The representation of atomic configurations for machine learning models has led to the development of numerous descriptors, often to describe the local environment of atoms. However, many of these representations are incomplete and/or functionally dependent. Incomplete descriptor sets are unable to represent all meaningful changes in the atomic environment. Complete constructions of atomic environment descriptors, on the other hand, often suffer from a high degree of functional dependence, where some descriptors can be written as functions of the others. These redundant descriptors do not provide additional power to discriminate between different atomic environments and increase the computational burden. By employing techniques from the pattern recognition literature to existing atomistic representations, we remove descriptors that are functions of other descriptors to produce the smallest possible set that satisfies completeness. We apply this in two ways: first we refine an existing description, the Atomistic Cluster Expansion. We show that this yields a more efficient subset of descriptors. Second, we augment an incomplete construction based on a scalar neural network, yielding a new message-passing network architecture that can recognize up to 5-body patterns in each neuron by taking advantage of an optimal set of Cartesian tensor invariants. This architecture shows strong accuracy on state-of-the-art benchmarks while retaining low computational cost. Our results not only yield improved models, but point the way to classes of invariant bases that minimize cost while maximizing expressivity for a host of applications.
Referring Video Object Segmentation (RVOS) aims to segment target objects throughout a video based on a text description. This task has attracted increasing attention in the field of computer vision due to its promising applications in video editing and human-agent interaction. Recently, ReferDINO has demonstrated promising performance in this task by adapting object-level vision-language knowledge from pretrained foundational image models. In this report, we further enhance its capabilities by incorporating the advantages of SAM2 in mask quality and object consistency. In addition, to effectively balance performance between single-object and multi-object scenarios, we introduce a conditional mask fusion strategy that adaptively fuses the masks from ReferDINO and SAM2. Our solution, termed ReferDINO-Plus, achieves 60.43 \(\mathcal{J}\&\mathcal{F}\) on MeViS test set, securing 2nd place in the MeViS PVUW challenge at CVPR 2025. The code is available at: https://github.com/iSEE-Laboratory/ReferDINO-Plus.
Deep neural networks face several challenges in hyperspectral image classification, including insufficient utilization of joint spatial-spectral information, gradient vanishing with increasing depth, and overfitting. To enhance feature extraction efficiency while skipping redundant information, this paper proposes a dynamic attention convolution design based on an improved 3D-DenseNet model. The design employs multiple parallel convolutional kernels instead of a single kernel and assigns dynamic attention weights to these parallel convolutions. This dynamic attention mechanism achieves adaptive feature response based on spatial characteristics in the spatial dimension of hyperspectral images, focusing more on key spatial structures. In the spectral dimension, it enables dynamic discrimination of different bands, alleviating information redundancy and computational complexity caused by high spectral dimensionality. The DAC module enhances model representation capability by attention-based aggregation of multiple convolutional kernels without increasing network depth or width. The proposed method demonstrates superior performance in both inference speed and accuracy, outperforming mainstream hyperspectral image classification methods on the IN, UP, and KSC datasets.
We present OpenDriveVLA, a Vision-Language Action (VLA) model designed for end-to-end autonomous driving. OpenDriveVLA builds upon open-source pre-trained large Vision-Language Models (VLMs) to generate reliable driving actions, conditioned on 3D environmental perception, ego vehicle states, and driver commands. To bridge the modality gap between driving visual representations and language embeddings, we propose a hierarchical vision-language alignment process, projecting both 2D and 3D structured visual tokens into a unified semantic space. Besides, OpenDriveVLA models the dynamic relationships between the ego vehicle, surrounding agents, and static road elements through an autoregressive agent-env-ego interaction process, ensuring both spatially and behaviorally informed trajectory planning. Extensive experiments on the nuScenes dataset demonstrate that OpenDriveVLA achieves state-of-the-art results across open-loop trajectory planning and driving-related question-answering tasks. Qualitative analyses further illustrate OpenDriveVLA's superior capability to follow high-level driving commands and robustly generate trajectories under challenging scenarios, highlighting its potential for next-generation end-to-end autonomous driving. We will release our code to facilitate further research in this domain.
This paper explores the task of Complex Visual Text Generation (CVTG), which centers on generating intricate textual content distributed across diverse regions within visual images. In CVTG, image generation models often rendering distorted and blurred visual text or missing some visual text. To tackle these challenges, we propose TextCrafter, a novel multi-visual text rendering method. TextCrafter employs a progressive strategy to decompose complex visual text into distinct components while ensuring robust alignment between textual content and its visual carrier. Additionally, it incorporates a token focus enhancement mechanism to amplify the prominence of visual text during the generation process. TextCrafter effectively addresses key challenges in CVTG tasks, such as text confusion, omissions, and blurriness. Moreover, we present a new benchmark dataset, CVTG-2K, tailored to rigorously evaluate the performance of generative models on CVTG tasks. Extensive experiments demonstrate that our method surpasses state-of-the-art approaches.
Vision Transformers (ViTs) have computational costs scaling quadratically with the number of tokens, calling for effective token pruning policies. Most existing policies are handcrafted, lacking adaptivity to varying inputs. Moreover, they fail to consider the sequential nature of token pruning across multiple layers. In this work, for the first time (as far as we know), we exploit Reinforcement Learning (RL) to data-adaptively learn a pruning policy. Formulating token pruning as a sequential decision-making problem, we model it as a Markov Game and utilize Multi-Agent Proximal Policy Optimization (MAPPO) where each agent makes an individualized pruning decision for a single token. We also develop reward functions that enable simultaneous collaboration and competition of these agents to balance efficiency and accuracy. On the well-known ImageNet-1k dataset, our method improves the inference speed by up to 44% while incurring only a negligible accuracy drop of 0.4%. The source code is available at https://github.com/daashuai/rl4evit.
Token compression is essential for reducing the computational and memory requirements of transformer models, enabling their deployment in resource-constrained environments. In this work, we propose an efficient and hardware-compatible token compression method called Prune and Merge. Our approach integrates token pruning and merging operations within transformer models to achieve layer-wise token compression. By introducing trainable merge and reconstruct matrices and utilizing shortcut connections, we efficiently merge tokens while preserving important information and enabling the restoration of pruned tokens. Additionally, we introduce a novel gradient-weighted attention scoring mechanism that computes token importance scores during the training phase, eliminating the need for separate computations during inference and enhancing compression efficiency. We also leverage gradient information to capture the global impact of tokens and automatically identify optimal compression structures. Extensive experiments on the ImageNet-1k and ADE20K datasets validate the effectiveness of our approach, achieving significant speed-ups with minimal accuracy degradation compared to state-of-the-art methods. For instance, on DeiT-Small, we achieve a 1.64$\times$ speed-up with only a 0.2\% drop in accuracy on ImageNet-1k. Moreover, by compressing segmenter models and comparing with existing methods, we demonstrate the superior performance of our approach in terms of efficiency and effectiveness. Code and models have been made available at https://github.com/NUST-Machine-Intelligence-Laboratory/prune_and_merge.
Recently, Vision Language Models (VLMs) have increasingly emphasized document visual grounding to achieve better human-computer interaction, accessibility, and detailed understanding. However, its application to visualizations such as charts remains under-explored due to the inherent complexity of interleaved visual-numerical relationships in chart images. Existing chart understanding methods primarily focus on answering questions without explicitly identifying the visual elements that support their predictions. To bridge this gap, we introduce RefChartQA, a novel benchmark that integrates Chart Question Answering (ChartQA) with visual grounding, enabling models to refer elements at multiple granularities within chart images. Furthermore, we conduct a comprehensive evaluation by instruction-tuning 5 state-of-the-art VLMs across different categories. Our experiments demonstrate that incorporating spatial awareness via grounding improves response accuracy by over 15%, reducing hallucinations, and improving model reliability. Additionally, we identify key factors influencing text-spatial alignment, such as architectural improvements in TinyChart, which leverages a token-merging module for enhanced feature fusion. Our dataset is open-sourced for community development and further advancements. All models and code will be publicly available at https://github.com/moured/RefChartQA.
We propose a novel approach for generating text-guided human-object interactions (HOIs) that achieves explicit joint-level interaction modeling in a computationally efficient manner. Previous methods represent the entire human body as a single token, making it difficult to capture fine-grained joint-level interactions and resulting in unrealistic HOIs. However, treating each individual joint as a token would yield over twenty times more tokens, increasing computational overhead. To address these challenges, we introduce an Efficient Explicit Joint-level Interaction Model (EJIM). EJIM features a Dual-branch HOI Mamba that separately and efficiently models spatiotemporal HOI information, as well as a Dual-branch Condition Injector for integrating text semantics and object geometry into human and object motions. Furthermore, we design a Dynamic Interaction Block and a progressive masking mechanism to iteratively filter out irrelevant joints, ensuring accurate and nuanced interaction modeling. Extensive quantitative and qualitative evaluations on public datasets demonstrate that EJIM surpasses previous works by a large margin while using only 5\% of the inference time. Code is available \href{https://github.com/Huanggh531/EJIM}{here}.
Reliable high-definition (HD) map construction is crucial for the driving safety of autonomous vehicles. Although recent studies demonstrate improved performance, their generalization capability across unfamiliar driving scenes remains unexplored. To tackle this issue, we propose UIGenMap, an uncertainty-instructed structure injection approach for generalizable HD map vectorization, which concerns the uncertainty resampling in statistical distribution and employs explicit instance features to reduce excessive reliance on training data. Specifically, we introduce the perspective-view (PV) detection branch to obtain explicit structural features, in which the uncertainty-aware decoder is designed to dynamically sample probability distributions considering the difference in scenes. With probabilistic embedding and selection, UI2DPrompt is proposed to construct PV-learnable prompts. These PV prompts are integrated into the map decoder by designed hybrid injection to compensate for neglected instance structures. To ensure real-time inference, a lightweight Mimic Query Distillation is designed to learn from PV prompts, which can serve as an efficient alternative to the flow of PV branches. Extensive experiments on challenging geographically disjoint (geo-based) data splits demonstrate that our UIGenMap achieves superior performance, with +5.7 mAP improvement on the nuScenes dataset. Source code will be available at https://github.com/xiaolul2/UIGenMap.
Coral reef ecosystems provide essential ecosystem services, but face significant threats from climate change and human activities. Although advances in deep learning have enabled automatic classification of coral reef conditions, conventional deep models struggle to achieve high performance when processing complex underwater ecological images. Vision foundation models, known for their high accuracy and cross-domain generalizability, offer promising solutions. However, fine-tuning these models requires substantial computational resources and results in high carbon emissions. To address these challenges, adapter learning methods such as Low-Rank Adaptation (LoRA) have emerged as a solution. This study introduces an approach integrating the DINOv2 vision foundation model with the LoRA fine-tuning method. The approach leverages multi-temporal field images collected through underwater surveys at 15 dive sites at Koh Tao, Thailand, with all images labeled according to universal standards used in citizen science-based conservation programs. The experimental results demonstrate that the DINOv2-LoRA model achieved superior accuracy, with a match ratio of 64.77%, compared to 60.34% achieved by the best conventional model. Furthermore, incorporating LoRA reduced the trainable parameters from 1,100M to 5.91M. Transfer learning experiments conducted under different temporal and spatial settings highlight the exceptional generalizability of DINOv2-LoRA across different seasons and sites. This study is the first to explore the efficient adaptation of foundation models for multi-label classification of coral reef conditions under multi-temporal and multi-spatial settings. The proposed method advances the classification of coral reef conditions and provides a tool for monitoring, conserving, and managing coral reef ecosystems.
Biofouling$\unicode{x2013}$communities of organisms that grow on hard surfaces immersed in water$\unicode{x2013}$provides a pathway for the spread of invasive marine species and diseases. To address this risk, international vessels are increasingly being obligated to provide evidence of their biofouling management practices. Verification that these activities are effective requires underwater inspections, using divers or underwater remotely operated vehicles (ROVs), and the collection and analysis of large amounts of imagery and footage. Automated assessment using computer vision techniques can significantly streamline this process, and this work shows how this challenge can be addressed efficiently and effectively using the interpretable Component Features (ComFe) approach with a DINOv2 Vision Transformer (ViT) foundation model. ComFe is able to obtain improved performance in comparison to previous non-interpretable Convolutional Neural Network (CNN) methods, with significantly fewer weights and greater transparency$\unicode{x2013}$through identifying which regions of the image contribute to the classification, and which images in the training data lead to that conclusion. All code, data and model weights are publicly released.
Recent advances in DUSt3R have enabled robust estimation of dense point clouds and camera parameters of static scenes, leveraging Transformer network architectures and direct supervision on large-scale 3D datasets. In contrast, the limited scale and diversity of available 4D datasets present a major bottleneck for training a highly generalizable 4D model. This constraint has driven conventional 4D methods to fine-tune 3D models on scalable dynamic video data with additional geometric priors such as optical flow and depths. In this work, we take an opposite path and introduce Easi3R, a simple yet efficient training-free method for 4D reconstruction. Our approach applies attention adaptation during inference, eliminating the need for from-scratch pre-training or network fine-tuning. We find that the attention layers in DUSt3R inherently encode rich information about camera and object motion. By carefully disentangling these attention maps, we achieve accurate dynamic region segmentation, camera pose estimation, and 4D dense point map reconstruction. Extensive experiments on real-world dynamic videos demonstrate that our lightweight attention adaptation significantly outperforms previous state-of-the-art methods that are trained or finetuned on extensive dynamic datasets. Our code is publicly available for research purpose at https://easi3r.github.io/
Despite the significant progress in diffusion prior-based image restoration, most existing methods apply uniform processing to the entire image, lacking the capability to perform region-customized image restoration according to user instructions. In this work, we propose a new framework, namely InstructRestore, to perform region-adjustable image restoration following human instructions. To achieve this, we first develop a data generation engine to produce training triplets, each consisting of a high-quality image, the target region description, and the corresponding region mask. With this engine and careful data screening, we construct a comprehensive dataset comprising 536,945 triplets to support the training and evaluation of this task. We then examine how to integrate the low-quality image features under the ControlNet architecture to adjust the degree of image details enhancement. Consequently, we develop a ControlNet-like model to identify the target region and allocate different integration scales to the target and surrounding regions, enabling region-customized image restoration that aligns with user instructions. Experimental results demonstrate that our proposed InstructRestore approach enables effective human-instructed image restoration, such as images with bokeh effects and user-instructed local enhancement. Our work advances the investigation of interactive image restoration and enhancement techniques. Data, code, and models will be found at https://github.com/shuaizhengliu/InstructRestore.git.
World foundation models, which simulate the physical world by predicting future states from current observations and inputs, have become central to many applications in physical intelligence, including autonomous driving and robotics. However, these models require substantial computational resources for pretraining and are further constrained by available data during post-training. As such, scaling computation at test time emerges as both a critical and practical alternative to traditional model enlargement or re-training. In this work, we introduce SWIFT, a test-time scaling framework tailored for WFMs. SWIFT integrates our extensible WFM evaluation toolkit with process-level inference strategies, including fast tokenization, probability-based Top-K pruning, and efficient beam search. Empirical results on the COSMOS model demonstrate that test-time scaling exists even in a compute-optimal way. Our findings reveal that test-time scaling laws hold for WFMs and that SWIFT provides a scalable and effective pathway for improving WFM inference without retraining or increasing model size. The code is available at https://github.com/Mia-Cong/SWIFT.git.
Understanding tissue motion in surgery is crucial to enable applications in downstream tasks such as segmentation, 3D reconstruction, virtual tissue landmarking, autonomous probe-based scanning, and subtask autonomy. Labeled data are essential to enabling algorithms in these downstream tasks since they allow us to quantify and train algorithms. This paper introduces a point tracking challenge to address this, wherein participants can submit their algorithms for quantification. The submitted algorithms are evaluated using a dataset named surgical tattoos in infrared (STIR), with the challenge aptly named the STIR Challenge 2024. The STIR Challenge 2024 comprises two quantitative components: accuracy and efficiency. The accuracy component tests the accuracy of algorithms on in vivo and ex vivo sequences. The efficiency component tests the latency of algorithm inference. The challenge was conducted as a part of MICCAI EndoVis 2024. In this challenge, we had 8 total teams, with 4 teams submitting before and 4 submitting after challenge day. This paper details the STIR Challenge 2024, which serves to move the field towards more accurate and efficient algorithms for spatial understanding in surgery. In this paper we summarize the design, submissions, and results from the challenge. The challenge dataset is available here: https://zenodo.org/records/14803158 , and the code for baseline models and metric calculation is available here: https://github.com/athaddius/STIRMetrics
Seismic processing plays a crucial role in transforming raw data into high-quality subsurface images, pivotal for various geoscience applications. Despite its importance, traditional seismic processing techniques face challenges such as noisy and damaged data and the reliance on manual, time-consuming workflows. The emergence of deep learning approaches has introduced effective and user-friendly alternatives, yet many of these deep learning approaches rely on synthetic datasets and specialized neural networks. Recently, foundation models have gained traction in the seismic domain, due to their success in the natural image domain. Therefore, we investigate the application of natural image foundation models on the three seismic processing tasks: demultiple, interpolation, and denoising. We evaluate the impact of different model characteristics, such as pre-training technique and neural network architecture, on performance and efficiency. Rather than proposing a single seismic foundation model, we critically examine various natural image foundation models and suggest some promising candidates for future exploration.
In colonoscopy, 80% of the missed polyps could be detected with the help of Deep Learning models. In the search for algorithms capable of addressing this challenge, foundation models emerge as promising candidates. Their zero-shot or few-shot learning capabilities, facilitate generalization to new data or tasks without extensive fine-tuning. A concept that is particularly advantageous in the medical imaging domain, where large annotated datasets for traditional training are scarce. In this context, a comprehensive evaluation of foundation models for polyp segmentation was conducted, assessing both detection and delimitation. For the study, three different colonoscopy datasets have been employed to compare the performance of five different foundation models, DINOv2, YOLO-World, GroundingDINO, SAM and MedSAM, against two benchmark networks, YOLOv8 and Mask R-CNN. Results show that the success of foundation models in polyp characterization is highly dependent on domain specialization. For optimal performance in medical applications, domain-specific models are essential, and generic models require fine-tuning to achieve effective results. Through this specialization, foundation models demonstrated superior performance compared to state-of-the-art detection and segmentation models, with some models even excelling in zero-shot evaluation; outperforming fine-tuned models on unseen data.
Weakly supervised object localization (WSOL) methods allow training models to classify images and localize ROIs. WSOL only requires low-cost image-class annotations yet provides a visually interpretable classifier, which is important in histology image analysis. Standard WSOL methods rely on class activation mapping (CAM) methods to produce spatial localization maps according to a single- or two-step strategy. While both strategies have made significant progress, they still face several limitations with histology images. Single-step methods can easily result in under- or over-activation due to the limited visual ROI saliency in histology images and the limited localization cues. They also face the well-known issue of asynchronous convergence between classification and localization tasks. The two-step approach is sub-optimal because it is tied to a frozen classifier, limiting the capacity for localization. Moreover, these methods also struggle when applied to out-of-distribution (OOD) datasets. In this paper, a multi-task approach for WSOL is introduced for simultaneous training of both tasks to address the asynchronous convergence problem. In particular, localization is performed in the pixel-feature space of an image encoder that is shared with classification. This allows learning discriminant features and accurate delineation of foreground/background regions to support ROI localization and image classification. We propose PixelCAM, a cost-effective foreground/background pixel-wise classifier in the pixel-feature space that allows for spatial object localization. PixelCAM is trained using pixel pseudo-labels collected from a pretrained WSOL model. Both image and pixel-wise classifiers are trained simultaneously using standard gradient descent. In addition, our pixel classifier can easily be integrated into CNN- and transformer-based architectures without any modifications.
The platonic representation hypothesis suggests that vision and language embeddings become more homogeneous as model and dataset sizes increase. In particular, pairwise distances within each modality become more similar. This suggests that as foundation models mature, it may become possible to match vision and language embeddings in a fully unsupervised fashion, i.e. without parallel data. We present the first feasibility study, and investigate conformity of existing vision and language foundation models in the context of unsupervised, or "blind", matching. First, we formulate unsupervised matching as a quadratic assignment problem and introduce a novel heuristic that outperforms previous solvers. We also develop a technique to find optimal matching problems, for which a non-trivial match is very likely. Second, we conduct an extensive study deploying a range of vision and language models on four datasets. Our analysis reveals that for many problem instances, vision and language representations can be indeed matched without supervision. This finding opens up the exciting possibility of embedding semantic knowledge into other modalities virtually annotation-free. As a proof of concept, we showcase an unsupervised classifier, which achieves non-trivial classification accuracy without any image-text annotation.