Yifan Liu, Chunhua Shen, Changqian Yu, Jingdong Wang
For semantic segmentation, most existing real-time deep models trained with each frame independently may produce inconsistent results for a video sequence. Advanced methods take into considerations the correlations in the video sequence, e.g., by propagating the results to the neighboring frames using optical flow, or extracting the frame representations with other frames, which may lead to inaccurate results or unbalanced latency. In this work, we process efficient semantic video segmentation in a per-frame fashion during the inference process. Different from previous per-frame models, we explicitly consider the temporal consistency among frames as extra constraints during the training process and embed the temporal consistency into the segmentation network. Therefore, in the inference process, we can process each frame independently with no latency, and improve the temporal consistency with no extra computational cost and post-processing. We employ compact models for real-time execution. To narrow the performance gap between compact models and large models, new knowledge distillation methods are designed. Our results outperform previous keyframe based methods with a better trade-off between the accuracy and the inference speed on popular benchmarks, including the Cityscapes and Camvid. The temporal consistency is also improved compared with corresponding baselines which are trained with each frame independently. Code is available at: https://tinyurl.com/segment-video
Haokui Zhang, Chunhua Shen, Ying Li, Yuanzhouhan Cao, Yu Liu, Youliang Yan
Accuracy of depth estimation from static images has been significantly improved recently, by exploiting hierarchical features from deep convolutional neural networks (CNNs). Compared with static images, vast information exists among video frames and can be exploited to improve the depth estimation performance. In this work, we focus on exploring temporal information from monocular videos for depth estimation. Specifically, we take the advantage of convolutional long short-term memory (CLSTM) and propose a novel spatial-temporal CSLTM (ST-CLSTM) structure. Our ST-CLSTM structure can capture not only the spatial features but also the temporal correlations/consistency among consecutive video frames with negligible increase in computational cost. Additionally, in order to maintain the temporal consistency among the estimated depth frames, we apply the generative adversarial learning scheme and design a temporal consistency loss. The temporal consistency loss is combined with the spatial loss to update the model in an end-to-end fashion. By taking advantage of the temporal information, we build a video depth estimation framework that runs in real-time and generates visually pleasant results. Moreover, our approach is flexible and can be generalized to most existing depth estimation frameworks. Code is available at: https://tinyurl.com/STCLSTM
Xinlong Wang, Tao Kong, Chunhua Shen, Yuning Jiang, Lei Li
We present a new, embarrassingly simple approach to instance segmentation in images. Compared to many other dense prediction tasks, e.g., semantic segmentation, it is the arbitrary number of instances that have made instance segmentation much more challenging. In order to predict a mask for each instance, mainstream approaches either follow the 'detect-thensegment' strategy as used by Mask R-CNN, or predict category masks first then use clustering techniques to group pixels into individual instances. We view the task of instance segmentation from a completely new perspective by introducing the notion of "instance categories", which assigns categories to each pixel within an instance according to the instance's location and size, thus nicely converting instance mask segmentation into a classification-solvable problem. Now instance segmentation is decomposed into two classification tasks. We demonstrate a much simpler and flexible instance segmentation framework with strong performance, achieving on par accuracy with Mask R-CNN and outperforming recent singleshot instance segmenters in accuracy. We hope that this very simple and strong framework can serve as a baseline for many instance-level recognition tasks besides instance segmentation.
Weian Mao, Yongtao Ge, Chunhua Shen, Zhi Tian, Xinlong Wang, Zhibin Wang
We propose a human pose estimation framework that solves the task in the regression-based fashion. Unlike previous regression-based methods, which often fall behind those state-of-the-art methods, we formulate the pose estimation task into a sequence prediction problem that can effectively be solved by transformers. Our framework is simple and direct, bypassing the drawbacks of the heatmap-based pose estimation. Moreover, with the attention mechanism in transformers, our proposed framework is able to adaptively attend to the features most relevant to the target keypoints, which largely overcomes the feature misalignment issue of previous regression-based methods and considerably improves the performance. Importantly, our framework can inherently take advantages of the structured relationship between keypoints. Experiments on the MS-COCO and MPII datasets demonstrate that our method can significantly improve the state-of-the-art of regression-based pose estimation and perform comparably with the best heatmap-based pose estimation methods.
Weian Mao, Zhi Tian, Xinlong Wang, Chunhua Shen
We propose a fully convolutional multi-person pose estimation framework using dynamic instance-aware convolutions, termed FCPose. Different from existing methods, which often require ROI (Region of Interest) operations and/or grouping post-processing, FCPose eliminates the ROIs and grouping post-processing with dynamic instance-aware keypoint estimation heads. The dynamic keypoint heads are conditioned on each instance (person), and can encode the instance concept in the dynamically-generated weights of their filters. Moreover, with the strong representation capacity of dynamic convolutions, the keypoint heads in FCPose are designed to be very compact, resulting in fast inference and making FCPose have almost constant inference time regardless of the number of persons in the image. For example, on the COCO dataset, a real-time version of FCPose using the DLA-34 backbone infers about 4.5x faster than Mask R-CNN (ResNet-101) (41.67 FPS vs. 9.26FPS) while achieving improved performance. FCPose also offers better speed/accuracy trade-off than other state-of-the-art methods. Our experiment results show that FCPose is a simple yet effective multi-person pose estimation framework. Code is available at: https://git.io/AdelaiDet
Weian Mao, Yongtao Ge, Chunhua Shen, Zhi Tian, Xinlong Wang, Zhibin Wang, Anton van den Hengel
We propose a direct, regression-based approach to 2D human pose estimation from single images. We formulate the problem as a sequence prediction task, which we solve using a Transformer network. This network directly learns a regression mapping from images to the keypoint coordinates, without resorting to intermediate representations such as heatmaps. This approach avoids much of the complexity associated with heatmap-based approaches. To overcome the feature misalignment issues of previous regression-based methods, we propose an attention mechanism that adaptively attends to the features that are most relevant to the target keypoints, considerably improving the accuracy. Importantly, our framework is end-to-end differentiable, and naturally learns to exploit the dependencies between keypoints. Experiments on MS-COCO and MPII, two predominant pose-estimation datasets, demonstrate that our method significantly improves upon the state-of-the-art in regression-based pose estimation. More notably, ours is the first regression-based approach to perform favorably compared to the best heatmap-based pose estimation methods.
Bohan Zhuang, Lingqiao Liu, Mingkui Tan, Chunhua Shen, Ian Reid
In this paper, we seek to tackle a challenge in training low-precision networks: the notorious difficulty in propagating gradient through a low-precision network due to the non-differentiable quantization function. We propose a solution by training the low-precision network with a fullprecision auxiliary module. Specifically, during training, we construct a mix-precision network by augmenting the original low-precision network with the full precision auxiliary module. Then the augmented mix-precision network and the low-precision network are jointly optimized. This strategy creates additional full-precision routes to update the parameters of the low-precision model, thus making the gradient back-propagates more easily. At the inference time, we discard the auxiliary module without introducing any computational complexity to the low-precision network. We evaluate the proposed method on image classification and object detection over various quantization approaches and show consistent performance increase. In particular, we achieve near lossless performance to the full-precision model by using a 4-bit detector, which is of great practical value.
Zhi Tian, Xiangxiang Chu, Xiaoming Wang, Xiaolin Wei, Chunhua Shen
We present a simple yet effective fully convolutional one-stage 3D object detector for LiDAR point clouds of autonomous driving scenes, termed FCOS-LiDAR. Unlike the dominant methods that use the bird-eye view (BEV), our proposed detector detects objects from the range view (RV, a.k.a. range image) of the LiDAR points. Due to the range view's compactness and compatibility with the LiDAR sensors' sampling process on self-driving cars, the range view-based object detector can be realized by solely exploiting the vanilla 2D convolutions, departing from the BEV-based methods which often involve complicated voxelization operations and sparse convolutions. For the first time, we show that an RV-based 3D detector with standard 2D convolutions alone can achieve comparable performance to state-of-the-art BEV-based detectors while being significantly faster and simpler. More importantly, almost all previous range view-based detectors only focus on single-frame point clouds, since it is challenging to fuse multi-frame point clouds into a single range view. In this work, we tackle this challenging issue with a novel range view projection mechanism, and for the first time demonstrate the benefits of fusing multi-frame point clouds for a range-view based detector. Extensive experiments on nuScenes show the superiority of our proposed method and we believe that our work can be strong evidence that an RV-based 3D detector can compare favourably with the current mainstream BEV-based detectors.
Muzhi Zhu, Hengtao Li, Hao Chen, Chengxiang Fan, Weian Mao, Chenchen Jing, Yifan Liu, Chunhua Shen
Current closed-set instance segmentation models rely on pre-defined class labels for each mask during training and evaluation, largely limiting their ability to detect novel objects. Open-world instance segmentation (OWIS) models address this challenge by detecting unknown objects in a class-agnostic manner. However, previous OWIS approaches completely erase category information during training to keep the model's ability to generalize to unknown objects. In this work, we propose a novel training mechanism termed SegPrompt that uses category information to improve the model's class-agnostic segmentation ability for both known and unknown categories. In addition, the previous OWIS training setting exposes the unknown classes to the training set and brings information leakage, which is unreasonable in the real world. Therefore, we provide a new open-world benchmark closer to a real-world scenario by dividing the dataset classes into known-seen-unseen parts. For the first time, we focus on the model's ability to discover objects that never appear in the training set images. Experiments show that SegPrompt can improve the overall and unseen detection performance by 5.6% and 6.1% in AR on our new benchmark without affecting the inference efficiency. We further demonstrate the effectiveness of our method on existing cross-dataset transfer and strongly supervised settings, leading to 5.5% and 12.3% relative improvement.
Chunhua Shen, Hanxi Li
We study boosting algorithms from a new perspective. We show that the Lagrange dual problems of AdaBoost, LogitBoost and soft-margin LPBoost with generalized hinge loss are all entropy maximization problems. By looking at the dual problems of these boosting algorithms, we show that the success of boosting algorithms can be understood in terms of maintaining a better margin distribution by maximizing margins and at the same time controlling the margin variance.We also theoretically prove that, approximately, AdaBoost maximizes the average margin, instead of the minimum margin. The duality formulation also enables us to develop column generation based optimization algorithms, which are totally corrective. We show that they exhibit almost identical classification results to that of standard stage-wise additive boosting algorithms but with much faster convergence rates. Therefore fewer weak classifiers are needed to build the ensemble using our proposed optimization technique.
Peixian Chen, Mengdan Zhang, Yunhang Shen, Kekai Sheng, Yuting Gao, Xing Sun, Ke Li, Chunhua Shen
Vision transformers (ViTs) are changing the landscape of object detection approaches. A natural usage of ViTs in detection is to replace the CNN-based backbone with a transformer-based backbone, which is straightforward and effective, with the price of bringing considerable computation burden for inference. More subtle usage is the DETR family, which eliminates the need for many hand-designed components in object detection but introduces a decoder demanding an extra-long time to converge. As a result, transformer-based object detection can not prevail in large-scale applications. To overcome these issues, we propose a novel decoder-free fully transformer-based (DFFT) object detector, achieving high efficiency in both training and inference stages, for the first time. We simplify objection detection into an encoder-only single-level anchor-based dense prediction problem by centering around two entry points: 1) Eliminate the training-inefficient decoder and leverage two strong encoders to preserve the accuracy of single-level feature map prediction; 2) Explore low-level semantic features for the detection task with limited computational resources. In particular, we design a novel lightweight detection-oriented transformer backbone that efficiently captures low-level features with rich semantics based on a well-conceived ablation study. Extensive experiments on the MS COCO benchmark demonstrate that DFFT_SMALL outperforms DETR by 2.5% AP with 28% computation cost reduction and more than $10$x fewer training epochs. Compared with the cutting-edge anchor-based detector RetinaNet, DFFT_SMALL obtains over 5.5% AP gain while cutting down 70% computation cost.
Chunhua Shen, Peng Wang, Anton van den Hengel
Cascade classifiers are widely used in real-time object detection. Different from conventional classifiers that are designed for a low overall classification error rate, a classifier in each node of the cascade is required to achieve an extremely high detection rate and moderate false positive rate. Although there are a few reported methods addressing this requirement in the context of object detection, there is no a principled feature selection method that explicitly takes into account this asymmetric node learning objective. We provide such an algorithm here. We show a special case of the biased minimax probability machine has the same formulation as the linear asymmetric classifier (LAC) of \cite{wu2005linear}. We then design a new boosting algorithm that directly optimizes the cost function of LAC. The resulting totally-corrective boosting algorithm is implemented by the column generation technique in convex optimization. Experimental results on object detection verify the effectiveness of the proposed boosting algorithm as a node classifier in cascade object detection, and show performance better than that of the current state-of-the-art.
Yongbin Zheng, Chunhua Shen, Richard Hartley, Xinsheng Huang
Accurately detecting pedestrians in images plays a critically important role in many computer vision applications. Extraction of effective features is the key to this task. Promising features should be discriminative, robust to various variations and easy to compute. In this work, we present novel features, termed dense center-symmetric local binary patterns (CS-LBP) and pyramid center-symmetric local binary/ternary patterns (CS-LBP/LTP), for pedestrian detection. The standard LBP proposed by Ojala et al. \cite{c4} mainly captures the texture information. The proposed CS-LBP feature, in contrast, captures the gradient information and some texture information. Moreover, the proposed dense CS-LBP and the pyramid CS-LBP/LTP are easy to implement and computationally efficient, which is desirable for real-time applications. Experiments on the INRIA pedestrian dataset show that the dense CS-LBP feature with linear supporct vector machines (SVMs) is comparable with the histograms of oriented gradients (HOG) feature with linear SVMs, and the pyramid CS-LBP/LTP features outperform both HOG features with linear SVMs and the start-of-the-art pyramid HOG (PHOG) feature with the histogram intersection kernel SVMs. We also demonstrate that the combination of our pyramid CS-LBP feature and the PHOG feature could significantly improve the detection performance-producing state-of-the-art accuracy on the INRIA pedestrian dataset.
Chunhua Shen, Hanxi Li, Nick Barnes
Consideration of the primal and dual problems together leads to important new insights into the characteristics of boosting algorithms. In this work, we propose a general framework that can be used to design new boosting algorithms. A wide variety of machine learning problems essentially minimize a regularized risk functional. We show that the proposed boosting framework, termed CGBoost, can accommodate various loss functions and different regularizers in a totally-corrective optimization fashion. We show that, by solving the primal rather than the dual, a large body of totally-corrective boosting algorithms can actually be efficiently solved and no sophisticated convex optimization solvers are needed. We also demonstrate that some boosting algorithms like AdaBoost can be interpreted in our framework--even their optimization is not totally corrective. We empirically show that various boosting algorithms based on the proposed framework perform similarly on the UCIrvine machine learning datasets [1] that we have used in the experiments.
Bohan Zhuang, Qi Wu, Chunhua Shen, Ian Reid, Anton van den Hengel
Recognising objects according to a pre-defined fixed set of class labels has been well studied in the Computer Vision. There are a great many practical applications where the subjects that may be of interest are not known beforehand, or so easily delineated, however. In many of these cases natural language dialog is a natural way to specify the subject of interest, and the task achieving this capability (a.k.a, Referring Expression Comprehension) has recently attracted attention. To this end we propose a unified framework, the ParalleL AttentioN (PLAN) network, to discover the object in an image that is being referred to in variable length natural expression descriptions, from short phrases query to long multi-round dialogs. The PLAN network has two attention mechanisms that relate parts of the expressions to both the global visual content and also directly to object candidates. Furthermore, the attention mechanisms are recurrent, making the referring process visualizable and explainable. The attended information from these dual sources are combined to reason about the referred object. These two attention mechanisms can be trained in parallel and we find the combined system outperforms the state-of-art on several benchmarked datasets with different length language input, such as RefCOCO, RefCOCO+ and GuessWhat?!.
Yu Chen, Chunhua Shen, Hao Chen, Xiu-Shen Wei, Lingqiao Liu, Jian Yang
Landmark/pose estimation in single monocular images have received much effort in computer vision due to its important applications. It remains a challenging task when input images severe occlusions caused by, e.g., adverse camera views. Under such circumstances, biologically implausible pose predictions may be produced. In contrast, human vision is able to predict poses by exploiting geometric constraints of landmark point inter-connectivity. To address the problem, by incorporating priors about the structure of pose components, we propose a novel structure-aware fully convolutional network to implicitly take such priors into account during training of the deep network. Explicit learning of such constraints is typically challenging. Instead, inspired by how human identifies implausible poses, we design discriminators to distinguish the real poses from the fake ones (such as biologically implausible ones). If the pose generator G generates results that the discriminator fails to distinguish from real ones, the network successfully learns the priors. Training of the network follows the strategy of conditional Generative Adversarial Networks (GANs). The effectiveness of the proposed network is evaluated on three pose-related tasks: 2D single human pose estimation, 2D facial landmark estimation and 3D single human pose estimation. The proposed approach significantly outperforms the state-of-the-art methods and almost always generates plausible pose predictions, demonstrating the usefulness of implicit learning of structures using GANs.
Zhekai Chen, Wen Wang, Zhen Yang, Zeqing Yuan, Hao Chen, Chunhua Shen
We offer a novel approach to image composition, which integrates multiple input images into a single, coherent image. Rather than concentrating on specific use cases such as appearance editing (image harmonization) or semantic editing (semantic image composition), we showcase the potential of utilizing the powerful generative prior inherent in large-scale pre-trained diffusion models to accomplish generic image composition applicable to both scenarios. We observe that the pre-trained diffusion models automatically identify simple copy-paste boundary areas as low-density regions during denoising. Building on this insight, we propose to optimize the composed image towards high-density regions guided by the diffusion prior. In addition, we introduce a novel maskguided loss to further enable flexible semantic image composition. Extensive experiments validate the superiority of our approach in achieving generic zero-shot image composition. Additionally, our approach shows promising potential in various tasks, such as object removal and multiconcept customization.
Yuanzhouhan Cao, Zifeng Wu, Chunhua Shen
Depth estimation from single monocular images is a key component of scene understanding and has benefited largely from deep convolutional neural networks (CNN) recently. In this article, we take advantage of the recent deep residual networks and propose a simple yet effective approach to this problem. We formulate depth estimation as a pixel-wise classification task. Specifically, we first discretize the continuous depth values into multiple bins and label the bins according to their depth range. Then we train fully convolutional deep residual networks to predict the depth label of each pixel. Performing discrete depth label classification instead of continuous depth value regression allows us to predict a confidence in the form of probability distribution. We further apply fully-connected conditional random fields (CRF) as a post processing step to enforce local smoothness interactions, which improves the results. We evaluate our approach on both indoor and outdoor datasets and achieve state-of-the-art performance.
Guosheng Lin, Chunhua Shen, Anton van den Hengel
Embedding image features into a binary Hamming space can improve both the speed and accuracy of large-scale query-by-example image retrieval systems. Supervised hashing aims to map the original features to compact binary codes in a manner which preserves the label-based similarities of the original data. Most existing approaches apply a single form of hash function, and an optimization process which is typically deeply coupled to this specific form. This tight coupling restricts the flexibility of those methods, and can result in complex optimization problems that are difficult to solve. In this work we proffer a flexible yet simple framework that is able to accommodate different types of loss functions and hash functions. The proposed framework allows a number of existing approaches to hashing to be placed in context, and simplifies the development of new problem-specific hashing methods. Our framework decomposes the into two steps: binary code (hash bits) learning, and hash function learning. The first step can typically be formulated as a binary quadratic problem, and the second step can be accomplished by training standard binary classifiers. For solving large-scale binary code inference, we show how to ensure that the binary quadratic problems are submodular such that an efficient graph cut approach can be used. To achieve efficiency as well as efficacy on large-scale high-dimensional data, we propose to use boosted decision trees as the hash functions, which are nonlinear, highly descriptive, and very fast to train and evaluate. Experiments demonstrate that our proposed method significantly outperforms most state-of-the-art methods, especially on high-dimensional data.
Lingqiao Liu, Chunhua Shen, Lei Wang, Anton van den Hengel, Chao Wang
Deriving from the gradient vector of a generative model of local features, Fisher vector coding (FVC) has been identified as an effective coding method for image classification. Most, if not all, % FVC implementations employ the Gaussian mixture model (GMM) to characterize the generation process of local features. This choice has shown to be sufficient for traditional low dimensional local features, e.g., SIFT; and typically, good performance can be achieved with only a few hundred Gaussian distributions. However, the same number of Gaussians is insufficient to model the feature space spanned by higher dimensional local features, which have become popular recently. In order to improve the modeling capacity for high dimensional features, it turns out to be inefficient and computationally impractical to simply increase the number of Gaussians. In this paper, we propose a model in which each local feature is drawn from a Gaussian distribution whose mean vector is sampled from a subspace. With certain approximation, this model can be converted to a sparse coding procedure and the learning/inference problems can be readily solved by standard sparse coding methods. By calculating the gradient vector of the proposed model, we derive a new fisher vector encoding strategy, termed Sparse Coding based Fisher Vector Coding (SCFVC). Moreover, we adopt the recently developed Deep Convolutional Neural Network (CNN) descriptor as a high dimensional local feature and implement image classification with the proposed SCFVC. Our experimental evaluations demonstrate that our method not only significantly outperforms the traditional GMM based Fisher vector encoding but also achieves the state-of-the-art performance in generic object recognition, indoor scene, and fine-grained image classification problems.