Knee OsteoArthritis (KOA) is a prevalent musculoskeletal disorder that causes decreased mobility in seniors. The lack of sufficient data in the medical field is always a challenge for training a learning model due to the high cost of labelling. At present, deep neural network training strongly depends on data augmentation to improve the model's generalization capability and avoid over-fitting. However, existing data augmentation operations, such as rotation, gamma correction, etc., are designed based on the data itself, which does not substantially increase the data diversity. In this paper, we proposed a novel approach based on the Vision Transformer (ViT) model with Selective Shuffled Position Embedding (SSPE) and a ROI-exchange strategy to obtain different input sequences as a method of data augmentation for early detection of KOA (KL-0 vs KL-2). More specifically, we fixed and shuffled the position embedding of ROI and non-ROI patches, respectively. Then, for the input image, we randomly selected other images from the training set to exchange their ROI patches and thus obtained different input sequences. Finally, a hybrid loss function was derived using different loss functions with optimized weights. Experimental results show that our proposed approach is a valid method of data augmentation as it can significantly improve the model's classification performance.
Existing 3D scene understanding tasks have achieved high performance on close-set benchmarks but fail to handle novel categories in real-world applications. To this end, we propose a Regional Point-Language Contrastive learning framework, namely RegionPLC, for open-world 3D scene understanding, which equips models trained on closed-set datasets with open-vocabulary recognition capabilities. We propose dense visual prompts to elicit region-level visual-language knowledge from 2D foundation models via captioning, which further allows us to build dense regional point-language associations. Then, we design a point-discriminative contrastive learning objective to enable point-independent learning from captions for dense scene understanding. We conduct extensive experiments on ScanNet, ScanNet200, and nuScenes datasets. Our RegionPLC significantly outperforms previous base-annotated 3D open-world scene understanding approaches by an average of 11.6\% and 6.6\% for semantic and instance segmentation, respectively. It also shows promising open-world results in absence of any human annotation with low training and inference costs. Code will be released.
Knee OsteoArthritis (KOA) is a prevalent musculoskeletal disorder that causes decreased mobility in seniors. The diagnosis provided by physicians is subjective, however, as it relies on personal experience and the semi-quantitative Kellgren-Lawrence (KL) scoring system. KOA has been successfully diagnosed by Computer-Aided Diagnostic (CAD) systems that use deep learning techniques like Convolutional Neural Networks (CNN). In this paper, we propose a novel Siamese-based network, and we introduce a new hybrid loss strategy for the early detection of KOA. The model extends the classical Siamese network by integrating a collection of Global Average Pooling (GAP) layers for feature extraction at each level. Then, to improve the classification performance, a novel training strategy that partitions each training batch into low-, medium- and high-confidence subsets, and a specific hybrid loss function are used for each new label attributed to each sample. The final loss function is then derived by combining the latter loss functions with optimized weights. Our test results demonstrate that our proposed approach significantly improves the detection performance.
In autonomous driving, Vehicle-Infrastructure Cooperative 3D Object Detection (VIC3D) makes use of multi-view cameras from both vehicles and traffic infrastructure, providing a global vantage point with rich semantic context of road conditions beyond a single vehicle viewpoint. Two major challenges prevail in VIC3D: 1) inherent calibration noise when fusing multi-view images, caused by time asynchrony across cameras; 2) information loss when projecting 2D features into 3D space. To address these issues, We propose a novel 3D object detection framework, Vehicles-Infrastructure Multi-view Intermediate fusion (VIMI). First, to fully exploit the holistic perspectives from both vehicles and infrastructure, we propose a Multi-scale Cross Attention (MCA) module that fuses infrastructure and vehicle features on selective multi-scales to correct the calibration noise introduced by camera asynchrony. Then, we design a Camera-aware Channel Masking (CCM) module that uses camera parameters as priors to augment the fused features. We further introduce a Feature Compression (FC) module with channel and spatial compression blocks to reduce the size of transmitted features for enhanced efficiency. Experiments show that VIMI achieves 15.61% overall AP_3D and 21.44% AP_BEV on the new VIC3D dataset, DAIR-V2X-C, significantly outperforming state-of-the-art early fusion and late fusion methods with comparable transmission cost.
For semantic segmentation in urban scene understanding, RGB cameras alone often fail to capture a clear holistic topology, especially in challenging lighting conditions. Thermal signal is an informative additional channel that can bring to light the contour and fine-grained texture of blurred regions in low-quality RGB image. Aiming at RGB-T (thermal) segmentation, existing methods either use simple passive channel/spatial-wise fusion for cross-modal interaction, or rely on heavy labeling of ambiguous boundaries for fine-grained supervision. We propose a Spatial-aware Demand-guided Recursive Meshing (SpiderMesh) framework that: 1) proactively compensates inadequate contextual semantics in optically-impaired regions via a demand-guided target masking algorithm; 2) refines multimodal semantic features with recursive meshing to improve pixel-level semantic analysis performance. We further introduce an asymmetric data augmentation technique M-CutOut, and enable semi-supervised learning to fully utilize RGB-T labels only sparsely available in practical use. Extensive experiments on MFNet and PST900 datasets demonstrate that SpiderMesh achieves new state-of-the-art performance on standard RGB-T segmentation benchmarks.
Effective BEV object detection on infrastructure can greatly improve traffic scenes understanding and vehicle-toinfrastructure (V2I) cooperative perception. However, cameras installed on infrastructure have various postures, and previous BEV detection methods rely on accurate calibration, which is difficult for practical applications due to inevitable natural factors (e.g., wind and snow). In this paper, we propose a Calibration-free BEV Representation (CBR) network, which achieves 3D detection based on BEV representation without calibration parameters and additional depth supervision. Specifically, we utilize two multi-layer perceptrons for decoupling the features from perspective view to front view and birdeye view under boxes-induced foreground supervision. Then, a cross-view feature fusion module matches features from orthogonal views according to similarity and conducts BEV feature enhancement with front view features. Experimental results on DAIR-V2X demonstrate that CBR achieves acceptable performance without any camera parameters and is naturally not affected by calibration noises. We hope CBR can serve as a baseline for future research addressing practical challenges of infrastructure perception.
A popular track of network compression approach is Quantization aware Training (QAT), which accelerates the forward pass during the neural network training and inference. However, not much prior efforts have been made to quantize and accelerate the backward pass during training, even though that contributes around half of the training time. This can be partly attributed to the fact that errors of low-precision gradients during backward cannot be amortized by the training objective as in the QAT setting. In this work, we propose to solve this problem by incorporating the gradients into the computation graph of the next training iteration via a hypernetwork. Various experiments on CIFAR-10 dataset with different CNN network architectures demonstrate that our hypernetwork-based approach can effectively reduce the negative effect of gradient quantization noise and successfully quantizes the gradients to INT4 with only 0.64 accuracy drop for VGG-16 on CIFAR-10.
Knee OsteoArthritis (KOA) is a prevalent musculoskeletal condition that impairs the mobility of senior citizens. The lack of sufficient data in the medical field is always a challenge for training a learning model due to the high cost of labelling. At present, Deep neural network training strongly depends on data augmentation to improve the model's generalization capability and avoid over-fitting. However, existing data augmentation operations, such as rotation, gamma correction, etc., are designed based on the original data, which does not substantially increase the data diversity. In this paper, we propose a learning model based on the convolutional Auto-Encoder and a hybrid loss strategy to generate new data for early KOA (KL-0 vs KL-2) diagnosis. Four hidden layers are designed among the encoder and decoder, which represent the key and unrelated features of each input, respectively. Then, two key feature vectors are exchanged to obtain the generated images. To do this, a hybrid loss function is derived using different loss functions with optimized weights to supervise the reconstruction and key-exchange learning. Experimental results show that the generated data are valid as they can significantly improve the model's classification performance.
In this paper, we investigate the uplink performance of cell-free (CF) extremely large-scale multiple-input-multipleoutput (XL-MIMO) systems, which is a promising technique for future wireless communications. More specifically, we consider the practical scenario with multiple base stations (BSs) and multiple user equipments (UEs). To this end, we derive exact achievable spectral efficiency (SE) expressions for any combining scheme. It is worth noting that we derive the closed-form SE expressions for the CF XL-MIMO with maximum ratio (MR) combining. Numerical results show that the SE performance of the CF XL-MIMO can be hugely improved compared with the small-cell XL-MIMO. It is interesting that a smaller antenna spacing leads to a higher correlation level among patch antennas. Finally, we prove that increasing the number of UE antennas may decrease the SE performance with MR combining.
Recent NLP literature has seen growing interest in improving model interpretability. Along this direction, we propose a trainable neural network layer that learns a global interaction graph between words and then selects more informative words using the learned word interactions. Our layer, we call WIGRAPH, can plug into any neural network-based NLP text classifiers right after its word embedding layer. Across multiple SOTA NLP models and various NLP datasets, we demonstrate that adding the WIGRAPH layer substantially improves NLP models' interpretability and enhances models' prediction performance at the same time.