Abstract:In this paper, we propose to pre-train audio encoders using synthetic patterns instead of real audio data. Our proposed framework consists of two key elements. The first one is Masked Autoencoder (MAE), a self-supervised learning framework that learns from reconstructing data from randomly masked counterparts. MAEs tend to focus on low-level information such as visual patterns and regularities within data. Therefore, it is unimportant what is portrayed in the input, whether it be images, audio mel-spectrograms, or even synthetic patterns. This leads to the second key element, which is synthetic data. Synthetic data, unlike real audio, is free from privacy and licensing infringement issues. By combining MAEs and synthetic patterns, our framework enables the model to learn generalized feature representations without real data, while addressing the issues related to real audio. To evaluate the efficacy of our framework, we conduct extensive experiments across a total of 13 audio tasks and 17 synthetic datasets. The experiments provide insights into which types of synthetic patterns are effective for audio. Our results demonstrate that our framework achieves performance comparable to models pre-trained on AudioSet-2M and partially outperforms image-based pre-training methods.
Abstract:Pre-training video transformers generally requires a large amount of data, presenting significant challenges in terms of data collection costs and concerns related to privacy, licensing, and inherent biases. Synthesizing data is one of the promising ways to solve these issues, yet pre-training solely on synthetic data has its own challenges. In this paper, we introduce an effective self-supervised learning framework for videos that leverages readily available and less costly static images. Specifically, we define the Pseudo Motion Generator (PMG) module that recursively applies image transformations to generate pseudo-motion videos from images. These pseudo-motion videos are then leveraged in masked video modeling. Our approach is applicable to synthetic images as well, thus entirely freeing video pre-training from data collection costs and other concerns in real data. Through experiments in action recognition tasks, we demonstrate that this framework allows effective learning of spatio-temporal features through pseudo-motion videos, significantly improving over existing methods which also use static images and partially outperforming those using both real and synthetic videos. These results uncover fragments of what video transformers learn through masked video modeling.
Abstract:In this work, we investigate the understudied effect of the training data used for image super-resolution (SR). Most commonly, novel SR methods are developed and benchmarked on common training datasets such as DIV2K and DF2K. However, we investigate and rethink the training data from the perspectives of diversity and quality, {thereby addressing the question of ``How important is SR training for SR models?''}. To this end, we propose an automated image evaluation pipeline. With this, we stratify existing high-resolution image datasets and larger-scale image datasets such as ImageNet and PASS to compare their performances. We find that datasets with (i) low compression artifacts, (ii) high within-image diversity as judged by the number of different objects, and (iii) a large number of images from ImageNet or PASS all positively affect SR performance. We hope that the proposed simple-yet-effective dataset curation pipeline will inform the construction of SR datasets in the future and yield overall better models.
Abstract:Capturing the 3D human body is one of the important tasks in computer vision with a wide range of applications such as virtual reality and sports analysis. However, conventional frame cameras are limited by their temporal resolution and dynamic range, which imposes constraints in real-world application setups. Event cameras have the advantages of high temporal resolution and high dynamic range (HDR), but the development of event-based methods is necessary to handle data with different characteristics. This paper proposes a novel event-based method for 3D pose estimation and human mesh recovery. Prior work on event-based human mesh recovery require frames (images) as well as event data. The proposed method solely relies on events; it carves 3D voxels by moving the event camera around a stationary body, reconstructs the human pose and mesh by attenuated rays, and fit statistical body models, preserving high-frequency details. The experimental results show that the proposed method outperforms conventional frame-based methods in the estimation accuracy of both pose and body mesh. We also demonstrate results in challenging situations where a conventional camera has motion blur. This is the first to demonstrate event-only human mesh recovery, and we hope that it is the first step toward achieving robust and accurate 3D human body scanning from vision sensors.
Abstract:Generating annotations for bird's-eye-view (BEV) segmentation presents significant challenges due to the scenes' complexity and the high manual annotation cost. In this work, we address these challenges by leveraging the abundance of unlabeled data available. We propose the Perspective Cue Training (PCT) framework, a novel training framework that utilizes pseudo-labels generated from unlabeled perspective images using publicly available semantic segmentation models trained on large street-view datasets. PCT applies a perspective view task head to the image encoder shared with the BEV segmentation head, effectively utilizing the unlabeled data to be trained with the generated pseudo-labels. Since image encoders are present in nearly all camera-based BEV segmentation architectures, PCT is flexible and applicable to various existing BEV architectures. PCT can be applied to various settings where unlabeled data is available. In this paper, we applied PCT for semi-supervised learning (SSL) and unsupervised domain adaptation (UDA). Additionally, we introduce strong input perturbation through Camera Dropout (CamDrop) and feature perturbation via BEV Feature Dropout (BFD), which are crucial for enhancing SSL capabilities using our teacher-student framework. Our comprehensive approach is simple and flexible but yields significant improvements over various baselines for SSL and UDA, achieving competitive performances even against the current state-of-the-art.
Abstract:Semantic segmentation is essential in computer vision for various applications, yet traditional approaches face significant challenges, including the high cost of annotation and extensive training for supervised learning. Additionally, due to the limited predefined categories in supervised learning, models typically struggle with infrequent classes and are unable to predict novel classes. To address these limitations, we propose MaskDiffusion, an innovative approach that leverages pretrained frozen Stable Diffusion to achieve open-vocabulary semantic segmentation without the need for additional training or annotation, leading to improved performance compared to similar methods. We also demonstrate the superior performance of MaskDiffusion in handling open vocabularies, including fine-grained and proper noun-based categories, thus expanding the scope of segmentation applications. Overall, our MaskDiffusion shows significant qualitative and quantitative improvements in contrast to other comparable unsupervised segmentation methods, i.e. on the Potsdam dataset (+10.5 mIoU compared to GEM) and COCO-Stuff (+14.8 mIoU compared to DiffSeg). All code and data will be released at https://github.com/Valkyrja3607/MaskDiffusion.
Abstract:Semantic segmentation is a crucial task in computer vision, where each pixel in an image is classified into a category. However, traditional methods face significant challenges, including the need for pixel-level annotations and extensive training. Furthermore, because supervised learning uses a limited set of predefined categories, models typically struggle with rare classes and cannot recognize new ones. Unsupervised and open-vocabulary segmentation, proposed to tackle these issues, faces challenges, including the inability to assign specific class labels to clusters and the necessity of user-provided text queries for guidance. In this context, we propose a novel approach, TAG which achieves Training, Annotation, and Guidance-free open-vocabulary semantic segmentation. TAG utilizes pre-trained models such as CLIP and DINO to segment images into meaningful categories without additional training or dense annotations. It retrieves class labels from an external database, providing flexibility to adapt to new scenarios. Our TAG achieves state-of-the-art results on PascalVOC, PascalContext and ADE20K for open-vocabulary segmentation without given class names, i.e. improvement of +15.3 mIoU on PascalVOC. All code and data will be released at https://github.com/Valkyrja3607/TAG.
Abstract:Schlieren imaging is an optical technique to observe the flow of transparent media, such as air or water, without any particle seeding. However, conventional frame-based techniques require both high spatial and temporal resolution cameras, which impose bright illumination and expensive computation limitations. Event cameras offer potential advantages (high dynamic range, high temporal resolution, and data efficiency) to overcome such limitations due to their bio-inspired sensing principle. This paper presents a novel technique for perceiving air convection using events and frames by providing the first theoretical analysis that connects event data and schlieren. We formulate the problem as a variational optimization one combining the linearized event generation model with a physically-motivated parameterization that estimates the temporal derivative of the air density. The experiments with accurately aligned frame- and event camera data reveal that the proposed method enables event cameras to obtain on par results with existing frame-based optical flow techniques. Moreover, the proposed method works under dark conditions where frame-based schlieren fails, and also enables slow-motion analysis by leveraging the event camera's advantages. Our work pioneers and opens a new stack of event camera applications, as we publish the source code as well as the first schlieren dataset with high-quality frame and event data. https://github.com/tub-rip/event_based_bos
Abstract:In this paper, we present the Semantic Boundary Conditioned Backbone (SBCB) framework, a simple yet effective training framework that is model-agnostic and boosts segmentation performance, especially around the boundaries. Motivated by the recent development in improving semantic segmentation by incorporating boundaries as auxiliary tasks, we propose a multi-task framework that uses semantic boundary detection (SBD) as an auxiliary task. The SBCB framework utilizes the nature of the SBD task, which is complementary to semantic segmentation, to improve the backbone of the segmentation head. We apply an SBD head that exploits the multi-scale features from the backbone, where the model learns low-level features in the earlier stages, and high-level semantic understanding in the later stages. This head perfectly complements the common semantic segmentation architectures where the features from the later stages are used for classification. We can improve semantic segmentation models without additional parameters during inference by only conditioning the backbone. Through extensive evaluations, we show the effectiveness of the SBCB framework by improving various popular segmentation heads and backbones by 0.5% ~ 3.0% IoU on the Cityscapes dataset and gains 1.6% ~ 4.1% in boundary Fscores. We also apply this framework on customized backbones and the emerging vision transformer models and show the effectiveness of the SBCB framework.
Abstract:With the increase in demands for service robots and automated inspection, agents need to localize in its surrounding environment to achieve more natural communication with humans by shared contexts. In this work, we propose a novel but straightforward task of precise target view localization for look around agents called the FindView task. This task imitates the movements of PTZ cameras or user interfaces for 360 degree mediums, where the observer must "look around" to find a view that exactly matches the target. To solve this task, we introduce a rule-based agent that heuristically finds the optimal view and a policy learning agent that employs reinforcement learning to learn by interacting with the 360 degree scene. Through extensive evaluations and benchmarks, we conclude that learned methods have many advantages, in particular precise localization that is robust to corruption and can be easily deployed in novel scenes.