Transparent objects, such as glass walls and doors, constitute architectural obstacles hindering the mobility of people with low vision or blindness. For instance, the open space behind glass doors is inaccessible, unless it is correctly perceived and interacted with. However, traditional assistive technologies rarely cover the segmentation of these safety-critical transparent objects. In this paper, we build a wearable system with a novel dual-head Transformer for Transparency (Trans4Trans) perception model, which can segment general- and transparent objects. The two dense segmentation results are further combined with depth information in the system to help users navigate safely and assist them to negotiate transparent obstacles. We propose a lightweight Transformer Parsing Module (TPM) to perform multi-scale feature interpretation in the transformer-based decoder. Benefiting from TPM, the double decoders can perform joint learning from corresponding datasets to pursue robustness, meanwhile maintain efficiency on a portable GPU, with negligible calculation increase. The entire Trans4Trans model is constructed in a symmetrical encoder-decoder architecture, which outperforms state-of-the-art methods on the test sets of Stanford2D3D and Trans10K-v2 datasets, obtaining mIoU of 45.13% and 75.14%, respectively. Through a user study and various pre-tests conducted in indoor and outdoor scenes, the usability and reliability of our assistive system have been extensively verified. Meanwhile, the Tran4Trans model has outstanding performances on driving scene datasets. On Cityscapes, ACDC, and DADA-seg datasets corresponding to common environments, adverse weather, and traffic accident scenarios, mIoU scores of 81.5%, 76.3%, and 39.2% are obtained, demonstrating its high efficiency and robustness for real-world transportation applications.
Semantic segmentation aims to predict pixel-level labels. It has become a popular task in various computer vision applications. While fully supervised segmentation methods have achieved high accuracy on large-scale vision datasets, they are unable to generalize on a new test environment or a new domain well. In this work, we first introduce a new Un-aligned Domain Score to measure the efficiency of a learned model on a new target domain in unsupervised manner. Then, we present the new Bijective Maximum Likelihood(BiMaL) loss that is a generalized form of the Adversarial Entropy Minimization without any assumption about pixel independence. We have evaluated the proposed BiMaL on two domains. The proposed BiMaL approach consistently outperforms the SOTA methods on empirical experiments on "SYNTHIA to Cityscapes", "GTA5 to Cityscapes", and "SYNTHIA to Vistas".
Bird's-Eye-View (BEV) maps have emerged as one of the most powerful representations for scene understanding due to their ability to provide rich spatial context while being easy to interpret and process. Such maps have found use in many real-world tasks that extensively rely on accurate scene segmentation as well as object instance identification in the BEV space for their operation. However, existing segmentation algorithms only predict the semantics in the BEV space, which limits their use in applications where the notion of object instances is also critical. In this work, we present the first BEV panoptic segmentation approach for directly predicting dense panoptic segmentation maps in the BEV, given a single monocular image in the frontal view (FV). Our architecture follows the top-down paradigm and incorporates a novel dense transformer module consisting of two distinct transformers that learn to independently map vertical and flat regions in the input image from the FV to the BEV. Additionally, we derive a mathematical formulation for the sensitivity of the FV-BEV transformation which allows us to intelligently weight pixels in the BEV space to account for the varying descriptiveness across the FV image. Extensive evaluations on the KITTI-360 and nuScenes datasets demonstrate that our approach exceeds the state-of-the-art in the PQ metric by 3.61 pp and 4.93 pp respectively.
Identifying unexpected objects on roads in semantic segmentation (e.g., identifying dogs on roads) is crucial in safety-critical applications. Existing approaches use images of unexpected objects from external datasets or require additional training (e.g., retraining segmentation networks or training an extra network), which necessitate a non-trivial amount of labor intensity or lengthy inference time. One possible alternative is to use prediction scores of a pre-trained network such as the max logits (i.e., maximum values among classes before the final softmax layer) for detecting such objects. However, the distribution of max logits of each predicted class is significantly different from each other, which degrades the performance of identifying unexpected objects in urban-scene segmentation. To address this issue, we propose a simple yet effective approach that standardizes the max logits in order to align the different distributions and reflect the relative meanings of max logits within each predicted class. Moreover, we consider the local regions from two different perspectives based on the intuition that neighboring pixels share similar semantic information. In contrast to previous approaches, our method does not utilize any external datasets or require additional training, which makes our method widely applicable to existing pre-trained segmentation models. Such a straightforward approach achieves a new state-of-the-art performance on the publicly available Fishyscapes Lost & Found leaderboard with a large margin. Our code is publicly available at this $\href{https://github.com/shjung13/Standardized-max-logits}{link}$.
We study the problem of inferring an object-centric scene representation from a single image, aiming to derive a representation that explains the image formation process, captures the scene's 3D nature, and is learned without supervision. Most existing methods on scene decomposition lack one or more of these characteristics, due to the fundamental challenge in integrating the complex 3D-to-2D image formation process into powerful inference schemes like deep networks. In this paper, we propose unsupervised discovery of Object Radiance Fields (uORF), integrating recent progresses in neural 3D scene representations and rendering with deep inference networks for unsupervised 3D scene decomposition. Trained on multi-view RGB images without annotations, uORF learns to decompose complex scenes with diverse, textured background from a single image. We show that uORF enables novel tasks, such as scene segmentation and editing in 3D, and it performs well on these tasks and on novel view synthesis on three datasets.
3D point-clouds and 2D images are different visual representations of the physical world. While human vision can understand both representations, computer vision models designed for 2D image and 3D point-cloud understanding are quite different. Our paper explores the potential of transferring 2D model architectures and weights to understand 3D point-clouds, by empirically investigating the feasibility of the transfer, the benefits of the transfer, and shedding light on why the transfer works. We discover that we can indeed use the same architecture and pretrained weights of a neural net model to understand both images and point-clouds. Specifically, we transfer the image-pretrained model to a point-cloud model by copying or inflating the weights. We find that finetuning the transformed image-pretrained models (FIP) with minimal efforts -- only on input, output, and normalization layers -- can achieve competitive performance on 3D point-cloud classification, beating a wide range of point-cloud models that adopt task-specific architectures and use a variety of tricks. When finetuning the whole model, the performance improves even further. Meanwhile, FIP improves data efficiency, reaching up to 10.0 top-1 accuracy percent on few-shot classification. It also speeds up the training of point-cloud models by up to 11.1x for a target accuracy (e.g., 90 % accuracy). Lastly, we provide an explanation of the image to point-cloud transfer from the aspect of neural collapse. The code is available at: \url{https://github.com/chenfengxu714/image2point}.
Aerial pixel-wise scene perception of the surrounding environment is an important task for UAVs (Unmanned Aerial Vehicles). Previous research works mainly adopt conventional pinhole cameras or fisheye cameras as the imaging device. However, these imaging systems cannot achieve large Field of View (FoV), small size, and lightweight at the same time. To this end, we design a UAV system with a Panoramic Annular Lens (PAL), which has the characteristics of small size, low weight, and a 360-degree annular FoV. A lightweight panoramic annular semantic segmentation neural network model is designed to achieve high-accuracy and real-time scene parsing. In addition, we present the first drone-perspective panoramic scene segmentation dataset Aerial-PASS, with annotated labels of track, field, and others. A comprehensive variety of experiments shows that the designed system performs satisfactorily in aerial panoramic scene parsing. In particular, our proposed model strikes an excellent trade-off between segmentation performance and inference speed suitable, validated on both public street-scene and our established aerial-scene datasets.
Recently, various convolutions based on continuous or discrete kernels for point cloud processing have been widely studied, and achieve impressive performance in many applications, such as shape classification, scene segmentation and so on. However, they still suffer from some drawbacks. For continuous kernels, the inaccurate estimation of the kernel weights constitutes a bottleneck for further improving the performance; while for discrete ones, the kernels represented as the points located in the 3D space are lack of rich geometry information. In this work, rather than defining a continuous or discrete kernel, we directly embed convolutional kernels into the learnable potential fields, giving rise to potential convolution. It is convenient for us to define various potential functions for potential convolution which can generalize well to a wide range of tasks. Specifically, we provide two simple yet effective potential functions via point-wise convolution operations. Comprehensive experiments demonstrate the effectiveness of our method, which achieves superior performance on the popular 3D shape classification and scene segmentation benchmarks compared with other state-of-the-art point convolution methods.
Despite rapid progress in scene segmentation in recent years, 3D segmentation methods are still limited when there is severe occlusion. The key challenge is estimating the segment boundaries of (partially) occluded objects, which are inherently ambiguous when considering only a single frame. In this work, we propose Multihypothesis Segmentation Tracking (MST), a novel method for volumetric segmentation in changing scenes, which allows scene ambiguity to be tracked and our estimates to be adjusted over time as we interact with the scene. Two main innovations allow us to tackle this difficult problem: 1) A novel way to sample possible segmentations from a segmentation tree; and 2) A novel approach to fusing tracking results with multiple segmentation estimates. These methods allow MST to track the segmentation state over time and incorporate new information, such as new objects being revealed. We evaluate our method on several cluttered tabletop environments in simulation and reality. Our results show that MST outperforms baselines in all tested scenes.
Domain adaptation is to transfer the shared knowledge learned from the source domain to a new environment, i.e., target domain. One common practice is to train the model on both labeled source-domain data and unlabeled target-domain data. Yet the learned models are usually biased due to the strong supervision of the source domain. Most researchers adopt the early-stopping strategy to prevent over-fitting, but when to stop training remains a challenging problem since the lack of the target-domain validation set. In this paper, we propose one efficient bootstrapping method, called Adaboost Student, explicitly learning complementary models during training and liberating users from empirical early stopping. Adaboost Student combines the deep model learning with the conventional training strategy, i.e., adaptive boosting, and enables interactions between learned models and the data sampler. We adopt one adaptive data sampler to progressively facilitate learning on hard samples and aggregate "weak" models to prevent over-fitting. Extensive experiments show that (1) Without the need to worry about the stopping time, AdaBoost Student provides one robust solution by efficient complementary model learning during training. (2) AdaBoost Student is orthogonal to most domain adaptation methods, which can be combined with existing approaches to further improve the state-of-the-art performance. We have achieved competitive results on three widely-used scene segmentation domain adaptation benchmarks.
Enhancing the generalization capability of deep neural networks to unseen domains is crucial for safety-critical applications in the real world such as autonomous driving. To address this issue, this paper proposes a novel instance selective whitening loss to improve the robustness of the segmentation networks for unseen domains. Our approach disentangles the domain-specific style and domain-invariant content encoded in higher-order statistics (i.e., feature covariance) of the feature representations and selectively removes only the style information causing domain shift. As shown in Fig. 1, our method provides reasonable predictions for (a) low-illuminated, (b) rainy, and (c) unseen structures. These types of images are not included in the training dataset, where the baseline shows a significant performance drop, contrary to ours. Being simple yet effective, our approach improves the robustness of various backbone networks without additional computational cost. We conduct extensive experiments in urban-scene segmentation and show the superiority of our approach to existing work. Our code is available at https://github.com/shachoi/RobustNet.
Knee arthroscopy is a minimally invasive surgical (MIS) procedure which is performed to treat knee-joint ailment. Lack of visual information of the surgical site obtained from miniaturized cameras make this surgical procedure more complex. Knee cavity is a very confined space; therefore, surgical scenes are captured at close proximity. Insignificant context of knee atlas often makes them unrecognizable as a consequence unintentional tissue damage often occurred and shows a long learning curve to train new surgeons. Automatic context awareness through labeling of the surgical site can be an alternative to mitigate these drawbacks. However, from the previous studies, it is confirmed that the surgical site exhibits several limitations, among others, lack of discriminative contextual information such as texture and features which drastically limits this vision task. Additionally, poor imaging conditions and lack of accurate ground-truth labels are also limiting the accuracy. To mitigate these limitations of knee arthroscopy, in this work we proposed a scene segmentation method that successfully segments multi structures.
This paper presents a novel self-supervised learning method for handling conversational documents consisting of transcribed text of human-to-human conversations. One of the key technologies for understanding conversational documents is utterance-level sequential labeling, where labels are estimated from the documents in an utterance-by-utterance manner. The main issue with utterance-level sequential labeling is the difficulty of collecting labeled conversational documents, as manual annotations are very costly. To deal with this issue, we propose large-context conversational representation learning (LC-CRL), a self-supervised learning method specialized for conversational documents. A self-supervised learning task in LC-CRL involves the estimation of an utterance using all the surrounding utterances based on large-context language modeling. In this way, LC-CRL enables us to effectively utilize unlabeled conversational documents and thereby enhances the utterance-level sequential labeling. The results of experiments on scene segmentation tasks using contact center conversational datasets demonstrate the effectiveness of the proposed method.
Depth information matters in RGB-D semantic segmentation task for providing additional geometric information to color images. Most existing methods exploit a multi-stage fusion strategy to propagate depth feature to the RGB branch. However, at the very deep stage, the propagation in a simple element-wise addition manner can not fully utilize the depth information. We propose Global-Local propagation network (GLPNet) to solve this problem. Specifically, a local context fusion module(L-CFM) is introduced to dynamically align both modalities before element-wise fusion, and a global context fusion module(G-CFM) is introduced to propagate the depth information to the RGB branch by jointly modeling the multi-modal global context features. Extensive experiments demonstrate the effectiveness and complementarity of the proposed fusion modules. Embedding two fusion modules into a two-stream encoder-decoder structure, our GLPNet achieves new state-of-the-art performance on two challenging indoor scene segmentation datasets, i.e., NYU-Depth v2 and SUN-RGBD dataset.
PixelLib [1] is a library created to allow easy implementation of object segmentation in real life applications. In this paper we discussed in detail how PixelLib makes it possible for developers to implement semantic segmentation, instance segmentation, and background editing in images and videos with great simplification.
Self-attention networks have revolutionized natural language processing and are making impressive strides in image analysis tasks such as image classification and object detection. Inspired by this success, we investigate the application of self-attention networks to 3D point cloud processing. We design self-attention layers for point clouds and use these to construct self-attention networks for tasks such as semantic scene segmentation, object part segmentation, and object classification. Our Point Transformer design improves upon prior work across domains and tasks. For example, on the challenging S3DIS dataset for large-scale semantic scene segmentation, the Point Transformer attains an mIoU of 70.4% on Area 5, outperforming the strongest prior model by 3.3 absolute percentage points and crossing the 70% mIoU threshold for the first time.
Robust semantic scene segmentation for automotive applications is a challenging problem in two key aspects: (1) labelling every individual scene pixel and (2) performing this task under unstable weather and illumination changes (e.g., foggy weather), which results in poor outdoor scene visibility. Such visibility limitations lead to non-optimal performance of generalised deep convolutional neural network-based semantic scene segmentation. In this paper, we propose an efficient end-to-end automotive semantic scene understanding approach that is robust to foggy weather conditions. As an end-to-end pipeline, our proposed approach provides: (1) the transformation of imagery from foggy to clear weather conditions using a domain transfer approach (correcting for poor visibility) and (2) semantically segmenting the scene using a competitive encoder-decoder architecture with low computational complexity (enabling real-time performance). Our approach incorporates RGB colour, depth and luminance images via distinct encoders with dense connectivity and features fusion to effectively exploit information from different inputs, which contributes to an optimal feature representation within the overall model. Using this architectural formulation with dense skip connections, our model achieves comparable performance to contemporary approaches at a fraction of the overall model complexity.
Learning new representations of 3D point clouds is an active research area in 3D vision, as the order-invariant point cloud structure still presents challenges to the design of neural network architectures. Recent works explored learning either global or local features or both for point clouds, however none of the earlier methods focused on capturing contextual shape information by analysing local orientation distribution of points. In this paper, we leverage on point orientation distributions around a point in order to obtain an expressive local neighborhood representation for point clouds. We achieve this by dividing the spherical neighborhood of a given point into predefined cone volumes, and statistics inside each volume are used as point features. In this way, a local patch can be represented by not only the selected point's nearest neighbors, but also considering a point density distribution defined along multiple orientations around the point. We are then able to construct an orientation distribution function (ODF) neural network that involves an ODFBlock which relies on mlp (multi-layer perceptron) layers. The new ODFNet model achieves state-of the-art accuracy for object classification on ModelNet40 and ScanObjectNN datasets, and segmentation on ShapeNet S3DIS datasets.
Semantic scene completion is the task of jointly estimating 3D geometry and semantics of objects and surfaces within a given extent. This is a particularly challenging task on real-world data that is sparse and occluded. We propose a scene segmentation network based on local Deep Implicit Functions as a novel learning-based method for scene completion. Unlike previous work on scene completion, our method produces a continuous scene representation that is not based on voxelization. We encode raw point clouds into a latent space locally and at multiple spatial resolutions. A global scene completion function is subsequently assembled from the localized function patches. We show that this continuous representation is suitable to encode geometric and semantic properties of extensive outdoor scenes without the need for spatial discretization (thus avoiding the trade-off between level of scene detail and the scene extent that can be covered). We train and evaluate our method on semantically annotated LiDAR scans from the Semantic KITTI dataset. Our experiments verify that our method generates a powerful representation that can be decoded into a dense 3D description of a given scene. The performance of our method surpasses the state of the art on the Semantic KITTI Scene Completion Benchmark in terms of geometric completion intersection-over-union (IoU).
Vector quantised variational autoencoders (VQ-VAE) are characterised by three main components: 1) encoding visual data, 2) assigning $k$ different vectors in the so-called embedding space, and 3) decoding the learnt features. While images are often represented in RGB colour space, the specific organisation of colours in other spaces also offer interesting features, e.g. CIE L*a*b* decorrelates chromaticity into opponent axes. In this article, we propose colour space conversion, a simple quasi-unsupervised task, to enforce a network learning structured representations. To this end, we trained several instances of VQ-VAE whose input is an image in one colour space, and its output in another, e.g. from RGB to CIE L*a*b* (in total five colour spaces were considered). We examined the finite embedding space of trained networks in order to disentangle the colour representation in VQ-VAE models. Our analysis suggests that certain vectors encode hue and others luminance information. We further evaluated the quality of reconstructed images at low-level using pixel-wise colour metrics, and at high-level by inputting them to image classification and scene segmentation networks. We conducted experiments in three benchmark datasets: ImageNet, COCO and CelebA. Our results show, with respect to the baseline network (whose input and output are RGB), colour conversion to decorrelated spaces obtains 1-2 Delta-E lower colour difference and 5-10% higher classification accuracy. We also observed that the learnt embedding space is easier to interpret in colour opponent models.