A mainstream type of current self-supervised learning methods pursues a general-purpose representation that can be well transferred to downstream tasks, typically by optimizing on a given pretext task such as instance discrimination. In this work, we argue that existing pretext tasks inevitably introduce biases into the learned representation, which in turn leads to biased transfer performance on various downstream tasks. To cope with this issue, we propose Maximum Entropy Coding (MEC), a more principled objective that explicitly optimizes on the structure of the representation, so that the learned representation is less biased and thus generalizes better to unseen downstream tasks. Inspired by the principle of maximum entropy in information theory, we hypothesize that a generalizable representation should be the one that admits the maximum entropy among all plausible representations. To make the objective end-to-end trainable, we propose to leverage the minimal coding length in lossy data coding as a computationally tractable surrogate for the entropy, and further derive a scalable reformulation of the objective that allows fast computation. Extensive experiments demonstrate that MEC learns a more generalizable representation than previous methods based on specific pretext tasks. It achieves state-of-the-art performance consistently on various downstream tasks, including not only ImageNet linear probe, but also semi-supervised classification, object detection, instance segmentation, and object tracking. Interestingly, we show that existing batch-wise and feature-wise self-supervised objectives could be seen equivalent to low-order approximations of MEC. Code and pre-trained models are available at https://github.com/xinliu20/MEC.
Background modelling is a fundamental step for several real-time computer vision applications that requires security systems and monitoring. An accurate background model helps detecting activity of moving objects in the video. In this work, we have developed a new subspace based background modelling algorithm using the concept of Common Vector Approach with Gram-Schmidt orthogonalization. Once the background model that involves the common characteristic of different views corresponding to the same scene is acquired, a smart foreground detection and background updating procedure is applied based on dynamic control parameters. A variety of experiments is conducted on different problem types related to dynamic backgrounds. Several types of metrics are utilized as objective measures and the obtained visual results are judged subjectively. It was observed that the proposed method stands successfully for all problem types reported on CDNet2014 dataset by updating the background frames with a self-learning feedback mechanism.
The binary neural network, largely saving the storage and computation, serves as a promising technique for deploying deep models on resource-limited devices. However, the binarization inevitably causes severe information loss, and even worse, its discontinuity brings difficulty to the optimization of the deep network. To address these issues, a variety of algorithms have been proposed, and achieved satisfying progress in recent years. In this paper, we present a comprehensive survey of these algorithms, mainly categorized into the native solutions directly conducting binarization, and the optimized ones using techniques like minimizing the quantization error, improving the network loss function, and reducing the gradient error. We also investigate other practical aspects of binary neural networks such as the hardware-friendly design and the training tricks. Then, we give the evaluation and discussions on different tasks, including image classification, object detection and semantic segmentation. Finally, the challenges that may be faced in future research are prospected.
This paper presents a new Vision Transformer (ViT) architecture Multi-Scale Vision Longformer, which significantly enhances the ViT of \cite{dosovitskiy2020image} for encoding high-resolution images using two techniques. The first is the multi-scale model structure, which provides image encodings at multiple scales with manageable computational cost. The second is the attention mechanism of vision Longformer, which is a variant of Longformer \cite{beltagy2020longformer}, originally developed for natural language processing, and achieves a linear complexity w.r.t. the number of input tokens. A comprehensive empirical study shows that the new ViT significantly outperforms several strong baselines, including the existing ViT models and their ResNet counterparts, and the Pyramid Vision Transformer from a concurrent work \cite{wang2021pyramid}, on a range of vision tasks, including image classification, object detection, and segmentation. The models and source code are released at \url{https://github.com/microsoft/vision-longformer}.
We consider the problem of localizing a spatio-temporal tube in a video corresponding to a given text query. This is a challenging task that requires the joint and efficient modeling of temporal, spatial and multi-modal interactions. To address this task, we propose TubeDETR, a transformer-based architecture inspired by the recent success of such models for text-conditioned object detection. Our model notably includes: (i) an efficient video and text encoder that models spatial multi-modal interactions over sparsely sampled frames and (ii) a space-time decoder that jointly performs spatio-temporal localization. We demonstrate the advantage of our proposed components through an extensive ablation study. We also evaluate our full approach on the spatio-temporal video grounding task and demonstrate improvements over the state of the art on the challenging VidSTG and HC-STVG benchmarks. Code and trained models are publicly available at https://antoyang.github.io/tubedetr.html.
We propose a novel hybrid Mamba-Transformer backbone, MambaVision, specifically tailored for vision applications. Our core contribution includes redesigning the Mamba formulation to enhance its capability for efficient modeling of visual features. Through a comprehensive ablation study, we demonstrate the feasibility of integrating Vision Transformers (ViT) with Mamba. Our results show that equipping the Mamba architecture with self-attention blocks in the final layers greatly improves its capacity to capture long-range spatial dependencies. Based on these findings, we introduce a family of MambaVision models with a hierarchical architecture to meet various design criteria. For classification on the ImageNet-1K dataset, MambaVision variants achieve state-of-the-art (SOTA) performance in terms of both Top-1 accuracy and throughput. In downstream tasks such as object detection, instance segmentation, and semantic segmentation on MS COCO and ADE20K datasets, MambaVision outperforms comparably sized backbones while demonstrating favorable performance. Code: https://github.com/NVlabs/MambaVision
Evaluating diffusion-based image-editing models is a crucial task in the field of Generative AI. Specifically, it is imperative to assess their capacity to execute diverse editing tasks while preserving the image content and realism. While recent developments in generative models have opened up previously unheard-of possibilities for image editing, conducting a thorough evaluation of these models remains a challenging and open task. The absence of a standardized evaluation benchmark, primarily due to the inherent need for a post-edit reference image for evaluation, further complicates this issue. Currently, evaluations often rely on established models such as CLIP or require human intervention for a comprehensive understanding of the performance of these image editing models. Our benchmark, PixLens, provides a comprehensive evaluation of both edit quality and latent representation disentanglement, contributing to the advancement and refinement of existing methodologies in the field.
Domain Adaptation (DA) approaches achieved significant improvements in a wide range of machine learning and computer vision tasks (i.e., classification, detection, and segmentation). However, as far as we are aware, there are few methods yet to achieve domain adaptation directly on 3D point cloud data. The unique challenge of point cloud data lies in its abundant spatial geometric information, and the semantics of the whole object is contributed by including regional geometric structures. Specifically, most general-purpose DA methods that struggle for global feature alignment and ignore local geometric information are not suitable for 3D domain alignment. In this paper, we propose a novel 3D Domain Adaptation Network for point cloud data (PointDAN). PointDAN jointly aligns the global and local features in multi-level. For local alignment, we propose Self-Adaptive (SA) node module with an adjusted receptive field to model the discriminative local structures for aligning domains. To represent hierarchically scaled features, node-attention module is further introduced to weight the relationship of SA nodes across objects and domains. For global alignment, an adversarial-training strategy is employed to learn and align global features across domains. Since there is no common evaluation benchmark for 3D point cloud DA scenario, we build a general benchmark (i.e., PointDA-10) extracted from three popular 3D object/scene datasets (i.e., ModelNet, ShapeNet and ScanNet) for cross-domain 3D objects classification fashion. Extensive experiments on PointDA-10 illustrate the superiority of our model over the state-of-the-art general-purpose DA methods.
3D sensing for monocular in-the-wild images, e.g., depth estimation and 3D object detection, has become increasingly important. However, the unknown intrinsic parameter hinders their development and deployment. Previous methods for the monocular camera calibration rely on specific 3D objects or strong geometry prior, such as using a checkerboard or imposing a Manhattan World assumption. This work solves the problem from the other perspective by exploiting the monocular 3D prior. Our method is assumption-free and calibrates the complete $4$ Degree-of-Freedom (DoF) intrinsic parameters. First, we demonstrate intrinsic is solved from two well-studied monocular priors, i.e., monocular depthmap, and surface normal map. However, this solution imposes a low-bias and low-variance requirement for depth estimation. Alternatively, we introduce a novel monocular 3D prior, the incidence field, defined as the incidence rays between points in 3D space and pixels in the 2D imaging plane. The incidence field is a pixel-wise parametrization of the intrinsic invariant to image cropping and resizing. With the estimated incidence field, a robust RANSAC algorithm recovers intrinsic. We demonstrate the effectiveness of our method by showing superior performance on synthetic and zero-shot testing datasets. Beyond calibration, we demonstrate downstream applications in image manipulation detection & restoration, uncalibrated two-view pose estimation, and 3D sensing. Codes, models, and data will be held in https://github.com/ShngJZ/WildCamera.
Recent advancements in deep learning have greatly advanced the field of infrared small object detection (IRSTD). Despite their remarkable success, a notable gap persists between these IRSTD methods and generic segmentation approaches in natural image domains. This gap primarily arises from the significant modality differences and the limited availability of infrared data. In this study, we aim to bridge this divergence by investigating the adaptation of generic segmentation models, such as the Segment Anything Model (SAM), to IRSTD tasks. Our investigation reveals that many generic segmentation models can achieve comparable performance to state-of-the-art IRSTD methods. However, their full potential in IRSTD remains untapped. To address this, we propose a simple, lightweight, yet effective baseline model for segmenting small infrared objects. Through appropriate distillation strategies, we empower smaller student models to outperform state-of-the-art methods, even surpassing fine-tuned teacher results. Furthermore, we enhance the model's performance by introducing a novel query design comprising dense and sparse queries to effectively encode multi-scale features. Through extensive experimentation across four popular IRSTD datasets, our model demonstrates significantly improved performance in both accuracy and throughput compared to existing approaches, surpassing SAM and Semantic-SAM by over 14 IoU on NUDT and 4 IoU on IRSTD1k. The source code and models will be released at https://github.com/O937-blip/SimIR.
We show that the YOLOv4 object detection neural network based on the CSP approach, scales both up and down and is applicable to small and large networks while maintaining optimal speed and accuracy. We propose a network scaling approach that modifies not only the depth, width, resolution, but also structure of the network. YOLOv4-large model achieves state-of-the-art results: 55.5% AP (73.4% AP50) for the MS COCO dataset at a speed of ~16 FPS on Tesla V100, while with the test time augmentation, YOLOv4-large achieves 56.0% AP (73.3 AP50). To the best of our knowledge, this is currently the highest accuracy on the COCO dataset among any published work. The YOLOv4-tiny model achieves 22.0% AP (42.0% AP50) at a speed of 443 FPS on RTX 2080Ti, while by using TensorRT, batch size = 4 and FP16-precision the YOLOv4-tiny achieves 1774 FPS.
Current methods of multi-person pose estimation typically treat the localization and the association of body joints separately. It is convenient but inefficient, leading to additional computation and a waste of time. This paper, however, presents a novel framework PoseDet (Estimating Pose by Detection) to localize and associate body joints simultaneously at higher inference speed. Moreover, we propose the keypoint-aware pose embedding to represent an object in terms of the locations of its keypoints. The proposed pose embedding contains semantic and geometric information, allowing us to access discriminative and informative features efficiently. It is utilized for candidate classification and body joint localization in PoseDet, leading to robust predictions of various poses. This simple framework achieves an unprecedented speed and a competitive accuracy on the COCO benchmark compared with state-of-the-art methods. Extensive experiments on the CrowdPose benchmark show the robustness in the crowd scenes. Source code is available.
Data-based and learning-based sound source localization (SSL) has shown promising results in challenging conditions, and is commonly set as a classification or a regression problem. Regression-based approaches have certain advantages over classification-based, such as continuous direction-of-arrival estimation of static and moving sources. However, multi-source scenarios require multiple regressors without a clear training strategy up-to-date, that does not rely on auxiliary information such as simultaneous sound classification. We investigate end-to-end training of such methods with a technique recently proposed for video object detectors, adapted to the SSL setting. A differentiable network is constructed that can be plugged to the output of the localizer to solve the optimal assignment between predictions and references, optimizing directly the popular CLEAR-MOT tracking metrics. Results indicate large improvements over directly optimizing mean squared errors, in terms of localization error, detection metrics, and tracking capabilities.
Unlike the conventional Knowledge Distillation (KD), Self-KD allows a network to learn knowledge from itself without any guidance from extra networks. This paper proposes to perform Self-KD from image Mixture (MixSKD), which integrates these two techniques into a unified framework. MixSKD mutually distills feature maps and probability distributions between the random pair of original images and their mixup images in a meaningful way. Therefore, it guides the network to learn cross-image knowledge by modelling supervisory signals from mixup images. Moreover, we construct a self-teacher network by aggregating multi-stage feature maps for providing soft labels to supervise the backbone classifier, further improving the efficacy of self-boosting. Experiments on image classification and transfer learning to object detection and semantic segmentation demonstrate that MixSKD outperforms other state-of-the-art Self-KD and data augmentation methods. The code is available at https://github.com/winycg/Self-KD-Lib.
Autonomous agents require the capability to identify dynamic objects in their environment for safe planning and navigation. Incomplete and erroneous dynamic detections jeopardize the agent's ability to accomplish its task. Dynamic detection is a challenging problem due to the numerous sources of uncertainty inherent in the problem's inputs and the wide variety of applications, which often lead to use-case-tailored solutions. We propose a robust learning-free approach to segment moving objects in point cloud data. The foundation of the approach lies in modelling each voxel using a hidden Markov model (HMM), and probabilistically integrating beliefs into a map using an HMM filter. The proposed approach is tested on benchmark datasets and consistently performs better than or as well as state-of-the-art methods with strong generalized performance across sensor characteristics and environments. The approach is open-sourced at https://github.com/vb44/HMM-MOS.
What is a good visual representation for autonomous agents? We address this question in the context of semantic visual navigation, which is the problem of a robot finding its way through a complex environment to a target object, e.g. go to the refrigerator. Instead of acquiring a metric semantic map of an environment and using planning for navigation, our approach learns navigation policies on top of representations that capture spatial layout and semantic contextual cues. We propose to using high level semantic and contextual features including segmentation and detection masks obtained by off-the-shelf state-of-the-art vision as observations and use deep network to learn the navigation policy. This choice allows using additional data, from orthogonal sources, to better train different parts of the model the representation extraction is trained on large standard vision datasets while the navigation component leverages large synthetic environments for training. This combination of real and synthetic is possible because equitable feature representations are available in both (e.g., segmentation and detection masks), which alleviates the need for domain adaptation. Both the representation and the navigation policy can be readily applied to real non-synthetic environments as demonstrated on the Active Vision Dataset [1]. Our approach gets successfully to the target in 54% of the cases in unexplored environments, compared to 46% for non-learning based approach, and 28% for the learning-based baseline.
Early smoke segmentation (ESS) enables the accurate identification of smoke sources, facilitating the prompt extinguishing of fires and preventing large-scale gas leaks. But ESS poses greater challenges than conventional object and regular smoke segmentation due to its small scale and transparent appearance, which can result in high miss detection rate and low precision. To address these issues, a Focus and Separation Network (FoSp) is proposed. We first introduce a Focus module employing bidirectional cascade which guides low-resolution and high-resolution features towards mid-resolution to locate and determine the scope of smoke, reducing the miss detection rate. Next, we propose a Separation module that separates smoke images into a pure smoke foreground and a smoke-free background, enhancing the contrast between smoke and background fundamentally, improving segmentation precision. Finally, a Domain Fusion module is developed to integrate the distinctive features of the two modules which can balance recall and precision to achieve high F_beta. Futhermore, to promote the development of ESS, we introduce a high-quality real-world dataset called SmokeSeg, which contains more small and transparent smoke than the existing datasets. Experimental results show that our model achieves the best performance on three available datasets: SYN70K (mIoU: 83.00%), SMOKE5K (F_beta: 81.6%) and SmokeSeg (F_beta: 72.05%). Especially, our FoSp outperforms SegFormer by 7.71% (F_beta) for early smoke segmentation on SmokeSeg.
Plastic pollution is a critical environmental issue, and detecting and monitoring plastic litter is crucial to mitigate its impact. This paper presents the methodology of mapping street-level litter, focusing primarily on plastic waste and the location of trash bins. Our methodology involves employing a deep learning technique to identify litter and trash bins from street-level imagery taken by a camera mounted on a vehicle. Subsequently, we utilized heat maps to visually represent the distribution of litter and trash bins throughout cities. Additionally, we provide details about the creation of an open-source dataset ("pLitterStreet") which was developed and utilized in our approach. The dataset contains more than 13,000 fully annotated images collected from vehicle-mounted cameras and includes bounding box labels. To evaluate the effectiveness of our dataset, we tested four well known state-of-the-art object detection algorithms (Faster R-CNN, RetinaNet, YOLOv3, and YOLOv5), achieving an average precision (AP) above 40%. While the results show average metrics, our experiments demonstrated the reliability of using vehicle-mounted cameras for plastic litter mapping. The "pLitterStreet" can also be a valuable resource for researchers and practitioners to develop and further improve existing machine learning models for detecting and mapping plastic litter in an urban environment. The dataset is open-source and more details about the dataset and trained models can be found at https://github.com/gicait/pLitter.
Transformers, renowned for their powerful feature extraction capabilities, have played an increasingly prominent role in various vision tasks. Especially, recent advancements present transformer with hierarchical structures such as Dilated Neighborhood Attention Transformer (DiNAT), demonstrating outstanding ability to efficiently capture both global and local features. However, transformers' application in edge detection has not been fully exploited. In this paper, we propose EdgeNAT, a one-stage transformer-based edge detector with DiNAT as the encoder, capable of extracting object boundaries and meaningful edges both accurately and efficiently. On the one hand, EdgeNAT captures global contextual information and detailed local cues with DiNAT, on the other hand, it enhances feature representation with a novel SCAF-MLA decoder by utilizing both inter-spatial and inter-channel relationships of feature maps. Extensive experiments on multiple datasets show that our method achieves state-of-the-art performance on both RGB and depth images. Notably, on the widely used BSDS500 dataset, our L model achieves impressive performances, with ODS F-measure and OIS F-measure of 86.0%, 87.6% for multi-scale input,and 84.9%, and 86.3% for single-scale input, surpassing the current state-of-the-art EDTER by 1.2%, 1.1%, 1.7%, and 1.6%, respectively. Moreover, as for throughput, our approach runs at 20.87 FPS on RTX 4090 GPU with single-scale input. The code for our method will be released soon.
Transformer architectures have become the model of choice in natural language processing and are now being introduced into computer vision tasks such as image classification, object detection, and semantic segmentation. However, in the field of human pose estimation, convolutional architectures still remain dominant. In this work, we present PoseFormer, a purely transformer-based approach for 3D human pose estimation in videos without convolutional architectures involved. Inspired by recent developments in vision transformers, we design a spatial-temporal transformer structure to comprehensively model the human joint relations within each frame as well as the temporal correlations across frames, then output an accurate 3D human pose of the center frame. We quantitatively and qualitatively evaluate our method on two popular and standard benchmark datasets: Human3.6M and MPI-INF-3DHP. Extensive experiments show that PoseFormer achieves state-of-the-art performance on both datasets. Code is available at \url{https://github.com/zczcwh/PoseFormer}