Unsupervised localization and segmentation are long-standing robot vision challenges that describe the critical ability for an autonomous robot to learn to decompose images into individual objects without labeled data. These tasks are important because of the limited availability of dense image manual annotation and the promising vision of adapting to an evolving set of object categories in lifelong learning. Most recent methods focus on using visual appearance continuity as object cues by spatially clustering features obtained from self-supervised vision transformers (ViT). In this work, we leverage motion cues, inspired by the common fate principle that pixels that share similar movements tend to belong to the same object. We propose a new loss term formulation that uses optical flow in unlabeled videos to encourage self-supervised ViT features to become closer to each other if their corresponding spatial locations share similar movements, and vice versa. We use the proposed loss function to finetune vision transformers that were originally trained on static images. Our fine-tuning procedure outperforms state-of-the-art techniques for unsupervised semantic segmentation through linear probing, without the use of any labeled data. This procedure also demonstrates increased performance over original ViT networks across unsupervised object localization and semantic segmentation benchmarks.
相關內容
Humans learn about objects via interaction and using multiple perceptions, such as vision, sound, and touch. While vision can provide information about an object's appearance, non-visual sensors, such as audio and haptics, can provide information about its intrinsic properties, such as weight, temperature, hardness, and the object's sound. Using tools to interact with objects can reveal additional object properties that are otherwise hidden (e.g., knives and spoons can be used to examine the properties of food, including its texture and consistency). Robots can use tools to interact with objects and gather information about their implicit properties via non-visual sensors. However, a robot's model for recognizing objects using a tool-mediated behavior does not generalize to a new tool or behavior due to differing observed data distributions. To address this challenge, we propose a framework to enable robots to transfer implicit knowledge about granular objects across different tools and behaviors. The proposed approach learns a shared latent space from multiple robots' contexts produced by respective sensory data while interacting with objects using tools. We collected a dataset using a UR5 robot that performed 5,400 interactions using 6 tools and 6 behaviors on 15 granular objects and tested our method on cross-tool and cross-behavioral transfer tasks. Our results show the less experienced target robot can benefit from the experience gained from the source robot and perform recognition on a set of novel objects. We have released the code, datasets, and additional results: //github.com/gtatiya/Tool-Knowledge-Transfer.
A typical application of upper-limb exoskeleton robots is deployment in rehabilitation training, helping patients to regain manipulative abilities. However, as the patient is not always capable of following the robot, safety issues may arise during the training. Due to the bias in different patients, an individualized scheme is also important to ensure that the robot suits the specific conditions (e.g., movement habits) of a patient, hence guaranteeing effectiveness. To fulfill this requirement, this paper proposes a new motion planning scheme for upper-limb exoskeleton robots, which drives the robot to provide customized, safe, and individualized assistance using both human demonstration and interactive learning. Specifically, the robot first learns from a group of healthy subjects to generate a reference motion trajectory via probabilistic movement primitives (ProMP). It then learns from the patient during the training process to further shape the trajectory inside a moving safe region. The interactive data is fed back into the ProMP iteratively to enhance the individualized features for as long as the training process continues. The robot tracks the individualized trajectory under a variable impedance model to realize the assistance. Finally, the experimental results are presented in this paper to validate the proposed control scheme.
Differentiable Resolution Compression and Alignment for Efficient Video Classification and Retrieval
Optimizing video inference efficiency has become increasingly important with the growing demand for video analysis in various fields. Some existing methods achieve high efficiency by explicit discard of spatial or temporal information, which poses challenges in fast-changing and fine-grained scenarios. To address these issues, we propose an efficient video representation network with Differentiable Resolution Compression and Alignment mechanism, which compresses non-essential information in the early stage of the network to reduce computational costs while maintaining consistent temporal correlations. Specifically, we leverage a Differentiable Context-aware Compression Module to encode the saliency and non-saliency frame features, refining and updating the features into a high-low resolution video sequence. To process the new sequence, we introduce a new Resolution-Align Transformer Layer to capture global temporal correlations among frame features with different resolutions, while reducing spatial computation costs quadratically by utilizing fewer spatial tokens in low-resolution non-saliency frames. The entire network can be end-to-end optimized via the integration of the differentiable compression module. Experimental results show that our method achieves the best trade-off between efficiency and performance on near-duplicate video retrieval and competitive results on dynamic video classification compared to state-of-the-art methods. Code://github.com/dun-research/DRCA
Recent advances in eXplainable AI (XAI) have provided new insights into how models for vision, language, and tabular data operate. However, few approaches exist for understanding speech models. Existing work focuses on a few spoken language understanding (SLU) tasks, and explanations are difficult to interpret for most users. We introduce a new approach to explain speech classification models. We generate easy-to-interpret explanations via input perturbation on two information levels. 1) Word-level explanations reveal how each word-related audio segment impacts the outcome. 2) Paralinguistic features (e.g., prosody and background noise) answer the counterfactual: ``What would the model prediction be if we edited the audio signal in this way?'' We validate our approach by explaining two state-of-the-art SLU models on two speech classification tasks in English and Italian. Our findings demonstrate that the explanations are faithful to the model's inner workings and plausible to humans. Our method and findings pave the way for future research on interpreting speech models.
Monocular cameras are extensively employed in indoor robotics, but their performance is limited in visual odometry, depth estimation, and related applications due to the absence of scale information.Depth estimation refers to the process of estimating a dense depth map from the corresponding input image, existing researchers mostly address this issue through deep learning-based approaches, yet their inference speed is slow, leading to poor real-time capabilities. To tackle this challenge, we propose an explicit method for rapid monocular depth recovery specifically designed for corridor environments, leveraging the principles of nonlinear optimization. We adopt the virtual camera assumption to make full use of the prior geometric features of the scene. The depth estimation problem is transformed into an optimization problem by minimizing the geometric residual. Furthermore, a novel depth plane construction technique is introduced to categorize spatial points based on their possible depths, facilitating swift depth estimation in enclosed structural scenarios, such as corridors. We also propose a new corridor dataset, named Corr\_EH\_z, which contains images as captured by the UGV camera of a variety of corridors. An exhaustive set of experiments in different corridors reveal the efficacy of the proposed algorithm.
RGB-T saliency detection has emerged as an important computer vision task, identifying conspicuous objects in challenging scenes such as dark environments. However, existing methods neglect the characteristics of cross-modal features and rely solely on network structures to fuse RGB and thermal features. To address this, we first propose a Multi-Modal Hybrid loss (MMHL) that comprises supervised and self-supervised loss functions. The supervised loss component of MMHL distinctly utilizes semantic features from different modalities, while the self-supervised loss component reduces the distance between RGB and thermal features. We further consider both spatial and channel information during feature fusion and propose the Hybrid Fusion Module to effectively fuse RGB and thermal features. Lastly, instead of jointly training the network with cross-modal features, we implement a sequential training strategy which performs training only on RGB images in the first stage and then learns cross-modal features in the second stage. This training strategy improves saliency detection performance without computational overhead. Results from performance evaluation and ablation studies demonstrate the superior performance achieved by the proposed method compared with the existing state-of-the-art methods.
Foundation models pretrained on diverse data at scale have demonstrated extraordinary capabilities in a wide range of vision and language tasks. When such models are deployed in real world environments, they inevitably interface with other entities and agents. For example, language models are often used to interact with human beings through dialogue, and visual perception models are used to autonomously navigate neighborhood streets. In response to these developments, new paradigms are emerging for training foundation models to interact with other agents and perform long-term reasoning. These paradigms leverage the existence of ever-larger datasets curated for multimodal, multitask, and generalist interaction. Research at the intersection of foundation models and decision making holds tremendous promise for creating powerful new systems that can interact effectively across a diverse range of applications such as dialogue, autonomous driving, healthcare, education, and robotics. In this manuscript, we examine the scope of foundation models for decision making, and provide conceptual tools and technical background for understanding the problem space and exploring new research directions. We review recent approaches that ground foundation models in practical decision making applications through a variety of methods such as prompting, conditional generative modeling, planning, optimal control, and reinforcement learning, and discuss common challenges and open problems in the field.
Denoising diffusion models represent a recent emerging topic in computer vision, demonstrating remarkable results in the area of generative modeling. A diffusion model is a deep generative model that is based on two stages, a forward diffusion stage and a reverse diffusion stage. In the forward diffusion stage, the input data is gradually perturbed over several steps by adding Gaussian noise. In the reverse stage, a model is tasked at recovering the original input data by learning to gradually reverse the diffusion process, step by step. Diffusion models are widely appreciated for the quality and diversity of the generated samples, despite their known computational burdens, i.e. low speeds due to the high number of steps involved during sampling. In this survey, we provide a comprehensive review of articles on denoising diffusion models applied in vision, comprising both theoretical and practical contributions in the field. First, we identify and present three generic diffusion modeling frameworks, which are based on denoising diffusion probabilistic models, noise conditioned score networks, and stochastic differential equations. We further discuss the relations between diffusion models and other deep generative models, including variational auto-encoders, generative adversarial networks, energy-based models, autoregressive models and normalizing flows. Then, we introduce a multi-perspective categorization of diffusion models applied in computer vision. Finally, we illustrate the current limitations of diffusion models and envision some interesting directions for future research.
Temporal relational modeling in video is essential for human action understanding, such as action recognition and action segmentation. Although Graph Convolution Networks (GCNs) have shown promising advantages in relation reasoning on many tasks, it is still a challenge to apply graph convolution networks on long video sequences effectively. The main reason is that large number of nodes (i.e., video frames) makes GCNs hard to capture and model temporal relations in videos. To tackle this problem, in this paper, we introduce an effective GCN module, Dilated Temporal Graph Reasoning Module (DTGRM), designed to model temporal relations and dependencies between video frames at various time spans. In particular, we capture and model temporal relations via constructing multi-level dilated temporal graphs where the nodes represent frames from different moments in video. Moreover, to enhance temporal reasoning ability of the proposed model, an auxiliary self-supervised task is proposed to encourage the dilated temporal graph reasoning module to find and correct wrong temporal relations in videos. Our DTGRM model outperforms state-of-the-art action segmentation models on three challenging datasets: 50Salads, Georgia Tech Egocentric Activities (GTEA), and the Breakfast dataset. The code is available at //github.com/redwang/DTGRM.
Ensembles over neural network weights trained from different random initialization, known as deep ensembles, achieve state-of-the-art accuracy and calibration. The recently introduced batch ensembles provide a drop-in replacement that is more parameter efficient. In this paper, we design ensembles not only over weights, but over hyperparameters to improve the state of the art in both settings. For best performance independent of budget, we propose hyper-deep ensembles, a simple procedure that involves a random search over different hyperparameters, themselves stratified across multiple random initializations. Its strong performance highlights the benefit of combining models with both weight and hyperparameter diversity. We further propose a parameter efficient version, hyper-batch ensembles, which builds on the layer structure of batch ensembles and self-tuning networks. The computational and memory costs of our method are notably lower than typical ensembles. On image classification tasks, with MLP, LeNet, and Wide ResNet 28-10 architectures, our methodology improves upon both deep and batch ensembles.
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