KD-VLP: Improving End-to-End Vision-and-Language Pretraining with Object Knowledge Distillation

Self-supervised vision-and-language pretraining (VLP) aims to learn transferable multi-modal representations from large-scale image-text data and to achieve strong performances on a broad scope of vision-language tasks after finetuning. Previous mainstream VLP approaches typically adopt a two-step strategy relying on external object detectors to encode images in a multi-modal Transformer framework, which suffer from restrictive object concept space, limited image context and inefficient computation. In this paper, we propose an object-aware end-to-end VLP framework, which directly feeds image grid features from CNNs into the Transformer and learns the multi-modal representations jointly. More importantly, we propose to perform object knowledge distillation to facilitate learning cross-modal alignment at different semantic levels. To achieve that, we design two novel pretext tasks by taking object features and their semantic labels from external detectors as supervision: 1.) Object-guided masked vision modeling task focuses on enforcing object-aware representation learning in the multi-modal Transformer; 2.) Phrase-region alignment task aims to improve cross-modal alignment by utilizing the similarities between noun phrases and object labels in the linguistic space. Extensive experiments on a wide range of vision-language tasks demonstrate the efficacy of our proposed framework, and we achieve competitive or superior performances over the existing pretraining strategies. The code is available in supplementary materials.

Update in Unit Gradient

In Machine Learning, optimization mostly has been done by using a gradient descent method to find the minimum value of the loss. However, especially in deep learning, finding a global minimum from a nonconvex loss function across a high dimensional space is an extraordinarily difficult task. Recently, a generalization learning algorithm, Sharpness-Aware Minimization (SAM), has made a great success in image classification task. Despite the great performance in creating convex space, proper direction leading by SAM is still remained unclear. We, thereby, propose a creating a Unit Vector space in SAM, which not only consisted of the mathematical instinct in linear algebra but also kept the advantages of adaptive gradient algorithm. Moreover, applying SAM in unit gradient brings models competitive performances in image classification datasets, such as CIFAR - {10, 100}. The experiment showed that it performed even better and more robust than SAM.

ElePose: Unsupervised 3D Human Pose Estimation by Predicting Camera Elevation and Learning Normalizing Flows on 2D Poses

Human pose estimation from single images is a challenging problem that is typically solved by supervised learning. Unfortunately, labeled training data does not yet exist for many human activities since 3D annotation requires dedicated motion capture systems. Therefore, we propose an unsupervised approach that learns to predict a 3D human pose from a single image while only being trained with 2D pose data, which can be crowd-sourced and is already widely available. To this end, we estimate the 3D pose that is most likely over random projections, with the likelihood estimated using normalizing flows on 2D poses. While previous work requires strong priors on camera rotations in the training data set, we learn the distribution of camera angles which significantly improves the performance. Another part of our contribution is to stabilize training with normalizing flows on high-dimensional 3D pose data by first projecting the 2D poses to a linear subspace. We outperform the state-of-the-art unsupervised human pose estimation methods on the benchmark datasets Human3.6M and MPI-INF-3DHP in many metrics.

MiNet: A Convolutional Neural Network for Identifying and Categorising Minerals

Identification of minerals in the field is a task that is wrought with many challenges. Traditional approaches are prone to errors where there is no enough experience and expertise. Several existing techniques mainly make use of features of the minerals under a microscope and tend to favour a manual feature extraction pipeline. Deep learning methods can help overcome some of these hurdles and provide simple and effective ways to identify minerals. In this paper, we present an algorithm for identifying minerals from hand specimen images. Using a Convolutional Neural Network (CNN), we develop a single-label image classification model to identify and categorise seven classes of minerals. Experiments conducted using real-world datasets show that the model achieves an accuracy of 90.75%.

Generative Models for Multi-Illumination Color Constancy

In this paper, the aim is multi-illumination color constancy. However, most of the existing color constancy methods are designed for single light sources. Furthermore, datasets for learning multiple illumination color constancy are largely missing. We propose a seed (physics driven) based multi-illumination color constancy method. GANs are exploited to model the illumination estimation problem as an image-to-image domain translation problem. Additionally, a novel multi-illumination data augmentation method is proposed. Experiments on single and multi-illumination datasets show that our methods outperform sota methods.

Multi-Expert Adversarial Attack Detection in Person Re-identification Using Context Inconsistency

The success of deep neural networks (DNNs) haspromoted the widespread applications of person re-identification (ReID). However, ReID systems inherit thevulnerability of DNNs to malicious attacks of visually in-conspicuous adversarial perturbations. Detection of adver-sarial attacks is, therefore, a fundamental requirement forrobust ReID systems. In this work, we propose a Multi-Expert Adversarial Attack Detection (MEAAD) approach toachieve this goal by checking context inconsistency, whichis suitable for any DNN-based ReID systems. Specifically,three kinds of context inconsistencies caused by adversar-ial attacks are employed to learn a detector for distinguish-ing the perturbed examples, i.e., a) the embedding distancesbetween a perturbed query person image and its top-K re-trievals are generally larger than those between a benignquery image and its top-K retrievals, b) the embedding dis-tances among the top-K retrievals of a perturbed query im-age are larger than those of a benign query image, c) thetop-K retrievals of a benign query image obtained with mul-tiple expert ReID models tend to be consistent, which isnot preserved when attacks are present. Extensive exper-iments on the Market1501 and DukeMTMC-ReID datasetsshow that, as the first adversarial attack detection approachfor ReID,MEAADeffectively detects various adversarial at-tacks and achieves high ROC-AUC (over 97.5%).

Consistency Regularization with Generative Adversarial Networks for Semi-Supervised Image Classification

Generative Adversarial Networks (GANs) based semi-supervised learning (SSL) approaches are shown to improve classification performance by utilizing a large number of unlabeled samples in conjunction with limited labeled samples. However, their performance still lags behind the state-of-the-art non-GAN based SSL approaches. One main reason we identify is the lack of consistency in class probability predictions on the same image under local perturbations. This problem was addressed in the past in a generic setting using the label consistency regularization, which enforces the class probability predictions for an input image to be unchanged under various semantic-preserving perturbations. In this work, we incorporate the consistency regularization in the vanilla semi-GAN to address this critical limitation. In particular, we present a new composite consistency regularization method which, in spirit, combines two well-known consistency-based techniques -- Mean Teacher and Interpolation Consistency Training. We demonstrate the efficacy of our approach on two SSL image classification benchmark datasets, SVHN and CIFAR-10. Our experiments show that this new composite consistency regularization based semi-GAN significantly improves its performance and achieves new state-of-the-art performance among GAN-based SSL approaches.

Hyperspectral Image Restoration via Multi-mode and Double-weighted Tensor Nuclear Norm Minimization

Tensor nuclear norm (TNN) induced by tensor singular value decomposition plays an important role in hyperspectral image (HSI) restoration tasks. In this letter, we first consider three inconspicuous but crucial phenomenons in TNN. In the Fourier transform domain of HSIs, different frequency components contain different information; different singular values of each frequency component also represent different information. The two physical phenomenons lie not only in the spectral dimension but also in the spatial dimensions. Then, to improve the capability and flexibility of TNN for HSI restoration, we propose a multi-mode and double-weighted TNN based on the above three crucial phenomenons. It can adaptively shrink the frequency components and singular values according to their physical meanings in all modes of HSIs. In the framework of the alternating direction method of multipliers, we design an effective alternating iterative strategy to optimize our proposed model. Restoration experiments on both synthetic and real HSI datasets demonstrate their superiority against related methods.

CA-Net: Comprehensive Attention Convolutional Neural Networks for Explainable Medical Image Segmentation

Accurate medical image segmentation is essential for diagnosis and treatment planning of diseases. Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance for automatic medical image segmentation. However, they are still challenged by complicated conditions where the segmentation target has large variations of position, shape and scale, and existing CNNs have a poor explainability that limits their application to clinical decisions. In this work, we make extensive use of multiple attentions in a CNN architecture and propose a comprehensive attention-based CNN (CA-Net) for more accurate and explainable medical image segmentation that is aware of the most important spatial positions, channels and scales at the same time. In particular, we first propose a joint spatial attention module to make the network focus more on the foreground region. Then, a novel channel attention module is proposed to adaptively recalibrate channel-wise feature responses and highlight the most relevant feature channels. Also, we propose a scale attention module implicitly emphasizing the most salient feature maps among multiple scales so that the CNN is adaptive to the size of an object. Extensive experiments on skin lesion segmentation from ISIC 2018 and multi-class segmentation of fetal MRI found that our proposed CA-Net significantly improved the average segmentation Dice score from 87.77% to 92.08% for skin lesion, 84.79% to 87.08% for the placenta and 93.20% to 95.88% for the fetal brain respectively compared with U-Net. It reduced the model size to around 15 times smaller with close or even better accuracy compared with state-of-the-art DeepLabv3+. In addition, it has a much higher explainability than existing networks by visualizing the attention weight maps. Our code is available at https://github.com/HiLab-git/CA-Net

Gaussian-Hermite Moment Invariants of General Vector Functions to Rotation-Affine Transform

With the development of data acquisition technology, multi-channel data is collected and widely used in many fields. Most of them can be expressed as various types of vector functions. Feature extraction of vector functions for identifying certain patterns of interest is a critical but challenging task. In this paper, we focus on constructing moment invariants of general vector functions. Specifically, we define rotation-affine transform to describe real deformations of general vector functions, and then design a structural frame to systematically generate Gaussian-Hermite moment invariants to this transform model. This is the first time that a uniform frame has been proposed in the literature to construct orthogonal moment invariants of general vector functions. Given a certain type of multi-channel data, we demonstrate how to utilize the new method to derive all possible invariants and to eliminate various dependences among them. For RGB images, 2D and 3D flow fields, we obtain the complete and independent sets of the invariants with low orders and low degrees. Based on synthetic and popular datasets of vector-valued data, the experiments are carried out to evaluate the stability and discriminability of these invariants, and also their robustness to noise. The results clearly show that the moment invariants proposed in our paper have better performance than other previously used moment invariants of vector functions in RGB image classification, vortex detection in 2D vector fields and template matching for 3D flow fields.