Semi-supervised action segmentation aims to perform frame-wise classification in long untrimmed videos, where only a fraction of videos in the training set have labels. Recent studies have shown the potential of contrastive learning in unsupervised representation learning using unlabelled data. However, learning the representation of each frame by unsupervised contrastive learning for action segmentation remains an open and challenging problem. In this paper, we propose a novel Semantic-guided Multi-level Contrast scheme with a Neighbourhood-Consistency-Aware unit (SMC-NCA) to extract strong frame-wise representations for semi-supervised action segmentation. Specifically, for representation learning, SMC is firstly used to explore intra- and inter-information variations in a unified and contrastive way, based on dynamic clustering process of the original input, encoded semantic and temporal features. Then, the NCA module, which is responsible for enforcing spatial consistency between neighbourhoods centered at different frames to alleviate over-segmentation issues, works alongside SMC for semi-supervised learning. Our SMC outperforms the other state-of-the-art methods on three benchmarks, offering improvements of up to 17.8% and 12.6% in terms of edit distance and accuracy, respectively. Additionally, the NCA unit results in significant better segmentation performance against the others in the presence of only 5% labelled videos. We also demonstrate the effectiveness of the proposed method on our Parkinson's Disease Mouse Behaviour (PDMB) dataset. The code and datasets will be made publicly available.
相關內容
Masked Autoencoder (MAE) has demonstrated superior performance on various vision tasks via randomly masking image patches and reconstruction. However, effective data augmentation strategies for MAE still remain open questions, different from those in contrastive learning that serve as the most important part. This paper studies the prevailing mixing augmentation for MAE. We first demonstrate that naive mixing will in contrast degenerate model performance due to the increase of mutual information (MI). To address, we propose homologous recognition, an auxiliary pretext task, not only to alleviate the MI increasement by explicitly requiring each patch to recognize homologous patches, but also to perform object-aware self-supervised pre-training for better downstream dense perception performance. With extensive experiments, we demonstrate that our proposed Mixed Autoencoder (MixedAE) achieves the state-of-the-art transfer results among masked image modeling (MIM) augmentations on different downstream tasks with significant efficiency. Specifically, our MixedAE outperforms MAE by +0.3% accuracy, +1.7 mIoU and +0.9 AP on ImageNet-1K, ADE20K and COCO respectively with a standard ViT-Base. Moreover, MixedAE surpasses iBOT, a strong MIM method combined with instance discrimination, while accelerating training by 2x. To our best knowledge, this is the very first work to consider mixing for MIM from the perspective of pretext task design. Code will be made available.
Text-to-image generation has made remarkable progress with the emergence of diffusion models. However, it is still a difficult task to generate images for street views based on text, mainly because the road topology of street scenes is complex, the traffic status is diverse and the weather condition is various, which makes conventional text-to-image models difficult to deal with. To address these challenges, we propose a novel controllable text-to-image framework, named \textbf{Text2Street}. In the framework, we first introduce the lane-aware road topology generator, which achieves text-to-map generation with the accurate road structure and lane lines armed with the counting adapter, realizing the controllable road topology generation. Then, the position-based object layout generator is proposed to obtain text-to-layout generation through an object-level bounding box diffusion strategy, realizing the controllable traffic object layout generation. Finally, the multiple control image generator is designed to integrate the road topology, object layout and weather description to realize controllable street-view image generation. Extensive experiments show that the proposed approach achieves controllable street-view text-to-image generation and validates the effectiveness of the Text2Street framework for street views.
Depth estimation in surgical video plays a crucial role in many image-guided surgery procedures. However, it is difficult and time consuming to create depth map ground truth datasets in surgical videos due in part to inconsistent brightness and noise in the surgical scene. Therefore, building an accurate and robust self-supervised depth and camera ego-motion estimation system is gaining more attention from the computer vision community. Although several self-supervision methods alleviate the need for ground truth depth maps and poses, they still need known camera intrinsic parameters, which are often missing or not recorded. Moreover, the camera intrinsic prediction methods in existing works depend heavily on the quality of datasets. In this work, we aimed to build a self-supervised depth and ego-motion estimation system which can predict not only accurate depth maps and camera pose, but also camera intrinsic parameters. We proposed a cost-volume-based supervision manner to give the system auxiliary supervision for camera parameters prediction. The experimental results showed that the proposed method improved the accuracy of estimated camera parameters, ego-motion, and depth estimation.
Instruction-based image editing improves the controllability and flexibility of image manipulation via natural commands without elaborate descriptions or regional masks. However, human instructions are sometimes too brief for current methods to capture and follow. Multimodal large language models (MLLMs) show promising capabilities in cross-modal understanding and visual-aware response generation via LMs. We investigate how MLLMs facilitate edit instructions and present MLLM-Guided Image Editing (MGIE). MGIE learns to derive expressive instructions and provides explicit guidance. The editing model jointly captures this visual imagination and performs manipulation through end-to-end training. We evaluate various aspects of Photoshop-style modification, global photo optimization, and local editing. Extensive experimental results demonstrate that expressive instructions are crucial to instruction-based image editing, and our MGIE can lead to a notable improvement in automatic metrics and human evaluation while maintaining competitive inference efficiency.
In contrast to close-set scenarios that restore images from a predefined set of degradations, open-set image restoration aims to handle the unknown degradations that were unforeseen during the pretraining phase, which is less-touched as far as we know. In this work, we explicitly study this challenging problem and reveal its essence, i.e., the unidentified distribution shifts between test and training data. In recent, test-time adaptation emerges as a fundamental method to address this inherent disparities. Inspired by this, we propose a test-time degradation adaption framework for open-set image restoration, which involves three components, i.e., i) a pre-trained and degradation-agnostic diffusion model to generate clean images, ii) a test-time degradation adapter adapts the unknown degradations based on the input image during the testing phase, and iii) the adapter-guided image restoration guides the model through the adapter to produce the corresponding clean image. Through experiments on multiple degradations absent from the training data, we show that our method achieves comparable even better performance than those task-specific methods.
As a cutting-edge biosensor, the event camera holds significant potential in the field of computer vision, particularly regarding privacy preservation. However, compared to traditional cameras, event streams often contain noise and possess extremely sparse semantics, posing a formidable challenge for event-based person re-identification (event Re-ID). To address this, we introduce a novel event person re-identification network: the Spectrum-guided Feature Enhancement Network (SFE-Net). This network consists of two innovative components: the Multi-grain Spectrum Attention Mechanism (MSAM) and the Consecutive Patch Dropout Module (CPDM). MSAM employs a fourier spectrum transform strategy to filter event noise, while also utilizing an event-guided multi-granularity attention strategy to enhance and capture discriminative person semantics. CPDM employs a consecutive patch dropout strategy to generate multiple incomplete feature maps, encouraging the deep Re-ID model to equally perceive each effective region of the person's body and capture robust person descriptors. Extensive experiments on Event Re-ID datasets demonstrate that our SFE-Net achieves the best performance in this task.
Most existing neural-based text-to-speech methods rely on extensive datasets and face challenges under low-resource condition. In this paper, we introduce a novel semi-supervised text-to-speech synthesis model that learns from both paired and unpaired data to address this challenge. The key component of the proposed model is a dynamic quantized representation module, which is integrated into a sequential autoencoder. When given paired data, the module incorporates a trainable codebook that learns quantized representations under the supervision of the paired data. However, due to the limited paired data in low-resource scenario, these paired data are difficult to cover all phonemes. Then unpaired data is fed to expand the dynamic codebook by adding quantized representation vectors that are sufficiently distant from the existing ones during training. Experiments show that with less than 120 minutes of paired data, the proposed method outperforms existing methods in both subjective and objective metrics.
Spatio-temporal representation learning is critical for video self-supervised representation. Recent approaches mainly use contrastive learning and pretext tasks. However, these approaches learn representation by discriminating sampled instances via feature similarity in the latent space while ignoring the intermediate state of the learned representations, which limits the overall performance. In this work, taking into account the degree of similarity of sampled instances as the intermediate state, we propose a novel pretext task - spatio-temporal overlap rate (STOR) prediction. It stems from the observation that humans are capable of discriminating the overlap rates of videos in space and time. This task encourages the model to discriminate the STOR of two generated samples to learn the representations. Moreover, we employ a joint optimization combining pretext tasks with contrastive learning to further enhance the spatio-temporal representation learning. We also study the mutual influence of each component in the proposed scheme. Extensive experiments demonstrate that our proposed STOR task can favor both contrastive learning and pretext tasks. The joint optimization scheme can significantly improve the spatio-temporal representation in video understanding. The code is available at //github.com/Katou2/CSTP.
Most object recognition approaches predominantly focus on learning discriminative visual patterns while overlooking the holistic object structure. Though important, structure modeling usually requires significant manual annotations and therefore is labor-intensive. In this paper, we propose to "look into object" (explicitly yet intrinsically model the object structure) through incorporating self-supervisions into the traditional framework. We show the recognition backbone can be substantially enhanced for more robust representation learning, without any cost of extra annotation and inference speed. Specifically, we first propose an object-extent learning module for localizing the object according to the visual patterns shared among the instances in the same category. We then design a spatial context learning module for modeling the internal structures of the object, through predicting the relative positions within the extent. These two modules can be easily plugged into any backbone networks during training and detached at inference time. Extensive experiments show that our look-into-object approach (LIO) achieves large performance gain on a number of benchmarks, including generic object recognition (ImageNet) and fine-grained object recognition tasks (CUB, Cars, Aircraft). We also show that this learning paradigm is highly generalizable to other tasks such as object detection and segmentation (MS COCO). Project page: //github.com/JDAI-CV/LIO.
Recommender systems play a crucial role in mitigating the problem of information overload by suggesting users' personalized items or services. The vast majority of traditional recommender systems consider the recommendation procedure as a static process and make recommendations following a fixed strategy. In this paper, we propose a novel recommender system with the capability of continuously improving its strategies during the interactions with users. We model the sequential interactions between users and a recommender system as a Markov Decision Process (MDP) and leverage Reinforcement Learning (RL) to automatically learn the optimal strategies via recommending trial-and-error items and receiving reinforcements of these items from users' feedbacks. In particular, we introduce an online user-agent interacting environment simulator, which can pre-train and evaluate model parameters offline before applying the model online. Moreover, we validate the importance of list-wise recommendations during the interactions between users and agent, and develop a novel approach to incorporate them into the proposed framework LIRD for list-wide recommendations. The experimental results based on a real-world e-commerce dataset demonstrate the effectiveness of the proposed framework.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191