The advent of AI and ML algorithms has led to opportunities as well as challenges. In this paper, we provide an overview of bias and fairness issues that arise with the use of ML algorithms. We describe the types and sources of data bias, and discuss the nature of algorithmic unfairness. This is followed by a review of fairness metrics in the literature, discussion of their limitations, and a description of de-biasing (or mitigation) techniques in the model life cycle.
Unsupervised domain adaptation (UDA) aims to solve the problem of knowledge transfer from labeled source domain to unlabeled target domain. Recently, many domain adaptation (DA) methods use centroid to align the local distribution of different domains, that is, to align different classes. This improves the effect of domain adaptation, but domain differences exist not only between classes, but also between samples. This work rethinks what is the alignment between different domains, and studies how to achieve the real alignment between different domains. Previous DA methods only considered one distribution feature of aligned samples, such as full distribution or local distribution. In addition to aligning the global distribution, the real domain adaptation should also align the meso distribution and the micro distribution. Therefore, this study propose a double classifier method based on high confidence label (DCP). By aligning the centroid and the distribution between centroid and sample of different classifiers, the meso and micro distribution alignment of different domains is realized. In addition, in order to reduce the chain error caused by error marking, This study propose a high confidence marking method to reduce the marking error. To verify its versatility, this study evaluates DCP on digital recognition and target recognition data sets. The results show that our method achieves state-of-the-art results on most of the current domain adaptation benchmark datasets.
Human-Object Interaction (HOI) detection devotes to learn how humans interact with surrounding objects. Latest end-to-end HOI detectors are short of relation reasoning, which leads to inability to learn HOI-specific interactive semantics for predictions. In this paper, we therefore propose novel relation reasoning for HOI detection. We first present a progressive Relation-aware Frame, which brings a new structure and parameter sharing pattern for interaction inference. Upon the frame, an Interaction Intensifier Module and a Correlation Parsing Module are carefully designed, where: a) interactive semantics from humans can be exploited and passed to objects to intensify interactions, b) interactive correlations among humans, objects and interactions are integrated to promote predictions. Based on modules above, we construct an end-to-end trainable framework named Relation Reasoning Network (abbr. RR-Net). Extensive experiments show that our proposed RR-Net sets a new state-of-the-art on both V-COCO and HICO-DET benchmarks and improves the baseline about 5.5% and 9.8% relatively, validating that this first effort in exploring relation reasoning and integrating interactive semantics has brought obvious improvement for end-to-end HOI detection.
Graph neural networks (GNN) have been ubiquitous in graph learning tasks such as node classification. Most of GNN methods update the node embedding iteratively by aggregating its neighbors' information. However, they often suffer from negative disturbance, due to edges connecting nodes with different labels. One approach to alleviate this negative disturbance is to use attention, but current attention always considers feature similarity and suffers from the lack of supervision. In this paper, we consider the label dependency of graph nodes and propose a decoupling attention mechanism to learn both hard and soft attention. The hard attention is learned on labels for a refined graph structure with fewer inter-class edges. Its purpose is to reduce the aggregation's negative disturbance. The soft attention is learned on features maximizing the information gain by message passing over better graph structures. Moreover, the learned attention guides the label propagation and the feature propagation. Extensive experiments are performed on five well-known benchmark graph datasets to verify the effectiveness of the proposed method.
The Low frequency analysis and recording (LOFAR) spectrum is one of the key features of the under water target, which can be used for underwater target recognition. However, the underwater environment noise is complicated and the signal-to-noise ratio of the underwater target is rather low, which introduces the breakpoints to the LOFAR spectrum and thus hinders the underwater target recognition. To overcome this issue and to further improve the recognition performance, we adopt a deep learning approach for underwater target recognition and propose a LOFAR spectrum enhancement (LSE)-based underwater target recognition scheme, which consists of preprocessing, offline training, and online testing. In preprocessing, a LOFAR spectrum enhancement based on multi-step decision algorithm is specifically designed to recover the breakpoints in LOFAR spectrum. In offline training, we then adopt the enhanced LOFAR spectrum as the input of convolutional neural network (CNN) and develop a LOFAR-based CNN (LOFAR-CNN) for online recognition. Taking advantage of the powerful capability of CNN in feature extraction, the proposed LOFAR-CNN can further improve the recognition accuracy. Finally, extensive simulation results demonstrate that the LOFAR-CNN network can achieve a recognition accuracy of $95.22\%$, which outperforms the state-of-the-art methods.
Channel Pruning has been long adopted for compressing CNNs, which significantly reduces the overall computation. Prior works implement channel pruning in an unexplainable manner, which tends to reduce the final classification errors while failing to consider the internal influence of each channel. In this paper, we conduct channel pruning in a white box. Through deep visualization of feature maps activated by different channels, we observe that different channels have a varying contribution to different categories in image classification. Inspired by this, we choose to preserve channels contributing to most categories. Specifically, to model the contribution of each channel to differentiating categories, we develop a class-wise mask for each channel, implemented in a dynamic training manner w.r.t. the input image's category. On the basis of the learned class-wise mask, we perform a global voting mechanism to remove channels with less category discrimination. Lastly, a fine-tuning process is conducted to recover the performance of the pruned model. To our best knowledge, it is the first time that CNN interpretability theory is considered to guide channel pruning. Extensive experiments demonstrate the superiority of our White-Box over many state-of-the-arts. For instance, on CIFAR-10, it reduces 65.23% FLOPs with even 0.62% accuracy improvement for ResNet-110. On ILSVRC-2012, White-Box achieves a 45.6% FLOPs reduction with only a small loss of 0.83% in the top-1 accuracy for ResNet-50. Code, training logs and pruned models are anonymously at https://github.com/zyxxmu/White-Box.
Virtual fitting room is a challenging task yet useful feature for e-commerce platforms and fashion designers. Existing works can only detect very few types of fashion items. Besides they did poorly in changing the texture and style of the selected fashion items. In this project, we propose a novel approach to address this problem. We firstly used Mask R-CNN to find the regions of different fashion items, and secondly used Neural Style Transfer to change the style of the selected fashion items. The dataset we used is composed of images from PaperDoll dataset and annotations provided by eBay's ModaNet. We trained 8 models and our best model massively outperformed baseline models both quantitatively and qualitatively, with 68.72% mAP, 0.2% ASDR.
Weakly-supervised temporal action localization (WS-TAL) aims to localize actions in untrimmed videos with only video-level labels. Most existing models follow the "localization by classification" procedure: locate temporal regions contributing most to the video-level classification. Generally, they process each snippet (or frame) individually and thus overlook the fruitful temporal context relation. Here arises the single snippet cheating issue: "hard" snippets are too vague to be classified. In this paper, we argue that learning by comparing helps identify these hard snippets and we propose to utilize snippet Contrastive learning to Localize Actions, CoLA for short. Specifically, we propose a Snippet Contrast (SniCo) Loss to refine the hard snippet representation in feature space, which guides the network to perceive precise temporal boundaries and avoid the temporal interval interruption. Besides, since it is infeasible to access frame-level annotations, we introduce a Hard Snippet Mining algorithm to locate the potential hard snippets. Substantial analyses verify that this mining strategy efficaciously captures the hard snippets and SniCo Loss leads to more informative feature representation. Extensive experiments show that CoLA achieves state-of-the-art results on THUMOS'14 and ActivityNet v1.2 datasets.
Noise injection-based regularization, such as Dropout, has been widely used in image domain to improve the performance of deep neural networks (DNNs). However, efficient regularization in the point cloud domain is rarely exploited, and most of the state-of-the-art works focus on data augmentation-based regularization. In this paper, we, for the first time, perform systematic investigation on noise injection-based regularization for point cloud-domain DNNs. To be specific, we propose a series of regularization techniques, namely DropFeat, DropPoint and DropCluster, to perform noise injection on the point feature maps at the feature level, point level and cluster level, respectively. We also empirically analyze the impacts of different factors, including dropping rate, cluster size and dropping position, to obtain useful insights and general deployment guidelines, which can facilitate the adoption of our approaches across different datasets and DNN architectures. We evaluate our proposed approaches on various DNN models for different point cloud processing tasks. Experimental results show our approaches enable significant performance improvement. Notably, our DropCluster brings 1.5%, 1.3% and 0.8% higher overall accuracy for PointNet, PointNet++ and DGCNN, respectively, on ModelNet40 shape classification dataset. On ShapeNet part segmentation dataset, DropCluster brings 0.5%, 0.5% and 0.2% mean Intersection-over-union (IoU) increase for PointNet, PointNet++ and DGCNN, respectively. On S3DIS semantic segmentation dataset, DropCluster improves the mean IoU of PointNet, PointNet++ and DGCNN by 3.2%, 2.9% and 3.7%, respectively. Meanwhile, DropCluster also enables the overall accuracy increase for these three popular backbone DNNs by 2.4%, 2.2% and 1.8%, respectively.
Binary neural networks (BNNs) have received increasing attention due to their superior reductions of computation and memory. Most existing works focus on either lessening the quantization error by minimizing the gap between the full-precision weights and their binarization or designing a gradient approximation to mitigate the gradient mismatch, while leaving the "dead weights" untouched. This leads to slow convergence when training BNNs. In this paper, for the first time, we explore the influence of "dead weights" which refer to a group of weights that are barely updated during the training of BNNs, and then introduce rectified clamp unit (ReCU) to revive the "dead weights" for updating. We prove that reviving the "dead weights" by ReCU can result in a smaller quantization error. Besides, we also take into account the information entropy of the weights, and then mathematically analyze why the weight standardization can benefit BNNs. We demonstrate the inherent contradiction between minimizing the quantization error and maximizing the information entropy, and then propose an adaptive exponential scheduler to identify the range of the "dead weights". By considering the "dead weights", our method offers not only faster BNN training, but also state-of-the-art performance on CIFAR-10 and ImageNet, compared with recent methods. Code can be available at [this https URL](https://github.com/z-hXu/ReCU).