ECCV 2024 论文列表

"Vision transformers (ViTs) have emerged as a promising alternative to convolutional neural networks (CNNs) for various image analysis tasks, offering comparable or superior performance. However, one significant drawback of ViTs is their resource-intensive nature, leading to increased memory footprint, computation complexity, and power consumption. To democratize this high-performance technology and make it more environmentally friendly, it is essential to compress ViT models, reducing their resource requirements while maintaining high performance. In this paper, we introduce a new block-structured pruning to address the resource-intensive issue for ViTs, offering a balanced trade-off between accuracy and hardware acceleration. Unlike unstructured pruning or channel-wise structured pruning, block pruning leverages the block-wise structure of linear layers, resulting in more efficient matrix multiplications. To optimize this pruning scheme, our paper proposes a novel hardware-aware learning objective that simultaneously maximizes speedup and minimizes power consumption during inference, tailored to the block sparsity structure. This objective eliminates the need for empirical look-up tables and focuses solely on reducing parametrized layer connections. Moreover, our paper provides a lightweight algorithm to achieve post-training pruning for ViTs, utilizing second-order Taylor approximation and empirical optimization to solve the proposed hardware-aware objective. Extensive experiments on ImageNet are conducted across various ViT architectures, including DeiT-B and DeiT-S, demonstrating competitive performance with other pruning methods and achieving a remarkable balance between accuracy preservation and power savings. Especially, we achieve up to 3.93× and 1.79× speedups on dedicated hardware and GPUs respectively for DeiT-B, and also observe an inference power reduction by 1.4× on real-world GPUs. Code will be released soon."

"Learning with noisy labels (LNL) aims to train a high-performing model using a noisy dataset. We observe that noise for a given class often comes from a limited set of categories, yet many LNL methods overlook this. For example, an image mislabeled as a cheetah is more likely a leopard than a hippopotamus due to its visual similarity. Thus, we explore Learning with Noisy Labels with noise source Knowledge integration (LNL+K), which leverages knowledge about likely source(s) of label noise that is often provided in a dataset’s meta-data. Integrating noise source knowledge boosts performance even in settings where LNL methods typically fail. For example, LNL+K methods are effective on datasets where noise represents the majority of samples, which breaks a critical premise of most methods developed for LNL. Our LNL+K methods can boost performance even when noise sources are estimated rather than extracted from meta-data. We provide several baseline LNL+K methods that integrate noise source knowledge into state-of-the-art LNL models that are evaluated across six diverse datasets and two types of noise, where we report gains of up to 23% compared to the unadapted methods. Critically, we show that LNL methods fail to generalize on some real-world datasets, even when adapted to integrate noise source knowledge, highlighting the importance of directly exploring LNL+K1 . 1 Code available: https://github.com/SunnySiqi/LNL_K"

"The field of neural rendering has witnessed significant progress with advancements in generative models and differentiable rendering techniques. Though 2D diffusion has achieved success, a unified 3D diffusion pipeline remains unsettled. This paper introduces a novel framework called to address this gap and enable fast, high-quality, and generic conditional 3D generation. Our approach harnesses a 3D-aware architecture and variational autoencoder (VAE) to encode the input image(s) into a structured, compact, and 3D latent space. The latent is decoded by a transformer-based decoder into a high-capacity 3D neural field. Through training a diffusion model on this 3D-aware latent space, our method achieves superior performance on Objaverse, ShapeNet and FFHQ for conditional 3D generation. Moreover, it surpasses existing 3D diffusion methods in terms of inference speed, requiring no per-instance optimization. Video demos can be found on our project webpage: https://nirvanalan.github.io/projects/ ln3diff."

"While recent low-light image enhancement (LLIE) methods have made significant advancements, they still face challenges in terms of low visual quality and weak generalization ability when applied to complex scenarios. To address these issues, we propose a semi-supervised method based on latent mean-teacher and Gaussian process, named LMT-GP. We first design a latent mean-teacher framework that integrates both labeled and unlabeled data, as well as their latent vectors, into model training. Meanwhile, we use a mean-teacher-assisted Gaussian process learning strategy to establish a connection between the latent and pseudo-latent vectors obtained from the labeled and unlabeled data. To guide the learning process, we utilize an assisted Gaussian process regression (GPR) loss function. Furthermore, we design a pseudo-label adaptation module (PAM) to ensure the reliability of the network learning. To demonstrate our method’s generalization ability and effectiveness, we apply it to multiple LLIE datasets and high-level vision tasks. Experiment results demonstrate that our method achieves high generalization performance and image quality. The code is available at https://github.com/HFUT-CV/LMT-GP"

"Visual encoding constitutes the basis of large multimodal models (LMMs) in understanding the visual world. Conventional LMMs process images in fixed sizes and limited resolutions, while recent explorations in this direction are limited in adaptivity, efficiency, and even correctness. In this work, we first take GPT-4V and LLaVA 1.5 as representative examples and expose systematic flaws rooted in their visual encoding strategy. To address the challenges, we present LLaVA-UHD, a large multimodal model that can efficiently perceive images in any aspect ratio and high resolution. LLaVA-UHD includes three key components: (1) An image modularization strategy that divides native-resolution images into smaller variable-sized slices for efficient and extensible encoding, (2) a compression module that further condenses image tokens from visual encoders, and (3) a spatial schema to organize slice tokens for LLMs. Comprehensive experiments show that LLaVA-UHD outperforms established LMMs trained with 2-3 orders of magnitude more data on black8 benchmarks. Notably, our model built on LLaVA-1.5 336×336 supports 6 times larger (i.e., 672×1008) resolution images, and achieves 5.7 accuracy improvement on TextVQA."

"This paper presents (), a general-purpose multimodal assistant trained using an end-to-end approach that systematically expands the capabilities of large multimodal models (LMMs). maintains a skill repository that contains a wide range of vision and vision-language pre-trained models (tools), and is able to activate relevant tools, given users’ multimodal inputs, to compose their execution results on the fly to fulfill many real-world tasks. To acquire the ability of using tools, is trained on multimodal instruction-following data that we have curated. The training data covers many tool use examples of visual understanding, generation, external knowledge retrieval and their compositions. Empirical results show that outperforms LLaVA in existing capabilities, and exhibits many new capabilities. Compared with tool-augmented LLMs, is distinct in that the image query is directly grounded in and actively engaged throughout the entire human-AI interaction sessions, significantly improving tool use performance and enabling new scenarios."

"With the recent significant advancements in large multimodal models (LMMs), the importance of their grounding capability in visual chat is increasingly recognized. Despite recent efforts to enable LMMs to support grounding, their capabilities for grounding and chat are usually separate, and their chat performance drops dramatically when asked to ground. The problem is the lack of a dataset for grounded visual chat (GVC). Existing grounding datasets only contain short captions. To address this issue, we have created GVC data that allows for the combination of grounding and chat capabilities. To better evaluate the GVC capabilities, we have introduced a benchmark called . Additionally, we have proposed a model design that can support GVC and various types of visual prompts by connecting segmentation models with language models. Experimental results demonstrate that our model outperforms other LMMs on . Furthermore, our model achieves competitive performance on classic grounding benchmarks like RefCOCO/+/g and Flickr30K Entities."

"In this work, we present a novel method to tackle the token generation challenge in Vision Language Models (VLMs) for video and image understanding, called LLaMA-VID. Current VLMs, while proficient in tasks like image captioning and visual question answering, face computational burdens when processing long videos due to the excessive visual tokens. LLaMA-VID addresses this issue by representing each frame with two distinct tokens, namely context token and content token. The context token encodes the overall image context based on user input, whereas the content token encapsulates visual cues in each frame. This dual-token strategy significantly reduces the overload of long videos while preserving critical information. Generally, LLaMA-VID empowers existing frameworks to support hour-long videos and pushes their upper limit with an extra context token. It is demonstrated to surpass previous methods on most of video- or image-based benchmarks. Code and models are available at https://github.com/dvlab-research/LLaMA-VID."

"In this paper, we introduce a Multimodal Large Language Model-based Generation Assistant (LLMGA), leveraging the vast reservoir of knowledge and proficiency in reasoning, comprehension, and response inherent in Large Language Models (LLMs) to assist users in image generation and editing. Diverging from existing approaches where Multimodal Large Language Models (MLLMs) generate fixed-size embeddings to control Stable Diffusion (SD), our LLMGA provides a detailed language generation prompt for precise control over SD. This not only augments LLM context understanding but also reduces noise in generation prompts, yields images with more intricate and precise content, and elevates the interpretability of the network. To this end, we curate a comprehensive dataset comprising prompt refinement, similar image generation, inpainting & outpainting, and instruction-based editing. Moreover, we propose a two-stage training scheme. In the first stage, we train the MLLM to grasp the properties of image generation and editing, enabling it to generate detailed prompts. In the second stage, we optimize SD to align with the MLLM’s generation prompts. Additionally, we propose a reference-based restoration network to alleviate texture, brightness, and contrast disparities between generated and preserved regions during inpainting and outpainting. Extensive results show that LLMGA has promising generation and editing capabilities and can enable more flexible and expansive applications in an interactive manner."

"Restoring ancient manuscripts fragments, such as those from Dunhuang, is crucial for preserving human historical culture. However, their worldwide dispersal and the shifts in cultural and historical contexts pose significant restoration challenges. Traditional archaeological efforts primarily focus on manually piecing major fragments together, yet the small and more intricate pieces remain largely unexplored, which is technically due to their irregular shapes, sparse textual content, and extensive combinatorial space for reassembly. In this paper, we formalize the task of restoring the ancient manuscript from fragments as a cardinality-constrained combinatorial optimization problem, and propose a framework named LLMCO4MR: (Multimodal) Large Language Model-aided Combinatorial Optimization Neural Networks for Ancient Manuscript Restoration. Specifically, LLMCO4MR encapsulates a neural combinatorial solver equipped with a differentiable optimal transport (OT) layer, to efficiently predict the Top-K likely mutual reassembly candidates. Multimodal Large Language Model (MLLM) is then adopted and prompted to yield pairwise matching confidence and relative directions for final restoration. Experiments on synthetic data and cases studies with real-world famous Dunhuang fragments demonstrate our approach’s practical potential in assisting archaeologists. Our method provides a novel perspective for ancient manuscript restoration."

"The distribution of subpopulations is an important property hidden within a dataset. Uncovering and analyzing the subpopulation distribution within datasets provides a comprehensive understanding of the datasets, standing as a powerful tool beneficial to various downstream tasks, including Dataset Subpopulation Organization, Subpopulation Shift, and Slice Discovery. Despite its importance, there has been no work that systematically explores the subpopulation distribution of datasets to our knowledge. To address the limitation and solve all the mentioned tasks in a unified way, we introduce a novel concept of subpopulation structures to represent, analyze, and utilize subpopulation distributions within datasets. To characterize the structures in an interpretable manner, we propose the Subpopulation Structure Discovery with Large Language Models (SSD-LLM) framework, which employs world knowledge and instruction-following capabilities of Large Language Models (LLMs) to linguistically analyze informative image captions and summarize the structures. Furthermore, we propose complete workflows to address downstream tasks, named Task-specific Tuning, showcasing the application of the discovered structure to a spectrum of subpopulation-related tasks, including dataset subpopulation organization, subpopulation shift, and slice discovery. With the help of SSD-LLM, we can structuralize the datasets into subpopulation-level automatically, achieve average +3.3% worst group accuracy gain compared to previous methods on subpopulation shift benchmark Waterbirds, Metashift and Nico++, and also identify more consistent slice topics with a higher model error rate of 3.95% on slice discovery task for ImageNet. The code will be available at https://llm-as-dataset-analyst.github.io/."

"Vision-and-Language Navigation (VLN) involves guiding an agent through indoor environments using human-provided textual instructions. Coarse-grained VLN, with short and high-level instructions, has gained popularity as it closely mirrors real-world scenarios. However, a significant challenge is these instructions are often too concise for agents to comprehend and act upon. Previous studies have explored allowing agents to seek assistance during navigation, but typically offer rigid support from pre-existing datasets or simulators. The advent of Large Language Models (LLMs) presents a novel avenue for aiding VLN agents. This paper introduces VLN-Copilot, a framework enabling agents to actively seek assistance when encountering confusion, with the LLM serving as a copilot to facilitate navigation. Our approach includes the introduction of a confusion score, quantifying the level of uncertainty in an agent’s action decisions, while the LLM offers real-time detailed guidance for navigation. Experimental results on two coarse-grained VLN datasets show the efficacy of our method."

"There has been tremendous progress in multimodal Large Language Models (LLMs). Recent works have extended these models to video input with promising instruction following capabilities. However, an important missing piece is temporal localization. These models cannot accurately answer the “When?” questions. We identify three key aspects that limit their temporal localization capabilities: (i) time representation, (ii) architecture, and (iii) data. We address these shortcomings by proposing Language Instructed Temporal-Localization Assistant () with the following features: (1) We introduce time tokens that encode timestamps relative to the video length to better represent time in videos. (2) We introduce SlowFast tokens in the architecture to capture temporal information at fine temporal resolution. (3) We emphasize temporal localization data for . In addition to leveraging existing video datasets with timestamps, we propose a new task, Reasoning Temporal Localization (RTL), along with the dataset, ActivityNet-RTL, for learning and evaluating this task. Reasoning temporal localization requires both the reasoning and temporal localization of Video LLMs. demonstrates strong performance on this challenging task, nearly doubling the temporal mean intersection-over-union (mIoU) of baselines. In addition, we show that our emphasis on temporal localization also substantially improves video-based text generation compared to existing Video LLMs, including a 36% relative improvement of Temporal Understanding. Code is available at: https://github.com/NVlabs/LITA"

"3D object detection is one of the most important components in any Self-Driving stack, but current object detectors require costly & slow manual annotation of 3D bounding boxes to perform well. Recently, several methods emerged to generate without human supervision, however, all of these methods have various drawbacks: Some methods require sensor rigs with full camera coverage and accurate calibration, partly supplemented by an auxiliary optical flow engine. Others require expensive high-precision localization to find objects that disappeared over multiple drives. We introduce a novel self-supervised method to train object detection networks, requiring only unlabeled sequences of lidar point clouds. We call this trajectory-regularized self-training. It utilizes a self-supervised network under the hood to generate, track, and iteratively refine . We demonstrate the effectiveness of our approach for multiple object detection networks across multiple real-world datasets. Code will be released1 . 1 https://github.com/baurst/liso"

"The revolutionary capabilities of large language models (LLMs) have paved the way for multimodal large language models (MLLMs) and fostered diverse applications across various specialized domains. In the remote sensing (RS) field, however, the diverse geographical landscapes and varied objects in RS imagery are not adequately considered in recent MLLM endeavors. To bridge this gap, we construct a large-scale RS image-text dataset, LHRS1 -Align, and an informative RS-specific instruction dataset, , leveraging the extensive volunteered geographic information (VGI) and globally available RS images. Building on this foundation, we introduce , an MLLM tailored for RS image understanding through a novel multi-level vision-language alignment strategy and a curriculum learning method. Additionally, we introduce , a benchmark for thoroughly evaluating MLLMs’ abilities in RS image understanding. Comprehensive experiments demonstrate that exhibits a profound understanding of RS images and the ability to perform nuanced reasoning within the RS domain2 . 1 LHRS 2 Data, stands for ’Language Helps Remote Sensing’. Code and model are available at https://github.com/NJU-LHRS/LHRS-Bot"

"3D content creation has achieved significant progress in terms of both quality and speed. Although current feed-forward models can produce 3D objects in seconds, their resolution is constrained by the intensive computation required during training. In this paper, we introduce Large Multi-View Gaussian Model (LGM), a novel framework designed to generate high-resolution 3D models from text prompts or single-view images. Our key insights are two-fold: 1) 3D Representation: We propose multi-view Gaussian features as an efficient yet powerful representation, which can then be fused together for differentiable rendering. 2) 3D Backbone: We present an asymmetric U-Net as a high-throughput backbone operating on multi-view images, which can be produced from text or single-view image input by leveraging multi-view diffusion models. Extensive experiments demonstrate the high fidelity and efficiency of our approach. Notably, we maintain the fast speed to generate 3D objects within 5 seconds while boosting the training resolution to 512, thereby achieving high-resolution 3D content generation. Our project page is available at https://me.kiui.moe/ lgm/."

"The ability of gaze estimation models to generalize is often significantly hindered by various factors unrelated to gaze, especially when the training dataset is limited. Current strategies aim to address this challenge through different domain generalization techniques, yet they have had limited success due to the risk of overfitting when solely relying on value labels for regression. Recent progress in pre-trained vision-language models has motivated us to capitalize on the abundant semantic information available. We propose a novel approach in this paper, reframing the gaze estimation task as a vision-language alignment issue. Our proposed framework, named Language-Guided Gaze Estimation (LG-Gaze), learns continuous and geometry-sensitive features for gaze estimation benefit from the rich prior knowledges of vision-language models. Specifically, LG-Gaze aligns gaze features with continuous linguistic features through our proposed multimodal contrastive regression loss, which customizes adaptive weights for different negative samples. Furthermore, to better adapt to the labels for gaze estimation task, we propose a geometry-aware interpolation method to obtain more precise gaze embeddings. Through extensive experiments, we validate the efficacy of our framework in four different cross-domain evaluation tasks."

"Accurate 3D object detection is vital for automated driving. While lidar sensors are well suited for this task, they are expensive and have limitations in adverse weather conditions. 3+1D imaging radar sensors offer a cost-effective, robust alternative but face challenges due to their low resolution and high measurement noise. Existing 3+1D imaging radar datasets include radar and lidar data, enabling cross-modal model improvements. Although lidar should not be used during inference, it can aid the training of radar-only object detectors. We explore two strategies to transfer knowledge from the lidar to the radar domain and radar-only object detectors: 1. multi-stage training with sequential lidar point cloud thin-out, and 2. cross-modal knowledge distillation. In the multi-stage process, three thin-out methods are examined. Our results show significant performance gains of up to 4.2 percentage points in mean Average Precision with multi-stage training and up to 3.9 percentage points with knowledge distillation by initializing the student with the teacher’s weights. The main benefit of these approaches is their applicability to other 3D object detection networks without altering their architecture, as we show by analyzing it on two different object detectors. Our code is available at https://github.com/ rst-tu-dortmund/lerojd."

"Neural Radiance Fields (NeRFs) have revolutionized the reconstruction of static scenes and objects in 3D, offering unprecedented quality. However, extending NeRFs to model dynamic objects or object articulations remains a challenging problem. Previous works have tackled this issue by focusing on part-level reconstruction and motion estimation for objects, but they often rely on heuristics regarding the number of moving parts or object categories, which can limit their practical use. In this work, we introduce , a novel approach for representing dynamic 3D objects. Our method involves observing the object at distinct time steps or “states” and conditioning a hypernetwork on the current state, using this to parameterize our NeRF. This approach allows us to learn a view-invariant latent representation for each state. We further demonstrate that by interpolating between these states, we can generate novel articulation configurations in 3D space that were previously unseen. Our experimental results highlight the effectiveness of our method in articulating objects in a manner that is independent of the viewing angle and joint configuration. Notably, our approach outperforms previous methods that rely on motion information for articulation registration."