PyTorchKR Papers

최신 논문

총 588편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2407.10964공식 코드 · Papers with Code

No Train, all Gain: Self-Supervised Gradients Improve Deep Frozen Representations

This paper introduces FUNGI, Features from UNsupervised GradIents, a method to enhance the features of transformer encoders by leveraging self-supervised gradients. Our method is simple: given any pretrained model, we first compute gradients from various self-supervised objectives for each input. These gradients are projected to a lower dimension and then concatenated with the model's output embedding. The resulting features are evaluated on k-nearest neighbor classification over 11 datasets from vision, 5 from natural language processing, and 2 from audio. Across backbones spanning various sizes and pretraining strategies, FUNGI features provide consistent performance improvements over the embeddings. We also show that using FUNGI features can benefit linear classification, clustering and image retrieval, and that they significantly improve the retrieval-based in-context scene understanding abilities of pretrained models, for example improving upon DINO by +17% for semantic segmentation - without any training.

arXiv:2407.10200공식 코드 · Papers with Code

Shape2Scene: 3D Scene Representation Learning Through Pre-training on Shape Data

Current 3D self-supervised learning methods of 3D scenes face a data desert issue, resulting from the time-consuming and expensive collecting process of 3D scene data. Conversely, 3D shape datasets are easier to collect. Despite this, existing pre-training strategies on shape data offer limited potential for 3D scene understanding due to significant disparities in point quantities. To tackle these challenges, we propose Shape2Scene (S2S), a novel method that learns representations of large-scale 3D scenes from 3D shape data. We first design multiscale and high-resolution backbones for shape and scene level 3D tasks, i.e., MH-P (point-based) and MH-V (voxel-based). MH-P/V establishes direct paths to highresolution features that capture deep semantic information across multiple scales. This pivotal nature makes them suitable for a wide range of 3D downstream tasks that tightly rely on high-resolution features. We then employ a Shape-to-Scene strategy (S2SS) to amalgamate points from various shapes, creating a random pseudo scene (comprising multiple objects) for training data, mitigating disparities between shapes and scenes. Finally, a point-point contrastive loss (PPC) is applied for the pre-training of MH-P/V. In PPC, the inherent correspondence (i.e., point pairs) is naturally obtained in S2SS. Extensive experiments have demonstrated the transferability of 3D representations learned by MH-P/V across shape-level and scene-level 3D tasks. MH-P achieves notable performance on well-known point cloud datasets (93.8% OA on ScanObjectNN and 87.6% instance mIoU on ShapeNetPart). MH-V also achieves promising performance in 3D semantic segmentation and 3D object detection.

arXiv:2407.07541공식 코드 · Papers with Code

Swiss DINO: Efficient and Versatile Vision Framework for On-device Personal Object Search

In this paper, we address a recent trend in robotic home appliances to include vision systems on personal devices, capable of personalizing the appliances on the fly. In particular, we formulate and address an important technical task of personal object search, which involves localization and identification of personal items of interest on images captured by robotic appliances, with each item referenced only by a few annotated images. The task is crucial for robotic home appliances and mobile systems, which need to process personal visual scenes or to operate with particular personal objects (e.g., for grasping or navigation). In practice, personal object search presents two main technical challenges. First, a robot vision system needs to be able to distinguish between many fine-grained classes, in the presence of occlusions and clutter. Second, the strict resource requirements for the on-device system restrict the usage of most state-of-the-art methods for few-shot learning and often prevent on-device adaptation. In this work, we propose Swiss DINO: a simple yet effective framework for one-shot personal object search based on the recent DINOv2 transformer model, which was shown to have strong zero-shot generalization properties. Swiss DINO handles challenging on-device personalized scene understanding requirements and does not require any adaptation training. We show significant improvement (up to 55%) in segmentation and recognition accuracy compared to the common lightweight solutions, and significant footprint reduction of backbone inference time (up to 100x) and GPU consumption (up to 10x) compared to the heavy transformer-based solutions.

arXiv:2407.03263공식 코드 · Papers with Code

A Unified Framework for 3D Scene Understanding

We propose UniSeg3D, a unified 3D scene understanding framework that achieves panoptic, semantic, instance, interactive, referring, and open-vocabulary segmentation tasks within a single model. Most previous 3D segmentation approaches are typically tailored to a specific task, limiting their understanding of 3D scenes to a task-specific perspective. In contrast, the proposed method unifies six tasks into unified representations processed by the same Transformer. It facilitates inter-task knowledge sharing, thereby promoting comprehensive 3D scene understanding. To take advantage of multi-task unification, we enhance performance by establishing explicit inter-task associations. Specifically, we design knowledge distillation and contrastive learning methods to transfer task-specific knowledge across different tasks. Experiments on three benchmarks, including ScanNet20, ScanRefer, and ScanNet200, demonstrate that the UniSeg3D consistently outperforms current SOTA methods, even those specialized for individual tasks. We hope UniSeg3D can serve as a solid unified baseline and inspire future work. Code and models are available at https://github.com/dk-liang/UniSeg3D.

arXiv:2407.02228공식 코드 · Papers with Code

MTMamba: Enhancing Multi-Task Dense Scene Understanding by Mamba-Based Decoders

Multi-task dense scene understanding, which learns a model for multiple dense prediction tasks, has a wide range of application scenarios. Modeling long-range dependency and enhancing cross-task interactions are crucial to multi-task dense prediction. In this paper, we propose MTMamba, a novel Mamba-based architecture for multi-task scene understanding. It contains two types of core blocks: self-task Mamba (STM) block and cross-task Mamba (CTM) block. STM handles long-range dependency by leveraging Mamba, while CTM explicitly models task interactions to facilitate information exchange across tasks. Experiments on NYUDv2 and PASCAL-Context datasets demonstrate the superior performance of MTMamba over Transformer-based and CNN-based methods. Notably, on the PASCAL-Context dataset, MTMamba achieves improvements of +2.08, +5.01, and +4.90 over the previous best methods in the tasks of semantic segmentation, human parsing, and object boundary detection, respectively. The code is available at https://github.com/EnVision-Research/MTMamba.

arXiv:2407.01328공식 코드 · Papers with Code

CSFNet: A Cosine Similarity Fusion Network for Real-Time RGB-X Semantic Segmentation of Driving Scenes

Semantic segmentation, as a crucial component of complex visual interpretation, plays a fundamental role in autonomous vehicle vision systems. Recent studies have significantly improved the accuracy of semantic segmentation by exploiting complementary information and developing multimodal methods. Despite the gains in accuracy, multimodal semantic segmentation methods suffer from high computational complexity and low inference speed. Therefore, it is a challenging task to implement multimodal methods in driving applications. To address this problem, we propose the Cosine Similarity Fusion Network (CSFNet) as a real-time RGB-X semantic segmentation model. Specifically, we design a Cosine Similarity Attention Fusion Module (CS-AFM) that effectively rectifies and fuses features of two modalities. The CS-AFM module leverages cross-modal similarity to achieve high generalization ability. By enhancing the fusion of cross-modal features at lower levels, CS-AFM paves the way for the use of a single-branch network at higher levels. Therefore, we use dual and single-branch architectures in an encoder, along with an efficient context module and a lightweight decoder for fast and accurate predictions. To verify the effectiveness of CSFNet, we use the Cityscapes, MFNet, and ZJU datasets for the RGB-D/T/P semantic segmentation. According to the results, CSFNet has competitive accuracy with state-of-the-art methods while being state-of-the-art in terms of speed among multimodal semantic segmentation models. It also achieves high efficiency due to its low parameter count and computational complexity. The source code for CSFNet will be available at https://github.com/Danial-Qashqai/CSFNet.

arXiv:2406.16020공식 코드 · Papers with Code

AudioBench: A Universal Benchmark for Audio Large Language Models

We introduce AudioBench, a universal benchmark designed to evaluate Audio Large Language Models (AudioLLMs). It encompasses 8 distinct tasks and 26 datasets, among which, 7 are newly proposed datasets. The evaluation targets three main aspects: speech understanding, audio scene understanding, and voice understanding (paralinguistic). Despite recent advancements, there lacks a comprehensive benchmark for AudioLLMs on instruction following capabilities conditioned on audio signals. AudioBench addresses this gap by setting up datasets as well as desired evaluation metrics. Besides, we also evaluated the capabilities of five popular models and found that no single model excels consistently across all tasks. We outline the research outlook for AudioLLMs and anticipate that our open-sourced evaluation toolkit, data, and leaderboard will offer a robust testbed for future model developments.

arXiv:2406.09792공식 코드 · Papers with Code

A Two-Stage Masked Autoencoder Based Network for Indoor Depth Completion

Depth images have a wide range of applications, such as 3D reconstruction, autonomous driving, augmented reality, robot navigation, and scene understanding. Commodity-grade depth cameras are hard to sense depth for bright, glossy, transparent, and distant surfaces. Although existing depth completion methods have achieved remarkable progress, their performance is limited when applied to complex indoor scenarios. To address these problems, we propose a two-step Transformer-based network for indoor depth completion. Unlike existing depth completion approaches, we adopt a self-supervision pre-training encoder based on the masked autoencoder to learn an effective latent representation for the missing depth value; then we propose a decoder based on a token fusion mechanism to complete (i.e., reconstruct) the full depth from the jointly RGB and incomplete depth image. Compared to the existing methods, our proposed network, achieves the state-of-the-art performance on the Matterport3D dataset. In addition, to validate the importance of the depth completion task, we apply our methods to indoor 3D reconstruction. The code, dataset, and demo are available at https://github.com/kailaisun/Indoor-Depth-Completion.

arXiv:2406.09411공식 코드 · Papers with Code

MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding

We introduce MuirBench, a comprehensive benchmark that focuses on robust multi-image understanding capabilities of multimodal LLMs. MuirBench consists of 12 diverse multi-image tasks (e.g., scene understanding, ordering) that involve 10 categories of multi-image relations (e.g., multiview, temporal relations). Comprising 11,264 images and 2,600 multiple-choice questions, MuirBench is created in a pairwise manner, where each standard instance is paired with an unanswerable variant that has minimal semantic differences, in order for a reliable assessment. Evaluated upon 20 recent multi-modal LLMs, our results reveal that even the best-performing models like GPT-4o and Gemini Pro find it challenging to solve MuirBench, achieving 68.0% and 49.3% in accuracy. Open-source multimodal LLMs trained on single images can hardly generalize to multi-image questions, hovering below 33.3% in accuracy. These results highlight the importance of MuirBench in encouraging the community to develop multimodal LLMs that can look beyond a single image, suggesting potential pathways for future improvements.

arXiv:2406.08176공식 코드 · Papers with Code

Category-level Neural Field for Reconstruction of Partially Observed Objects in Indoor Environment

Neural implicit representation has attracted attention in 3D reconstruction through various success cases. For further applications such as scene understanding or editing, several works have shown progress towards object compositional reconstruction. Despite their superior performance in observed regions, their performance is still limited in reconstructing objects that are partially observed. To better treat this problem, we introduce category-level neural fields that learn meaningful common 3D information among objects belonging to the same category present in the scene. Our key idea is to subcategorize objects based on their observed shape for better training of the category-level model. Then we take advantage of the neural field to conduct the challenging task of registering partially observed objects by selecting and aligning against representative objects selected by ray-based uncertainty. Experiments on both simulation and real-world datasets demonstrate that our method improves the reconstruction of unobserved parts for several categories.

arXiv:2406.07089공식 코드 · Papers with Code

RS-Agent: Automating Remote Sensing Tasks through Intelligent Agent

The unprecedented advancements in Multimodal Large Language Models (MLLMs) have demonstrated strong potential in interacting with humans through both language and visual inputs to perform downstream tasks such as visual question answering and scene understanding. However, these models are constrained to basic instruction-following or descriptive tasks, facing challenges in complex real-world remote sensing applications that require specialized tools and knowledge. To address these limitations, we propose RS-Agent, an AI agent designed to interact with human users and autonomously leverage specialized models to address the demands of real-world remote sensing applications. RS-Agent integrates four key components: a Central Controller based on large language models, a dynamic toolkit for tool execution, a Solution Space for task-specific expert guidance, and a Knowledge Space for domain-level reasoning, enabling it to interpret user queries and orchestrate tools for accurate remote sensing task. We introduce two novel mechanisms: Task-Aware Retrieval, which improves tool selection accuracy through expert-guided planning, and DualRAG, a retrieval-augmented generation method that enhances knowledge relevance through weighted, dual-path retrieval. RS-Agent supports flexible integration of new tools and is compatible with both open-source and proprietary LLMs. Extensive experiments across 9 datasets and 18 remote sensing tasks demonstrate that RS-Agent significantly outperforms state-of-the-art MLLMs, achieving over 95% task planning accuracy and delivering superior performance in tasks such as scene classification, object counting, and remote sensing visual question answering. Our work presents RS-Agent as a robust and extensible framework for advancing intelligent automation in remote sensing analysis.

arXiv:2405.14731공식 코드 · Papers with Code

CoPeD-Advancing Multi-Robot Collaborative Perception: A Comprehensive Dataset in Real-World Environments

In the past decade, although single-robot perception has made significant advancements, the exploration of multi-robot collaborative perception remains largely unexplored. This involves fusing compressed, intermittent, limited, heterogeneous, and asynchronous environmental information across multiple robots to enhance overall perception, despite challenges like sensor noise, occlusions, and sensor failures. One major hurdle has been the lack of real-world datasets. This paper presents a pioneering and comprehensive real-world multi-robot collaborative perception dataset to boost research in this area. Our dataset leverages the untapped potential of air-ground robot collaboration featuring distinct spatial viewpoints, complementary robot mobilities, coverage ranges, and sensor modalities. It features raw sensor inputs, pose estimation, and optional high-level perception annotation, thus accommodating diverse research interests. Compared to existing datasets predominantly designed for Simultaneous Localization and Mapping (SLAM), our setup ensures a diverse range and adequate overlap of sensor views to facilitate the study of multi-robot collaborative perception algorithms. We demonstrate the value of this dataset qualitatively through multiple collaborative perception tasks. We believe this work will unlock the potential research of high-level scene understanding through multi-modal collaborative perception in multi-robot settings.

arXiv:2405.11985공식 코드 · Papers with Code

MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering

Text-Centric Visual Question Answering (TEC-VQA) in its proper format not only facilitates human-machine interaction in text-centric visual environments but also serves as a de facto gold proxy to evaluate AI models in the domain of text-centric scene understanding. Nonetheless, most existing TEC-VQA benchmarks have focused on high-resource languages like English and Chinese. Despite pioneering works to expand multilingual QA pairs in non-text-centric VQA datasets through translation engines, the translation-based protocol encounters a substantial "visual-textual misalignment" problem when applied to TEC-VQA. Specifically, it prioritizes the text in question-answer pairs while disregarding the visual text present in images. Moreover, it fails to address complexities related to nuanced meaning, contextual distortion, language bias, and question-type diversity. In this work, we tackle multilingual TEC-VQA by introducing MTVQA, the first benchmark featuring high-quality human expert annotations across 9 diverse languages, consisting of 6,778 question-answer pairs across 2,116 images. Further, by comprehensively evaluating numerous state-of-the-art Multimodal Large Language Models~(MLLMs), including Qwen2-VL, GPT-4o, GPT-4V, Claude3, and Gemini, on the MTVQA benchmark, it is evident that there is still a large room for performance improvement (Qwen2-VL scoring 30.9 versus 79.7 for human performance), underscoring the value of MTVQA. Additionally, we supply multilingual training data within the MTVQA dataset, demonstrating that straightforward fine-tuning with this data can substantially enhance multilingual TEC-VQA performance. We aspire that MTVQA will offer the research community fresh insights and stimulate further exploration in multilingual visual text comprehension. The project homepage is available at https://bytedance.github.io/MTVQA/.

arXiv:2405.10370공식 코드 · Papers with Code

Grounded 3D-LLM with Referent Tokens

Prior studies on 3D scene understanding have primarily developed specialized models for specific tasks or required task-specific fine-tuning. In this study, we propose Grounded 3D-LLM, which explores the potential of 3D large multi-modal models (3D LMMs) to consolidate various 3D vision tasks within a unified generative framework. The model uses scene referent tokens as special noun phrases to reference 3D scenes, enabling it to handle sequences that interleave 3D and textual data. Per-task instruction-following templates are employed to ensure natural and diversity in translating 3D vision tasks into language formats. To facilitate the use of referent tokens in subsequent language modeling, we provide a large-scale, automatically curated grounded scene-text dataset with over 1 million phrase-to-region correspondences and introduce Contrastive Language-Scene Pre-training (CLASP) to perform phrase-level scene-text alignment using this data. Our comprehensive evaluation covers open-ended tasks like dense captioning and 3D question answering, alongside close-ended tasks such as object detection and language grounding. Experiments across multiple 3D benchmarks reveal the leading performance and the broad applicability of Grounded 3D-LLM. Code and datasets are available at the https://groundedscenellm.github.io/grounded_3d-llm.github.io.

arXiv:2405.10255공식 코드 · Papers with Code

When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Models

As large language models (LLMs) evolve, their integration with 3D spatial data (3D-LLMs) has seen rapid progress, offering unprecedented capabilities for understanding and interacting with physical spaces. This survey provides a comprehensive overview of the methodologies enabling LLMs to process, understand, and generate 3D data. Highlighting the unique advantages of LLMs, such as in-context learning, step-by-step reasoning, open-vocabulary capabilities, and extensive world knowledge, we underscore their potential to significantly advance spatial comprehension and interaction within embodied Artificial Intelligence (AI) systems. Our investigation spans various 3D data representations, from point clouds to Neural Radiance Fields (NeRFs). It examines their integration with LLMs for tasks such as 3D scene understanding, captioning, question-answering, and dialogue, as well as LLM-based agents for spatial reasoning, planning, and navigation. The paper also includes a brief review of other methods that integrate 3D and language. The meta-analysis presented in this paper reveals significant progress yet underscores the necessity for novel approaches to harness the full potential of 3D-LLMs. Hence, with this paper, we aim to chart a course for future research that explores and expands the capabilities of 3D-LLMs in understanding and interacting with the complex 3D world. To support this survey, we have established a project page where papers related to our topic are organized and listed: https://github.com/ActiveVisionLab/Awesome-LLM-3D.

arXiv:2405.10305공식 코드 · Papers with Code

4D Panoptic Scene Graph Generation

We are living in a three-dimensional space while moving forward through a fourth dimension: time. To allow artificial intelligence to develop a comprehensive understanding of such a 4D environment, we introduce 4D Panoptic Scene Graph (PSG-4D), a new representation that bridges the raw visual data perceived in a dynamic 4D world and high-level visual understanding. Specifically, PSG-4D abstracts rich 4D sensory data into nodes, which represent entities with precise location and status information, and edges, which capture the temporal relations. To facilitate research in this new area, we build a richly annotated PSG-4D dataset consisting of 3K RGB-D videos with a total of 1M frames, each of which is labeled with 4D panoptic segmentation masks as well as fine-grained, dynamic scene graphs. To solve PSG-4D, we propose PSG4DFormer, a Transformer-based model that can predict panoptic segmentation masks, track masks along the time axis, and generate the corresponding scene graphs via a relation component. Extensive experiments on the new dataset show that our method can serve as a strong baseline for future research on PSG-4D. In the end, we provide a real-world application example to demonstrate how we can achieve dynamic scene understanding by integrating a large language model into our PSG-4D system.

arXiv:2405.05518공식 코드 · Papers with Code

DTCLMapper: Dual Temporal Consistent Learning for Vectorized HD Map Construction

Temporal information plays a pivotal role in Bird's-Eye-View (BEV) driving scene understanding, which can alleviate the visual information sparsity. However, the indiscriminate temporal fusion method will cause the barrier of feature redundancy when constructing vectorized High-Definition (HD) maps. In this paper, we revisit the temporal fusion of vectorized HD maps, focusing on temporal instance consistency and temporal map consistency learning. To improve the representation of instances in single-frame maps, we introduce a novel method, DTCLMapper. This approach uses a dual-stream temporal consistency learning module that combines instance embedding with geometry maps. In the instance embedding component, our approach integrates temporal Instance Consistency Learning (ICL), ensuring consistency from vector points and instance features aggregated from points. A vectorized points pre-selection module is employed to enhance the regression efficiency of vector points from each instance. Then aggregated instance features obtained from the vectorized points preselection module are grounded in contrastive learning to realize temporal consistency, where positive and negative samples are selected based on position and semantic information. The geometry mapping component introduces Map Consistency Learning (MCL) designed with self-supervised learning. The MCL enhances the generalization capability of our consistent learning approach by concentrating on the global location and distribution constraints of the instances. Extensive experiments on well-recognized benchmarks indicate that the proposed DTCLMapper achieves state-of-the-art performance in vectorized mapping tasks, reaching 61.9% and 65.1% mAP scores on the nuScenes and Argoverse datasets, respectively. The source code is available at https://github.com/lynn-yu/DTCLMapper.

arXiv:2405.05852공식 코드 · Papers with Code

Pre-trained Text-to-Image Diffusion Models Are Versatile Representation Learners for Control

Embodied AI agents require a fine-grained understanding of the physical world mediated through visual and language inputs. Such capabilities are difficult to learn solely from task-specific data. This has led to the emergence of pre-trained vision-language models as a tool for transferring representations learned from internet-scale data to downstream tasks and new domains. However, commonly used contrastively trained representations such as in CLIP have been shown to fail at enabling embodied agents to gain a sufficiently fine-grained scene understanding -- a capability vital for control. To address this shortcoming, we consider representations from pre-trained text-to-image diffusion models, which are explicitly optimized to generate images from text prompts and as such, contain text-conditioned representations that reflect highly fine-grained visuo-spatial information. Using pre-trained text-to-image diffusion models, we construct Stable Control Representations which allow learning downstream control policies that generalize to complex, open-ended environments. We show that policies learned using Stable Control Representations are competitive with state-of-the-art representation learning approaches across a broad range of simulated control settings, encompassing challenging manipulation and navigation tasks. Most notably, we show that Stable Control Representations enable learning policies that exhibit state-of-the-art performance on OVMM, a difficult open-vocabulary navigation benchmark.

arXiv:2405.05259공식 코드 · Papers with Code

OpenESS: Event-based Semantic Scene Understanding with Open Vocabularies

Event-based semantic segmentation (ESS) is a fundamental yet challenging task for event camera sensing. The difficulties in interpreting and annotating event data limit its scalability. While domain adaptation from images to event data can help to mitigate this issue, there exist data representational differences that require additional effort to resolve. In this work, for the first time, we synergize information from image, text, and event-data domains and introduce OpenESS to enable scalable ESS in an open-world, annotation-efficient manner. We achieve this goal by transferring the semantically rich CLIP knowledge from image-text pairs to event streams. To pursue better cross-modality adaptation, we propose a frame-to-event contrastive distillation and a text-to-event semantic consistency regularization. Experimental results on popular ESS benchmarks showed our approach outperforms existing methods. Notably, we achieve 53.93% and 43.31% mIoU on DDD17 and DSEC-Semantic without using either event or frame labels.

arXiv:2405.05258공식 코드 · Papers with Code

Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Driving

Efficient data utilization is crucial for advancing 3D scene understanding in autonomous driving, where reliance on heavily human-annotated LiDAR point clouds challenges fully supervised methods. Addressing this, our study extends into semi-supervised learning for LiDAR semantic segmentation, leveraging the intrinsic spatial priors of driving scenes and multi-sensor complements to augment the efficacy of unlabeled datasets. We introduce LaserMix++, an evolved framework that integrates laser beam manipulations from disparate LiDAR scans and incorporates LiDAR-camera correspondences to further assist data-efficient learning. Our framework is tailored to enhance 3D scene consistency regularization by incorporating multi-modality, including 1) multi-modal LaserMix operation for fine-grained cross-sensor interactions; 2) camera-to-LiDAR feature distillation that enhances LiDAR feature learning; and 3) language-driven knowledge guidance generating auxiliary supervisions using open-vocabulary models. The versatility of LaserMix++ enables applications across LiDAR representations, establishing it as a universally applicable solution. Our framework is rigorously validated through theoretical analysis and extensive experiments on popular driving perception datasets. Results demonstrate that LaserMix++ markedly outperforms fully supervised alternatives, achieving comparable accuracy with five times fewer annotations and significantly improving the supervised-only baselines. This substantial advancement underscores the potential of semi-supervised approaches in reducing the reliance on extensive labeled data in LiDAR-based 3D scene understanding systems.