ECCV 2024 Papers

"Multi-head self-attention (MSA) is a key component of Vision Transformers (ViTs), which have achieved great success in various vision tasks. However, their high computational cost and memory footprint hinder their deployment on resource-constrained devices. Conventional pruning approaches can only compress and accelerate the MSA module using head pruning, although the head is not an atomic unit. To address this issue, we propose a novel graph-aware neuron-level pruning method, Structured Neuron-level Pruning (SNP). SNP prunes neurons with less informative attention scores and eliminates redundancy among heads. Specifically, it prunes graphically connected query and key layers having the least informative attention scores while preserving the overall attention scores. Value layers, which can be pruned independently, are pruned to eliminate inter-head redundancy. Our proposed method effectively compresses and accelerates Transformer-based models for both edge devices and server processors. For instance, the DeiT-Small with SNP runs 3.1 times faster than the original model and achieves performance that is 21.94% faster and 1.12% higher than the DeiT-Tiny. Additionally, SNP accelerates the efficiently designed Transformer model, EfficientFormer, by 1.74 times on the Jetson Nano with acceptable performance degradation. Source code is at https://github.com/Nota-NetsPresso/SNP"

"We introduce a novel Stylized Motion Diffusion model, dubbed , to generate stylized motion driven by content texts and style motion sequences. Unlike existing methods that either generate motion of various content or transfer style from one sequence to another, can rapidly generate motion across a broad range of content and diverse styles. To this end, we tailor a pre-trained text-to-motion model for stylization. Specifically, we propose style guidance to ensure that the generated motion closely matches the reference style, alongside a lightweight style adaptor that directs the motion towards the desired style while ensuring realism. Experiments across various applications demonstrate that our proposed framework outperforms existing methods in stylized motion generation. Project Page: https://neu-vi.github.io/SMooDi/"

"Transformer-based restoration methods achieve significant performance as the self-attention (SA) of the Transformer can explore non-local information for better high-resolution image reconstruction. However, the key dot-product SA requires substantial computational resources, which limits its application in low-power devices. Moreover, the low-pass nature of the SA mechanism limits its capacity for capturing local details, consequently leading to smooth reconstruction results. To address these issues, we propose a self-modulation feature aggregation (SMFA) module to collaboratively exploit both local and non-local feature interactions for a more accurate reconstruction. Specifically, the SMFA module employs an efficient approximation of self-attention (EASA) branch to model non-local information and uses a local detail estimation (LDE) branch to capture local details. Additionally, we further introduce a partial convolution-based feed-forward network (PCFN) to refine the representative features derived from the SMFA. Extensive experiments show that the proposed SMFANet family achieve a better trade-off between reconstruction performance and computational efficiency on public benchmark datasets. In particular, compared to the ×4 SwinIR-light, SMFANet+ achieves 0.14dB higher performance over five public testsets on average, and ×10 times faster runtime, with only about 43% of the model complexity (e.g., FLOPs). Our source codes and pre-trained models are available at: https://github.com/Zheng-MJ/SMFANet."

"Recent studies highlight that deep learning models often learn spurious features mistakenly linked to labels, compromising their reliability in real-world scenarios where such correlations do not hold. Despite the increasing research effort, existing solutions often face two main challenges: they either demand substantial annotations of spurious attributes, or they yield less competitive outcomes with expensive training when additional annotations are absent. In this paper, we introduce , a cost-effective and performance-targeted approach to reducing spurious correlations in deep learning. Our method leverages a human-in-the-loop protocol featuring a novel attention labeling mechanism with a constructed attention representation space. significantly reduces the need for exhaustive additional labeling, requiring human input for fewer than 3% of instances. By prioritizing data quality over complicated training strategies, curates a smaller yet more feature-balanced data subset, fostering the development of spuriousness-robust models. Experimental validations across key benchmarks demonstrate that competes with or exceeds the performance of leading methods while significantly reducing costs. The framework thus presents a promising path for developing reliable models more efficiently. Our code is available in https://github.com/xiweix/SLIM.git/."

"SLEDGE is the first generative simulator for vehicle motion planning trained on real-world driving logs. Its core component is a learned model that is able to generate agent bounding boxes and lane graphs. The model’s outputs serve as an initial state for rule-based traffic simulation. The unique properties of the entities to be generated for SLEDGE, such as their connectivity and variable count per scene, render the naive application of most modern generative models to this task non-trivial. Therefore, together with a systematic study of existing lane graph representations, we introduce a novel raster-to-vector autoencoder. It encodes agents and the lane graph into distinct channels in a rasterized latent map. This facilitates both lane-conditioned agent generation and combined generation of lanes and agents with a Diffusion Transformer. Using generated entities in SLEDGE enables greater control over the simulation, e.g. upsampling turns or increasing traffic density. Further, SLEDGE can support 500m long routes, a capability not found in existing data-driven simulators like nuPlan. It presents new challenges for planning algorithms, evidenced by failure rates of over 40% for PDM, the winner of the 2023 nuPlan challenge, when tested on hard routes and dense traffic generated by our model. Compared to nuPlan, SLEDGE requires 500× less storage to set up (¡4 GB), making it a more accessible option and helping with democratizing future research in this field."

"Vision Transformer models trained on large-scale datasets, although effective, often exhibit artifacts in the patch token they extract. While such defects can be alleviated by re-training the entire model with additional classification tokens, the underlying reasons for the presence of these tokens remain unclear. In this paper, we conduct a thorough investigation of this phenomenon, combining theoretical analysis with empirical observations. Our findings reveal that these artifacts originate from the pre-trained network itself, specifically stemming from the leading left singular vector of the network’s weights. Furthermore, to mitigate these defects, we propose a novel fine-tuning smooth regularization that rectifies structural deficiencies using only a small dataset, thereby avoiding the need for complete re-training. We validate our method on various downstream tasks, including unsupervised segmentation, classification, supervised segmentation, and depth estimation, demonstrating its effectiveness in improving model performance. Codes and checkpoints are available at https://github.com/haoqiwang/sinder."

"Image-Text pretraining on web-scale image caption datasets has become the default recipe for open vocabulary classification and retrieval models thanks to the success of CLIP and its variants. Several works have also used CLIP features for dense prediction tasks and have shown the emergence of open-set abilities. However, the contrastive objective used by these models only focuses on image-text alignment and does not incentivise image feature learning for dense prediction tasks. In this work, we introduce SILC, a novel framework for vision language pretraining. SILC improves image-text contrastive learning with the simple addition of local-to-global correspondence learning by self-distillation. We show that distilling local image features from an exponential moving average (EMA) teacher model significantly improves model performance on dense predictions tasks like detection and segmentation, while also providing improvements on image-level tasks such as classification and retrieval. models sets a new state of the art for zero-shot classification, few shot classification, image and text retrieval, zero-shot segmentation, and open vocabulary segmentation. We further show that SILC features greatly benefit open vocabulary detection, captioning and visual question answering."

"Video-based pretraining offers immense potential for learning strong visual representations on an unprecedented scale. Recently, masked video modeling methods have shown promising scalability, yet fall short in capturing higher-level semantics due to reconstructing predefined low-level targets such as pixels. To tackle this, we present Sinkhorn-guided Masked Video Modelling (), a novel video pretraining method that jointly learns the video model in addition to a target feature space using a projection network. However, this simple modification means that the regular L2 reconstruction loss will lead to trivial solutions as both networks are jointly optimized. As a solution, we distribute features of space-time tubes evenly across a limited number of learnable clusters. By posing this as an optimal transport problem, we enforce high entropy in the generated features across the batch, infusing semantic and temporal meaning into the feature space. The resulting cluster assignments are used as targets for a symmetric prediction task where the video model predicts cluster assignment of the projection network and vice versa. Experimental results on ten datasets across three benchmarks validate the effectiveness of in learning more performant, temporally-aware, and robust video representations improving upon state-of-the-art methods. Our project website with code is available at: https://quva-lab. github.io/SIGMA."

"Temporal grounding, also known as video moment retrieval, aims at locating video segments corresponding to a given query sentence. The compositional nature of natural language enables the localization beyond predefined events, posing a certain challenge to the compositional generalizability of existing methods. Recent studies establish the correspondence between videos and queries through a decompose-reconstruct manner to achieve compositional generalization. However, they only consider dominant primitives and build negative queries through random sampling and recombination, resulting in semantically implausible negatives that hinder the models from learning rational compositions. In addition, recent DETR-based methods still underperform in compositional temporal grounding, showing irrational saliency responses when given negative queries that have subtle differences from positive queries. To address these limitations, we first propose a large language model-driven method for negative query construction, utilizing GPT-3.5 Turbo to generate semantically plausible hard negative queries. Subsequently, we introduce a coarse-to-fine saliency ranking strategy, which encourages the model to learn the multi-granularity semantic relationships between videos and hierarchical negative queries to boost compositional generalization. Extensive experiments on two challenging benchmarks validate the effectiveness and generalizability of our proposed method. Our code is available at https://github.com/zxccade/SHINE."

"Canonical surface mapping generalizes keypoint detection by assigning each pixel of an object to a corresponding point in a 3D template. Popularised by DensePose for the analysis of humans, authors have since attempted to apply the concept to more categories, but with limited success due to the high cost of manual supervision. In this work, we introduce , a method to learn canonical maps without manual supervision which achieves better results than supervised methods for most categories. Our idea is to leverage foundation computer vision models such as DINO and Stable Diffusion that are open-ended and thus possess excellent priors over natural categories. reduces the problem of estimating image-to-template correspondences to predicting image-to-image correspondences using features from the foundation models. The reduction works by matching images of the object to non-photorealistic renders of the template, which emulates the process of collecting manual annotations for this task. These correspondences are then used to supervise high-quality canonical maps for any object of interest. We also show that image generators can further improve the realism of the template views, which provide an additional source of supervision for the model."

"Parameter-efficient transfer learning (PETL) has emerged as a flourishing research field for adapting large pre-trained models to downstream tasks, greatly reducing trainable parameters while grappling with memory challenges during fine-tuning. To address it, memory-efficient series (METL) avoid backpropagating gradients through the large backbone. However, they compromise by exclusively relying on frozen intermediate outputs and limiting the exhaustive exploration of prior knowledge from pre-trained models. Moreover, the dependency and redundancy between cross-layer features are frequently overlooked, thereby submerging more discriminative representations and causing an inherent performance gap (vs. conventional PETL methods). Hence, we propose an innovative METL strategy called SHERL for resource-limited scenarios to decouple the entire adaptation into two successive and complementary processes. In the early route, intermediate outputs are consolidated via an anti-redundancy operation, enhancing their compatibility for subsequent interactions; thereby in the late route, utilizing minimal late pre-trained layers could alleviate the peak demand on memory overhead and regulate these fairly flexible features into more adaptive and powerful representations for new domains. Extensive ablations on vision-and-language and language-only tasks show that SHERL combines the strengths of both parameter and memory-efficient techniques, performing on-par or better across diverse architectures with lower memory during fine-tuning. Our code is publicly available at: https://github.com/Paranioar/SHERL."

"We present SGS-SLAM, the first semantic visual SLAM system based on Gaussian Splatting. It incorporates appearance, geometry, and semantic features through multi-channel optimization, addressing the oversmoothing limitations of neural implicit SLAM systems in high-quality rendering, scene understanding, and object-level geometry. We introduce a unique semantic feature loss that effectively compensates for the shortcomings of traditional depth and color losses in object optimization. Through a semantic-guided keyframe selection strategy, we prevent erroneous reconstructions caused by cumulative errors. Extensive experiments demonstrate that SGS-SLAM delivers state-of-the-art performance in camera pose estimation, map reconstruction, precise semantic segmentation, and object-level geometric accuracy, while ensuring real-time rendering capabilities."

"3D surface reconstruction from images is essential for numerous applications. Recently, Neural Radiance Fields (NeRFs) have emerged as a promising framework for 3D modeling. However, NeRFs require accurate camera poses as input, and existing methods struggle to handle significantly noisy pose estimates (i.e., outliers), which are commonly encountered in real-world scenarios. To tackle this challenge, we present a novel approach that optimizes radiance fields with scene graphs to mitigate the influence of outlier poses. Our method incorporates an adaptive inlier-outlier confidence estimation scheme based on scene graphs, emphasizing images of high compatibility with the neighborhood and consistency in the rendering quality. We also introduce an effective intersection-over-union (IoU) loss to optimize the camera pose and surface geometry, together with a coarse-to-fine strategy to facilitate the training. Furthermore, we propose a new dataset containing typical outlier poses for a detailed evaluation. Experimental results on various datasets consistently demonstrate the effectiveness and superiority of our method over existing approaches, showcasing its robustness in handling outliers and producing high-quality 3D reconstructions. Our code and data are available at: https://github.com/Iris-cyy/SG-NeRF."

"Although LiDAR semantic segmentation advances rapidly, state-of-the-art methods often incorporate specifically designed inductive bias derived from benchmarks originating from mechanical spinning LiDAR. This can limit model generalizability to other kinds of LiDAR technologies and make hyperparameter tuning more complex. To tackle these issues, we propose a generalized framework to accommodate various types of LiDAR prevalent in the market by replacing window-attention with our sparse focal point modulation. Our SFPNet is capable of extracting multi-level contexts and dynamically aggregating them using a gate mechanism. By implementing a channel-wise information query, features that incorporate both local and global contexts are encoded. We also introduce a novel large-scale hybrid-solid LiDAR semantic segmentation dataset for robotic applications. SFPNet demonstrates competitive performance on conventional benchmarks derived from mechanical spinning LiDAR, while achieving state-of-the-art results on benchmark derived from solid-state LiDAR. Additionally, it outperforms existing methods on our novel dataset sourced from hybrid-solid LiDAR. Code and dataset are available at https://github.com/Cavendish518/SFPNet and https://www.semanticindustry.top."

"We present SENC, a novel self-supervised neural cloth simulator that addresses the challenge of cloth self-collision. This problem has remained unresolved due to the gap in simulation setup between recent collision detection and response approaches and self-supervised neural simulators. The former requires collision-free initial setups, while the latter necessitates random cloth instantiation during training. To tackle this issue, we propose a novel loss based on Global Intersection Analysis (GIA). This loss extracts the volume surrounded by the cloth region that forms the penetration. By constructing an energy based on this volume, our self-supervised neural simulator can effectively address cloth self-collisions. Moreover, we develop a self-collision-aware graph neural network capable of learning to handle self-collisions, even for parts that are topologically distant from one another. Additionally, we introduce an effective external force scheme that enables the simulation to learn the cloth’s behavior in response to random external forces. We validate the efficacy of SENC through extensive quantitative and qualitative experiments, demonstrating that it effectively reduces cloth self-collision while maintaining high-quality animation results."

"In-context segmentation aims at segmenting novel images using a few labeled example images, termed as “in-context examples”, exploring content similarities between examples and the target. The resulting models can be generalized seamlessly to novel segmentation tasks, significantly reducing the labeling and training costs compared with conventional pipelines. However, in-context segmentation is more challenging than classic ones requiring the model to learn segmentation rules conditioned on a few samples. Unlike previous work with ad-hoc or non-end-to-end designs, we propose , an end-to-end segment-in-context framework built upon a single vision foundation model (VFM). In particular, leverages the emergent correspondence within VFM to capture dense relationships between target images and in-context samples. As such, information from in-context samples is then extracted into three types of instructions, geometric, visual, and meta instructions, serving as explicit conditions for the final mask prediction. is a straightforward yet effective approach that yields state-of-the-art performance on one-shot segmentation benchmarks. Notably, can be easily generalized to diverse tasks, including video object segmentation and open-vocabulary segmentation. Code will be available at https://github.com/MengLcool/SEGIC."

"Recently, detection transformers (DETRs) have gradually taken a dominant position in 2D detection thanks to their elegant framework. However, DETR-based detectors for 3D point clouds are still difficult to achieve satisfactory performance. We argue that the main challenges are twofold: 1) How to obtain the appropriate object queries is challenging due to the high sparsity and uneven distribution of point clouds; 2) How to implement an effective query interaction by exploiting the rich geometric structure of point clouds is not fully explored. To this end, we propose a Simple and EffEctive 3D DETR method () for detecting 3D objects from point clouds, which involves a dual query selection (DQS) module and a deformable grid attention (DGA) module. More concretely, to obtain appropriate queries, DQS first ensures a high recall to retain a large number of queries by the predicted confidence scores and then further picks out high-quality queries according to the estimated quality scores. DGA uniformly divides each reference box into grids as the reference points and then utilizes the predicted offsets to achieve a flexible receptive field, allowing the network to focus on relevant regions and capture more informative features. Extensive ablation studies on DQS and DGA demonstrate its effectiveness. Furthermore, our achieves state-of-the-art detection performance on both the large-scale Waymo and nuScenes datasets, illustrating the superiority of our proposed method. The code is available at https://github.com/happinesslz/SEED."

"In monocular depth estimation, it is challenging to acquire a large amount of depth-annotated training data, which leads to a reliance on synthetic datasets. However, the inherent discrepancies between the synthetic environment and the real-world result in a domain shift and sub-optimal performance. In this paper, we introduce SEDiff which firstly leverages a diffusion-based generative model to extract essential structural information for accurate depth estimation. SEDiff wipes out the domain-specific components in the synthetic data and enables structural-consistent style transfer to mitigate the performance degradation due to the domain gap. Extensive experiments demonstrate the superiority of SEDiff over state-of-the-art methods in various scenarios for domain-adaptive depth estimation."

"Prompt tuning methods have achieved remarkable success in parameter-efficient fine-tuning on large pre-trained models. However, their application to dual-modal fusion-based visual-language pre-trained models (VLPMs), such as GLIP, has encountered issues. Existing prompt tuning methods have not effectively addressed the modal mapping and aligning problem for tokens in different modalities, leading to poor transfer generalization. To address this issue, we propose Synchronous Dual Prompt Tuning (SDPT). SDPT initializes a single set of learnable unified prototype tokens in the established modal aligning space to represent the aligned semantics of text and image modalities for downstream tasks. Furthermore, SDPT establishes inverse linear projections that require no training to embed the information of unified prototype tokens into the input space of different modalities. The inverse linear projections allow the unified prototype token to synchronously represent the two modalities and enable SDPT to share the unified semantics of text and image for downstream tasks across different modal prompts. Experimental results demonstrate that SDPT assists fusion-based VLPMs to achieve superior outcomes with only 0.04% of model parameters for training across various scenarios, outperforming other single- or dual-modal methods. The code will be released at https://github.com/wuyongjianCODE/SDPT."