network parameters. Orthogonal to on-going logit-based distillation research, our method enjoys excellent generalisation properties and, without bells and whistles, boosts the performance of various existing approaches by considerable margins.

cs.CV↗

arXiv2024

Heterogeneous Graph Transformer for Multiple Tiny Object Tracking in RGB-T Videos

Tracking multiple tiny objects is highly challenging due to their weak appearance and limited features. Existing multi-object tracking algorithms generally focus on single-modality scenes, and overlook the complementary characteristics of tiny objects captured by multiple remote sensors. To enhance tracking performance by integrating complementary information from multiple sources, we propose a novel framework called {HGT-Track (Heterogeneous Graph Transformer based Multi-Tiny-Object Tracking)}. Specifically, we first employ a Transformer-based encoder to embed images from different modalities. Subsequently, we utilize Heterogeneous Graph Transformer to aggregate spatial and temporal information from multiple modalities to generate detection and tracking features. Additionally, we introduce a target re-detection module (ReDet) to ensure tracklet continuity by maintaining consistency across different modalities. Furthermore, this paper introduces the first benchmark VT-Tiny-MOT (Visible-Thermal Tiny Multi-Object Tracking) for RGB-T fused multiple tiny object tracking. Extensive experiments are conducted on VT-Tiny-MOT, and the results have demonstrated the effectiveness of our method. Compared to other state-of-the-art methods, our method achieves better performance in terms of MOTA (Multiple-Object Tracking Accuracy) and ID-F1 score. The code and dataset will be made available at https://github.com/xuqingyu26/HGTMT.

cs.CV↗

arXiv2024

A Fixed-Point Approach for Causal Generative Modeling

We propose a novel formalism for describing Structural Causal Models (SCMs) as fixed-point problems on causally ordered variables, eliminating the need for Directed Acyclic Graphs (DAGs), and establish the weakest known conditions for their unique recovery given the topological ordering (TO). Based on this, we design a two-stage causal generative model that first infers in a zero-shot manner a valid TO from observations, and then learns the generative SCM on the ordered variables. To infer TOs, we propose to amortize the learning of TOs on synthetically generated datasets by sequentially predicting the leaves of graphs seen during training. To learn SCMs, we design a transformer-based architecture that exploits a new attention mechanism enabling the modeling of causal structures, and show that this parameterization is consistent with our formalism. Finally, we conduct an extensive evaluation of each method individually, and show that when combined, our model outperforms various baselines on generated out-of-distribution problems. The code is available on \href{https://github.com/microsoft/causica/tree/main/research_experiments/fip}{Github}.

cs.LG↗

arXiv2024

XTrack: Multimodal Training Boosts RGB-X Video Object Trackers

Multimodal sensing has proven valuable for visual tracking, as different sensor types offer unique strengths in handling one specific challenging scene where object appearance varies. While a generalist model capable of leveraging all modalities would be ideal, development is hindered by data sparsity, typically in practice, only one modality is available at a time. Therefore, it is crucial to ensure and achieve that knowledge gained from multimodal sensing -- such as identifying relevant features and regions -- is effectively shared, even when certain modalities are unavailable at inference. We venture with a simple assumption: similar samples across different modalities have more knowledge to share than otherwise. To implement this, we employ a ``weak" classifier tasked with distinguishing between modalities. More specifically, if the classifier ``fails" to accurately identify the modality of the given sample, this signals an opportunity for cross-modal knowledge sharing. Intuitively, knowledge transfer is facilitated whenever a sample from one modality is sufficiently close and aligned with another. Technically, we achieve this by routing samples from one modality to the expert of the others, within a mixture-of-experts framework designed for multimodal video object tracking. During the inference, the expert of the respective modality is chosen, which we show to benefit from the multimodal knowledge available during training, thanks to the proposed method. Through the exhaustive experiments that use only paired RGB-E, RGB-D, and RGB-T during training, we showcase the benefit of the proposed method for RGB-X tracker during inference, with an average +3\% precision improvement over the current SOTA. Our source code is publicly available at https://github.com/supertyd/XTrack/tree/main.

cs.CV↗

arXiv2024

PhyCAGE: Physically Plausible Compositional 3D Asset Generation from a Single Image

We present PhyCAGE, the first approach for physically plausible compositional 3D asset generation from a single image. Given an input image, we first generate consistent multi-view images for components of the assets. These images are then fitted with 3D Gaussian Splatting representations. To ensure that the Gaussians representing objects are physically compatible with each other, we introduce a Physical Simulation-Enhanced Score Distillation Sampling (PSE-SDS) technique to further optimize the positions of the Gaussians. It is achieved by setting the gradient of the SDS loss as the initial velocity of the physical simulation, allowing the simulator to act as a physics-guided optimizer that progressively corrects the Gaussians' positions to a physically compatible state. Experimental results demonstrate that the proposed method can generate physically plausible compositional 3D assets given a single image.

cs.CV↗

arXiv2024

AVID: Adapting Video Diffusion Models to World Models

Large-scale generative models have achieved remarkable success in a number of domains. However, for sequential decision-making problems, such as robotics, action-labelled data is often scarce and therefore scaling-up foundation models for decision-making remains a challenge. A potential solution lies in leveraging widely-available unlabelled videos to train world models that simulate the consequences of actions. If the world model is accurate, it can be used to optimize decision-making in downstream tasks. Image-to-video diffusion models are already capable of generating highly realistic synthetic videos. However, these models are not action-conditioned, and the most powerful models are closed-source which means they cannot be finetuned. In this work, we propose to adapt pretrained video diffusion models to action-conditioned world models, without access to the parameters of the pretrained model. Our approach, AVID, trains an adapter on a small domain-specific dataset of action-labelled videos. AVID uses a learned mask to modify the intermediate outputs of the pretrained model and generate accurate action-conditioned videos. We evaluate AVID on video game and real-world robotics data, and show that it outperforms existing baselines for diffusion model adaptation.1 Our results demonstrate that if utilized correctly, pretrained video models have the potential to be powerful tools for embodied AI.

cs.CV↗

arXiv2024

Bulk Crystal Growth and Single-Crystal-to-Single-Crystal Phase Transitions in the Averievite CsClCu5V2O10

Quasi-two-dimensional averievites with triangle-kagome-triangle trilayers are of interest due to their rich structural and magnetic transitions and strong spin frustration that are expected to host quantum spin liquid ground state with suitable substitution or doping. Herein, we report growth of bulk single crystals of averievite CsClCu5V2O10 with dimensions of several millimeters on edge in order to (1) address the open question whether the room temperature crystal structure is P-3m1, P-3, P21/c or else, (2) to elucidate the nature of phase transitions, and (3) to study direction-dependent physical properties. Single-crystal-to-single-crystal structural transitions at ~305 K and ~127 K were observed in the averievite CsClCu5V2O10 single crystals. The nature of the transition at ~305 K, which was reported as P-3m1-P21/c transition, was found to be a structural transition from high temperature P-3m1 to low temperature P-3 by combining variable temperature synchrotron X-ray single crystal and high-resolution powder diffraction. In-plane and out-of-plane magnetic susceptibility and heat capacity measurements confirm a first-order transition at 305 K, a structural transition at 127 K and an antiferromagnetic transition at 24 K. These averievites are thus ideal model systems for a deeper understanding of structural transitions and magnetism.

cond-mat.str-el↗

arXiv2024

Deploying Multi-task Online Server with Large Language Model

In the industry, numerous tasks are deployed online. Traditional approaches often tackle each task separately by its own network, which leads to excessive costs for developing and scaling models, especially in the context of large language models. Although multi-task methods can save costs through parameter sharing, they often struggle to outperform single-task methods in real-world applications. To tackle these challenges, we present a three-stage multi-task learning framework for large language models. It involves task filtering, followed by fine-tuning on high-resource tasks, and finally fine-tuning on all tasks. We conducted comprehensive experiments in single-task and multi-task settings. Our approach, exemplified on different benchmarks, demonstrates that it is able to achieve performance comparable to the single-task method while reducing up to 90.9\% of its overhead.

cs.CL↗

arXiv2024

Probing disorder-induced time-reversal symmetry breaking in Josephson junctions

The relation between superconductivity and time-reversal symmetry (TRS) is one of the most fascinating problems in condensed matter physics. Although most superconductors inherently possess TRS, nonmagnetic disorder can induce states that demonstrate the breaking of this symmetry. Yet, the identification of experimental signatures of superconductivity with broken TRS remains a challenge. Here, we fabricate vertical Josephson junctions using metallic superconductor (Al) and ion bombarded Sr2RuO4 to study disorder-driven TRS breaking effects. We observe persistent magnetoresistive hysteresis behavior dependent on the disorder deposition time that provides evidence of TRS breaking below the superconducting transition temperature. Field and temperature dependent measurements suggest that the observed effects arise from disorder-induced anomalous flux in Sr2RuO4 which can be sensitively detected by superconducting Al. Our experimental results can be accounted within a physical framework of disorder-induced reconstruction of the superconducting order parameter as described within a multiband Ginzburg-Landau approach.

cond-mat.supr-con↗

arXiv2024

QuadMamba: Learning Quadtree-based Selective Scan for Visual State Space Model

Recent advancements in State Space Models, notably Mamba, have demonstrated superior performance over the dominant Transformer models, particularly in reducing the computational complexity from quadratic to linear. Yet, difficulties in adapting Mamba from language to vision tasks arise due to the distinct characteristics of visual data, such as the spatial locality and adjacency within images and large variations in information granularity across visual tokens. Existing vision Mamba approaches either flatten tokens into sequences in a raster scan fashion, which breaks the local adjacency of images, or manually partition tokens into windows, which limits their long-range modeling and generalization capabilities. To address these limitations, we present a new vision Mamba model, coined QuadMamba, that effectively captures local dependencies of varying granularities via quadtree-based image partition and scan. Concretely, our lightweight quadtree-based scan module learns to preserve the 2D locality of spatial regions within learned window quadrants. The module estimates the locality score of each token from their features, before adaptively partitioning tokens into window quadrants. An omnidirectional window shifting scheme is also introduced to capture more intact and informative features across different local regions. To make the discretized quadtree partition end-to-end trainable, we further devise a sequence masking strategy based on Gumbel-Softmax and its straight-through gradient estimator. Extensive experiments demonstrate that QuadMamba achieves state-of-the-art performance in various vision tasks, including image classification, object detection, instance segmentation, and semantic segmentation. The code is in https://github.com/VISION-SJTU/QuadMamba.

cs.CV↗

arXiv2024

Neural Material Adaptor for Visual Grounding of Intrinsic Dynamics

While humans effortlessly discern intrinsic dynamics and adapt to new scenarios, modern AI systems often struggle. Current methods for visual grounding of dynamics either use pure neural-network-based simulators (black box), which may violate physical laws, or traditional physical simulators (white box), which rely on expert-defined equations that may not fully capture actual dynamics. We propose the Neural Material Adaptor (NeuMA), which integrates existing physical laws with learned corrections, facilitating accurate learning of actual dynamics while maintaining the generalizability and interpretability of physical priors. Additionally, we propose Particle-GS, a particle-driven 3D Gaussian Splatting variant that bridges simulation and observed images, allowing back-propagate image gradients to optimize the simulator. Comprehensive experiments on various dynamics in terms of grounded particle accuracy, dynamic rendering quality, and generalization ability demonstrate that NeuMA can accurately capture intrinsic dynamics.

cs.CV↗

arXiv2024

Open-Vocabulary Remote Sensing Image Semantic Segmentation

Open-vocabulary image semantic segmentation (OVS) seeks to segment images into semantic regions across an open set of categories. Existing OVS methods commonly depend on foundational vision-language models and utilize similarity computation to tackle OVS tasks. However, these approaches are predominantly tailored to natural images and struggle with the unique characteristics of remote sensing images, such as rapidly changing orientations and significant scale variations. These challenges complicate OVS tasks in earth vision, requiring specialized approaches. To tackle this dilemma, we propose the first OVS framework specifically designed for remote sensing imagery, drawing inspiration from the distinct remote sensing traits. Particularly, to address the varying orientations, we introduce a rotation-aggregative similarity computation module that generates orientation-adaptive similarity maps as initial semantic maps. These maps are subsequently refined at both spatial and categorical levels to produce more accurate semantic maps. Additionally, to manage significant scale changes, we integrate multi-scale image features into the upsampling process, resulting in the final scale-aware semantic masks. To advance OVS in earth vision and encourage reproducible research, we establish the first open-sourced OVS benchmark for remote sensing imagery, including four public remote sensing datasets. Extensive experiments on this benchmark demonstrate our proposed method achieves state-of-the-art performance. All codes and datasets are available at https://github.com/caoql98/OVRS.

cs.CV↗

arXiv2024

Correlation-Embedded Transformer Tracking: A Single-Branch Framework

Developing robust and discriminative appearance models has been a long-standing research challenge in visual object tracking. In the prevalent Siamese-based paradigm, the features extracted by the Siamese-like networks are often insufficient to model the tracked targets and distractor objects, thereby hindering them from being robust and discriminative simultaneously. While most Siamese trackers focus on designing robust correlation operations, we propose a novel single-branch tracking framework inspired by the transformer. Unlike the Siamese-like feature extraction, our tracker deeply embeds cross-image feature correlation in multiple layers of the feature network. By extensively matching the features of the two images through multiple layers, it can suppress non-target features, resulting in target-aware feature extraction. The output features can be directly used for predicting target locations without additional correlation steps. Thus, we reformulate the two-branch Siamese tracking as a conceptually simple, fully transformer-based Single-Branch Tracking pipeline, dubbed SBT. After conducting an in-depth analysis of the SBT baseline, we summarize many effective design principles and propose an improved tracker dubbed SuperSBT. SuperSBT adopts a hierarchical architecture with a local modeling layer to enhance shallow-level features. A unified relation modeling is proposed to remove complex handcrafted layer pattern designs. SuperSBT is further improved by masked image modeling pre-training, integrating temporal modeling, and equipping with dedicated prediction heads. Thus, SuperSBT outperforms the SBT baseline by 4.7%,3.0%, and 4.5% AUC scores in LaSOT, TrackingNet, and GOT-10K. Notably, SuperSBT greatly raises the speed of SBT from 37 FPS to 81 FPS. Extensive experiments show that our method achieves superior results on eight VOT benchmarks.

cs.CV↗

arXiv2024

CP-VoteNet: Contrastive Prototypical VoteNet for Few-Shot Point Cloud Object Detection

Few-shot point cloud 3D object detection (FS3D) aims to identify and localise objects of novel classes from point clouds, using knowledge learnt from annotated base classes and novel classes with very few annotations. Thus far, this challenging task has been approached using prototype learning, but the performance remains far from satisfactory. We find that in existing methods, the prototypes are only loosely constrained and lack of fine-grained awareness of the semantic and geometrical correlation embedded within the point cloud space. To mitigate these issues, we propose to leverage the inherent contrastive relationship within the semantic and geometrical subspaces to learn more refined and generalisable prototypical representations. To this end, we first introduce contrastive semantics mining, which enables the network to extract discriminative categorical features by constructing positive and negative pairs within training batches. Meanwhile, since point features representing local patterns can be clustered into geometric components, we further propose to impose contrastive relationship at the primitive level. Through refined primitive geometric structures, the transferability of feature encoding from base to novel classes is significantly enhanced. The above designs and insights lead to our novel Contrastive Prototypical VoteNet (CP-VoteNet). Extensive experiments on two FS3D benchmarks FS-ScanNet and FS-SUNRGBD demonstrate that CP-VoteNet surpasses current state-of-the-art methods by considerable margins across different FS3D settings. Further ablation studies conducted corroborate the rationale and effectiveness of our designs.

cs.CV↗

arXiv2024

Frankenstein: Generating Semantic-Compositional 3D Scenes in One Tri-Plane

We present Frankenstein, a diffusion-based framework that can generate semantic-compositional 3D scenes in a single pass. Unlike existing methods that output a single, unified 3D shape, Frankenstein simultaneously generates multiple separated shapes, each corresponding to a semantically meaningful part. The 3D scene information is encoded in one single tri-plane tensor, from which multiple Singed Distance Function (SDF) fields can be decoded to represent the compositional shapes. During training, an auto-encoder compresses tri-planes into a latent space, and then the denoising diffusion process is employed to approximate the distribution of the compositional scenes. Frankenstein demonstrates promising results in generating room interiors as well as human avatars with automatically separated parts. The generated scenes facilitate many downstream applications, such as part-wise re-texturing, object rearrangement in the room or avatar cloth re-targeting. Our project page is available at: https://wolfball.github.io/frankenstein/.

cs.CV↗

arXiv2024

Free-breathing 3D cardiac extracellular volume (ECV) mapping using a linear tangent space alignment (LTSA) model

$\textbf{Purpose:}$ To develop a new method for free-breathing 3D extracellular volume (ECV) mapping of the whole heart at 3T. $\textbf{Methods:}$ A free-breathing 3D cardiac ECV mapping method was developed at 3T. T1 mapping was performed before and after contrast agent injection using a free-breathing ECG-gated inversion-recovery sequence with spoiled gradient echo readout. A linear tangent space alignment (LTSA) model-based method was used to reconstruct high-frame-rate dynamic images from (k,t)-space data sparsely sampled along a random stack-of-stars trajectory. Joint T1 and transmit B1 estimation was performed voxel-by-voxel for pre- and post-contrast T1 mapping. To account for the time-varying T1 after contrast agent injection, a linearly time-varying T1 model was introduced for post-contrast T1 mapping. ECV maps were generated by aligning pre- and post-contrast T1 maps through affine transformation. $\textbf{Results:}$ The feasibility of the proposed method was demonstrated using in vivo studies with six healthy volunteers at 3T. We obtained 3D ECV maps at a spatial resolution of 1.9$\times$1.9$\times$4.5 $mm^{3}$ and a FOV of 308$\times$308$\times$144 $mm^{3}$, with a scan time of 10.1$\pm$1.4 and 10.6$\pm$1.6 min before and after contrast agent injection, respectively. The ECV maps and the pre- and post-contrast T1 maps obtained by the proposed method were in good agreement with the 2D MOLLI method both qualitatively and quantitatively. $\textbf{Conclusion:}$ The proposed method allows for free-breathing 3D ECV mapping of the whole heart within a practically feasible imaging time. The estimated ECV values from the proposed method were comparable to those from the existing method. $\textbf{Keywords:}$ cardiac extracellular volume (ECV) mapping, cardiac T1 mapping, linear tangent space alignment (LTSA), manifold learning

physics.med-ph↗

arXiv2024

TSC: A Simple Two-Sided Constraint against Over-Smoothing

Graph Convolutional Neural Network (GCN), a widely adopted method for analyzing relational data, enhances node discriminability through the aggregation of neighboring information. Usually, stacking multiple layers can improve the performance of GCN by leveraging information from high-order neighbors. However, the increase of the network depth will induce the over-smoothing problem, which can be attributed to the quality and quantity of neighbors changing: (a) neighbor quality, node's neighbors become overlapping in high order, leading to aggregated information becoming indistinguishable, (b) neighbor quantity, the exponentially growing aggregated neighbors submerges the node's initial feature by recursively aggregating operations. Current solutions mainly focus on one of the above causes and seldom consider both at once. Aiming at tackling both causes of over-smoothing in one shot, we introduce a simple Two-Sided Constraint (TSC) for GCNs, comprising two straightforward yet potent techniques: random masking and contrastive constraint. The random masking acts on the representation matrix's columns to regulate the degree of information aggregation from neighbors, thus preventing the convergence of node representations. Meanwhile, the contrastive constraint, applied to the representation matrix's rows, enhances the discriminability of the nodes. Designed as a plug-in module, TSC can be easily coupled with GCN or SGC architectures. Experimental analyses on diverse real-world graph datasets verify that our approach markedly reduces the convergence of node's representation and the performance degradation in deeper GCN.

cs.LG↗

arXiv2024

Point-supervised Brain Tumor Segmentation with Box-prompted MedSAM

Delineating lesions and anatomical structure is important for image-guided interventions. Point-supervised medical image segmentation (PSS) has great potential to alleviate costly expert delineation labeling. However, due to the lack of precise size and boundary guidance, the effectiveness of PSS often falls short of expectations. Although recent vision foundational models, such as the medical segment anything model (MedSAM), have made significant advancements in bounding-box-prompted segmentation, it is not straightforward to utilize point annotation, and is prone to semantic ambiguity. In this preliminary study, we introduce an iterative framework to facilitate semantic-aware point-supervised MedSAM. Specifically, the semantic box-prompt generator (SBPG) module has the capacity to convert the point input into potential pseudo bounding box suggestions, which are explicitly refined by the prototype-based semantic similarity. This is then succeeded by a prompt-guided spatial refinement (PGSR) module that harnesses the exceptional generalizability of MedSAM to infer the segmentation mask, which also updates the box proposal seed in SBPG. Performance can be progressively improved with adequate iterations. We conducted an evaluation on BraTS2018 for the segmentation of whole brain tumors and demonstrated its superior performance compared to traditional PSS methods and on par with box-supervised methods.

cs.CV↗