ECCV 2024 论文列表

"In Composed Video Retrieval, a video and a textual description which modifies the video content are provided as inputs to the model. The aim is to retrieve the relevant video with the modified content from a database of videos. In this challenging task, the first step is to acquire large-scale training datasets and collect high-quality benchmarks for evaluation. In this work, we introduce , a new evaluation benchmark for fine-grained Composed Video Retrieval using large-scale egocentric video datasets. consists of 2,295 queries that specifically focus on high-quality temporal video understanding. We find that existing Composed Video Retrieval frameworks do not achieve the necessary high-quality temporal video understanding for this task. To address this shortcoming, we adapt a simple training-free method, propose a generic re-ranking framework for Composed Video Retrieval, and demonstrate that this achieves strong results on . Our code and benchmark are freely available at https://github.com/ ExplainableML/EgoCVR."

"Accurate tracking of a user’s body pose while wearing a virtual reality (VR), augmented reality (AR) or mixed reality (MR) headset is a prerequisite for authentic self-expression, natural social presence, and intuitive user interfaces. Existing body tracking approaches on VR/AR devices are either under-constrained, e.g., attempting to infer full body pose from only headset and controller pose, or require impractical hardware setups that place cameras far from a user’s face to improve body visibility. In this paper, we present the first controller-less egocentric body tracking solution that runs on an actual VR device using the same cameras that are used for SLAM tracking. We propose a novel egocentric tracking architecture that models the temporal history of body motion using multi-view latent features. Furthermore, we release the first large-scale real-image dataset for egocentric body tracking, , with a realistic VR headset configuration and diverse subjects and motions. Benchmarks on the dataset shows that our approach outperforms other state-of-the-art methods in both accuracy and smoothness of the resulting motion. We perform ablation studies on our model choices and demonstrate the method running in realtime on a VR headset. Our dataset with more than 30 hours of recordings and 3 million frames will be made publicly available."

"Large-scale image-text pre-trained models enable zero-shot classification and provide consistent accuracy across various data distributions. Nonetheless, optimizing these models in downstream tasks typically requires fine-tuning, which reduces generalization to out-of-distribution (OOD) data and demands extensive computational resources. We introduce Robust Adapter (R-Adapter), a novel method for fine-tuning zero-shot models to downstream tasks while simultaneously addressing both these issues. Our method integrates lightweight modules into the pre-trained model and employs novel self-ensemble techniques to boost OOD robustness and reduce storage expenses substantially. Furthermore, we propose MPM-NCE loss designed for fine-tuning on vision-language downstream tasks. It ensures precise alignment of multiple image-text pairs and discriminative feature learning. By extending the benchmark for robust fine-tuning beyond classification to include diverse tasks such as cross-modal retrieval and open vocabulary segmentation, we demonstrate the broad applicability of R-Adapter. Our extensive experiments demonstrate that R-Adapter achieves state-of-the-art performance across a diverse set of tasks, tuning only 13% of the parameters of the CLIP encoders."

"As a core of Vision Transformer (ViT), self-attention has high versatility in modeling long-range spatial interactions because every query attends to all spatial locations. Although ViT achieves promising performance in visual tasks, self-attention’s complexity is quadratic with token lengths. This leads to challenging problems when adapting ViT models to downstream tasks that require high input resolutions. Previous arts have tried to solve this problem by introducing sparse attention such as spatial reduction attention, and window attention. One common point of these methods is that all image/window tokens are joined during computing attention weights. In this paper, we find out that there exist high similarities between attention weights and incur computation redundancy. To address this issue, this paper introduces novel attention, called partial attention, that learns spatial interactions more efficiently, by reducing redundant information in attention maps. Each query in our attention only interacts with a small set of relevant tokens. Based on partial attention, we propose an efficient and general vision Transformer, named PartialFormer, that attains good trade-offs between accuracy and computational costs across vision tasks. For example, on ImageNet-1K, PartialFormer-B3 surpasses Swin-T by 1.7% Top-1 accuracy while saving 25% GFLOPs, and Focal-T by 0.8% while saving 30% GFLOPs."

"Self-supervised learning has recently emerged as the preeminent pretraining paradigm across and between modalities, with remarkable results. In the image domain specifically, group (or cluster) discrimination has been one of the most successful methods. However, such frameworks need to guard against heavily imbalanced cluster assignments to prevent collapse to trivial solutions. Existing works typically solve this by reweighing cluster assignments to promote balance, or with offline operations (e.g. regular re-clustering) that prevent collapse. However, the former typically requires large batch sizes, which leads to increased resource requirements, and the latter introduces scalability issues with regard to large datasets. In this work, we propose , a framework that tackles this problem with a novel cluster balancing method. estimates the relative size of the clusters across batches and balances them by adjusting cluster assignments, proportionately to their relative size and in an online manner. Thereby, it overcomes previous methods’ dependence on large batch sizes and is fully online, and therefore scalable to any dataset. We conduct extensive experiments to evaluate our approach and demonstrate that : a) achieves state-of-the-art results with significantly reduced resource requirements compared to previous works, b) is fully online, and therefore scalable to large datasets, and c) is stable and effective even with very small batch sizes. Code and models will be made available here."

"Good weight initialization serves as an effective measure to reduce the training cost of a deep neural network (DNN) model. The choice of how to initialize parameters is challenging and may require manual tuning, which can be time-consuming and prone to human error. To overcome such limitations, this work takes a novel step towards building a weight generator to synthesize the neural weights for initialization. We use the image-to-image translation task with generative adversarial networks (GANs) as an example due to the ease of collecting model weights spanning a wide range. Specifically, we first collect a dataset with various image editing concepts and their corresponding trained weights, which are later used for the training of the weight generator. To address the different characteristics among layers and the substantial number of weights to be predicted, we divide the weights into equal-sized blocks and assign each block an index. Subsequently, a diffusion model is trained with such a dataset using both text conditions of the concept and the block indexes. By initializing the image translation model with the denoised weights predicted by our diffusion model, the training requires only 43.3 seconds. Compared to training from scratch (, Pix2pix), we achieve a 15× training time acceleration for a new concept while obtaining even better image generation quality. We will release our dataset, code, and the pre-trained weight generator."

"Spiking neural networks (SNNs) are a novel type of bio-plausible neural network with energy efficiency. However, SNNs are non-differentiable and the training memory costs increase with the number of simulation steps. To address these challenges, this work introduces an implicit training method for SNNs inspired by equilibrium models. Our method relies on the multi-parallel implicit stream architecture (MPIS-SNNs). In the forward process, MPIS-SNNs drive multiple fused parallel implicit streams (ISs) to reach equilibrium state simultaneously. In the backward process, MPIS-SNNs solely rely on a single-time-step simulation of SNNs, avoiding the storage of a large number of activations. Extensive experiments on N-MNIST, Fashion-MNIST, CIFAR-10, and CIFAR-100 demonstrate that MPIS-SNNs exhibit excellent characteristics such as low latency, low memory cost, low firing rates, and fast convergence speed, and are competitive among latest efficient training methods for SNNs. Our code is available at an anonymized GitHub repository: https://github.com/kiritozc/MPIS-SNNs."

"Aiming to address the repetitive need for complex calibration in existing snapshot spectral imaging methods, while better trading off system complexity and spectral reconstruction accuracy, we demonstrate a novel Parallel Coded Calibration-free Aperture Diffraction Imaging Spectrometer (PCCADIS) with simplest parallel architecture and enhanced light throughput. The system integrates monochromatic acquisition of diffraction-induced blurred spatial-spectral projections with uncalibrated chromatic filtering for guidance, enabling portable and lightweight implementation. In the inverse process of PCCADIS, aperture diffraction produces blurred patterns through global replication and band-by-band integration, posing challenges in registration with clearly structured RGB information by feature matching. Therefore, the Self-aware Spectral Fusion Cascaded Transformer (SSFCT) is proposed to realize the fusion and reconstruction of uncalibrated inputs, which demonstrates the potential to substantially improve the accuracy of snapshot spectral imaging while concurrently reducing the associated costs. Our methodology is rigorously evaluated through comprehensive simulation experiments and real reconstruction experiments with a prototype, confirming the high accuracy and user-friendliness of PCCADIS."

"Procedural videos, exemplified by recipe demonstrations, are instrumental in conveying step-by-step instructions. However, understanding such videos is challenging as it involves the precise localization of steps and the generation of textual instructions. Manually annotating steps and writing instructions is costly, which limits the size of current datasets and hinders effective learning. Leveraging large but noisy video-transcript datasets for pre-training can boost performance but demands significant computational resources. Furthermore, transcripts contain irrelevant content and differ in style from human-written instructions. To mitigate these issues, we propose a novel technique, , to automatically generate high-quality training data for the recipe domain: (i) Sieve: filters irrelevant transcripts and (ii) Swap: acquires high-quality text by replacing transcripts with human-written instruction from a text-only recipe dataset. The resulting dataset is three orders of magnitude smaller than current web-scale datasets but enables efficient training of large-scale models. Alongside , we propose Procedure Transformer (ProcX), a model for end-to-end step localization and instruction generation for procedural videos. When pre-trained on our curated dataset, this model achieves state-of-the-art performance on YouCook2 and Tasty while using a fraction of the training data. We have released code and dataset.1 1 https://github.com/anilbatra2185/sns_procx"

"We propose an application of online hard sample mining for efficient training of Neural Radiance Fields (NeRF). NeRF models produce state-of-the-art quality for many 3D reconstruction and rendering tasks but require substantial computational resources. The encoding of the scene information within the NeRF network parameters necessitates stochastic sampling. We observe that during the training, a major part of the compute time and memory usage is spent on processing already learnt samples, which no longer affect the model update significantly. We identify the backward pass on the stochastic samples as the computational bottleneck during the optimization. We thus perform the first forward pass in inference mode as a relatively low-cost search for hard samples. This is followed by building the computational graph and updating the NeRF network parameters using only the hard samples. To demonstrate the effectiveness of the proposed approach, we apply our method to Instant-NGP, resulting in significant improvements of the view-synthesis quality over the baseline (1 dB improvement on average per training time, or 2x speedup to reach the same PSNR level) along with ∼40% memory savings coming from using only the hard samples to build the computational graph. As our method only interfaces with the network module, we expect it to be widely applicable."

"Leveraging the high temporal resolution of an event-based camera requires highly efficient event-by-event processing. However, dense prediction tasks require explicit pixel-level association, which is challenging for event-based processing frameworks. Existing works aggregate the events into a static frame-like representation at the cost of a much slower processing rate and high compute cost. To address this challenge, this work introduces an event-based spatiotemporal representation learning framework for efficiently solving dense prediction tasks. We uniquely handle the sparse, asynchronous events using an unstructured, set-based approach and project them into a hierarchically organized multi-level latent memory space that preserves the pixel-level structure. Low-level event streams are dynamically encoded into these latent structures through an explicit attention-based spatial association. Unlike existing works that update these memory stacks at a fixed rate, we introduce a data-adaptive update rate that recurrently keeps track of the past memory states and learns to update the corresponding memory stacks only when it has substantial new information, thereby improving the overall compute latency. Our method consistently achieves competitive performance across different event-based dense prediction tasks while ensuring much lower latency compared to the existing methods."

"In the field of instruction-following large vision-language models (LVLMs), the efficient deployment of these models faces challenges, notably due to the high memory demands of their key-value (KV) caches. Conventional cache management strategies for LLMs focus on cache eviction, which often fails to address the specific needs of multimodal instruction-following models. Recognizing this gap, in this paper, we introduce Elastic Cache, a novel approach that benefits from applying distinct acceleration methods for instruction encoding and output generation stages. We investigate the metrics of importance in different stages and propose an ‘importance-driven cache merging’ strategy to prune redundancy caches. Instead of discarding less important caches, our strategy identifies important key/value vectors as anchor points. Surrounding less important caches are then merged with these anchors, enhancing the preservation of contextual information in the KV caches while yielding an arbitrary acceleration ratio. For instruction encoding, we utilize the frequency to evaluate the importance of caches. Regarding output generation, we prioritize tokens based on their ‘distance’ with an offset, by which both the initial and most recent tokens are retained. Results on a range of LVLMs demonstrate that Elastic Cache not only boosts efficiency but also notably outperforms existing pruning methods in language generation across various tasks. Code is available at https://github. com/liuzuyan/ElasticCache"

"Self-supervised pre-training of image encoders is omnipresent in the literature, particularly following the introduction of Masked autoencoders (MAE). Current efforts attempt to learn object-centric representations from motion in videos. In particular, SiamMAE recently introduced a Siamese network, training a shared-weight encoder from two frames of a video with a high asymmetric masking ratio (95%). In this work, we propose CropMAE, an alternative approach to the Siamese pre-training introduced by SiamMAE. Our method specifically differs by exclusively considering pairs of cropped images sourced from the same image but cropped differently, deviating from the conventional pairs of frames extracted from a video. CropMAE therefore alleviates the need for video datasets, while maintaining competitive performances and drastically reducing pre-training and learning time. Furthermore, we demonstrate that CropMAE learns similar object-centric representations without explicit motion, showing that current self-supervised learning methods do not learn such representations from explicit object motion, but rather thanks to the implicit image transformations that occur between the two views. Finally, CropMAE achieves the highest masking ratio to date (98.5%), enabling the reconstruction of images using only two visible patches. Our code is available at https://github.com/alexandre-eymael/ CropMAE."

"Most current single image-deraining (SID) methods are based on the Transformer with global modeling for high-quality reconstruction. However, their architectures only build long-range features from the spatial domain, which suffers from a significant computational burden to keep effectiveness. Besides, these methods either overlook negative sample information in training or underutilize the rain streak patterns present in the negative ones. To tackle these problems, we propose a Frequency-Aware Deraining Transformer Framework (FADformer) that fully captures frequency domain features for efficient rain removal. Specifically, we construct the FADBlock, including the Fused Fourier Convolution Mixer (FFCM) and Prior-Gated Feed-forward Network (PGFN). Unlike self-attention mechanisms, the FFCM conducts convolution operations in both spatial and frequency domains, endowing it with local-global capturing capabilities and efficiency. Simultaneously, the PGFN introduces residue channel prior in a gating manner to enhance local details and retain feature structure. Furthermore, we introduce a Frequency-domain Contrastive Regularization (FCR) during training. The FCR facilitates contrastive learning in the frequency domain and leverages rain streak patterns in negative samples to improve performance. Extensive experiments show the efficiency and effectiveness of our FADformer. The source code is available at https://github.com/deng-ai-lab/FADformer."

"The integration with CLIP (Contrastive Vision-Language Pre-training) has significantly refreshed the accuracy leaderboard of FSAR (Few-Shot Action Recognition). However, the trainable overhead of ensuring that the domain alignment of CLIP and FSAR is often unbearable. To mitigate this issue, we present an Efficient Multi-Level Post-Reasoning Network, namely EMP-Net. By design, a post-reasoning mechanism is proposed for domain adaptation, which avoids most gradient backpropagation, improving the efficiency; meanwhile, a multi-level representation is utilised during the reasoning and matching processes to improve the discriminability, ensuring effectiveness. Specifically, the proposed EMP-Net starts with a skip-fusion involving cached multi-stage features extracted by CLIP. After that, the fused feature is decoupled into multi-level representations, including global-level, patch-level, and frame-level. The ensuing spatiotemporal reasoning module operates on multi-level representations to generate discriminative features. As for matching, the contrasts between text-visual and support-query are integrated to provide comprehensive guidance. The experimental results demonstrate that EMP-Net can unlock the potential performance of CLIP in a more efficient manner. The code and supplementary material can be found at https://github.com/cong-wu/EMP-Net."

"Test-time adaptation (TTA) addresses the unforeseen distribution shifts occurring during test time. In TTA, performance, memory consumption, and time consumption are crucial considerations. A recent diffusion-based TTA approach for restoring corrupted images involves image-level updates. However, using pixel space diffusion significantly increases resource requirements compared to conventional model updating TTA approaches, revealing limitations as a TTA method. To address this, we propose a novel TTA method that leverages an image editing model based on a latent diffusion model (LDM) and fine-tunes it using our newly introduced corruption modeling scheme. This scheme enhances the robustness of the diffusion model against distribution shifts by creating (clean, corrupted) image pairs and fine-tuning the model to edit corrupted images into clean ones. Moreover, we introduce a distilled variant to accelerate the model for corruption editing using only 4 network function evaluations (NFEs). We extensively validated our method across various architectures and datasets including image and video domains. Our model achieves the best performance with a 100 times faster runtime than that of a diffusion-based baseline. Furthermore, it is three times faster than the previous model updating TTA method that utilizes data augmentation, making an image-level updating approach more feasible. 1 1 Project page: magentahttps://github.com/oyt9306/Decorruptor"

"This paper identifies significant redundancy in the query-key interactions within self-attention mechanisms of diffusion transformer models, particularly during the early stages of denoising diffusion steps. In response to this observation, we present a novel diffusion transformer framework incorporating an additional set of mediator tokens to engage with queries and keys separately. By modulating the number of mediator tokens during the denoising generation phases, our model initiates the denoising process with a precise, non-ambiguous stage and gradually transitions to a phase enriched with detail. Concurrently, integrating mediator tokens simplifies the attention module’s complexity to a linear scale, enhancing the efficiency of global attention processes. Additionally, we propose a time-step dynamic mediator token adjustment mechanism that further decreases the required computational FLOPs for generation, simultaneously facilitating the generation of high-quality images within the constraints of varied inference budgets. Extensive experiments demonstrate that the proposed method can improve the generated image quality while also reducing the inference cost of diffusion transformers. When integrated with the recent work SiT, our method achieves a state-of-the-art FID score of 2.01. The source code is available at https://github.com/LeapLabTHU/Attention-Mediators."

"Recent advances in implicit scene representation enable high-fidelity street view novel view synthesis. However, existing methods optimize a neural radiance field for each scene, relying heavily on dense training images and extensive computation resources. To mitigate this shortcoming, we introduce a new method called Efficient Depth-Guided Urban View Synthesis (EDUS) for fast feed-forward inference and efficient per-scene fine-tuning. Different from prior generalizable methods that infer geometry based on feature matching, EDUS leverages noisy predicted geometric priors as guidance to enable generalizable urban view synthesis from sparse input images. The geometric priors allow us to apply our generalizable model directly in the 3D space, gaining robustness across various sparsity levels. Through comprehensive experiments on the KITTI-360 and Waymo datasets, we demonstrate promising generalization abilities on novel street scenes. Moreover, our results indicate that EDUS achieves state-of-the-art performance in sparse view settings when combined with fast test-time optimization."

"Image restoration, encompassing tasks such as deblurring, denoising, and super-resolution, remains a pivotal area in computer vision. However, efficiently addressing the spatially varying artifacts of various low-quality images with local adaptiveness and handling their degradations at different scales poses significant challenges. To efficiently tackle these issues, we propose the novel Efficient Cascaded Multiscale Adaptive (ECMA) Network. ECMA employs Local Adaptive Module, LAM, which dynamically adjusts convolution kernels across local image regions to efficiently handle varying artifacts. Thus, LAM addresses the local adaptiveness challenge more efficiently than costlier mechanisms like self-attention, due to its less computationally intensive convolutions. To construct a basic ECMA block, three cascading LAMs with convolution kernels from large to small sizes are employed to capture features at different scales. This cascaded multiscale learning effectively handles degradations at different scales, critical for diverse image restoration tasks. Finally, ECMA blocks are stacked in a U-Net architecture to build ECMA networks, which efficiently achieve both local adaptiveness and multiscale processing. Experiments show ECMA’s high performance and efficiency, achieving comparable or superior restoration performance to state-of-the-art methods while reducing computational costs by 1.2× to 9.7× across various image restoration tasks, e.g., image deblurring, denoising and super-resolution."