Automatic interpretation on smartphone-captured chest X-ray (CXR) photographs is challenging due to the geometric distortion (projective transformation) caused by the non-ideal camera position. In this paper, we proposed an innovative deep learning-based Projective Transformation Rectification Network (PTRN) to automatically rectify such distortions by predicting the projective transformation matrix. PTRN is trained on synthetic data to avoid the expensive collection of natural data. Therefore, we proposed an innovative synthetic data framework that accounts for the visual attributes of natural photographs including screen, background, illuminations, and visual artifacts, and generate synthetic CXR photographs and projective transformation matrices as the ground-truth labels for training PTRN. Finally, smartphone-captured CXR photographs are automatically rectified by trained PTRN and interpreted by a classifier trained on high-quality digital CXRs to produce final interpretation results. In the CheXphoto CXR photograph interpretation competition released by the Stanford University Machine Learning Group, our approach achieves a huge performance improvement and won first place (ours 0.850, second-best 0.762, in AUC). A deeper analysis demonstrates that the use of PTRN successfully achieves the performance on CXR photographs to the same level as on digital CXRs, indicating PTRN can eliminate all negative impacts of projective transformation to the interpretation performance. Additionally, there are many real-world scenarios where distorted photographs have to be used for image classification, our PTRN can be used to solve those similar problems due to its generality design.
Humans tend to decompose a sentence into different parts like \textsc{sth do sth at someplace} and then fill each part with certain content. Inspired by this, we follow the \textit{principle of modular design} to propose a novel image captioner: learning to Collocate Visual-Linguistic Neural Modules (CVLNM). Unlike the \re{widely used} neural module networks in VQA, where the language (\ie, question) is fully observable, \re{the task of collocating visual-linguistic modules is more challenging.} This is because the language is only partially observable, for which we need to dynamically collocate the modules during the process of image captioning. To sum up, we make the following technical contributions to design and train our CVLNM: 1) \textit{distinguishable module design} -- \re{four modules in the encoder} including one linguistic module for function words and three visual modules for different content words (\ie, noun, adjective, and verb) and another linguistic one in the decoder for commonsense reasoning, 2) a self-attention based \textit{module controller} for robustifying the visual reasoning, 3) a part-of-speech based \textit{syntax loss} imposed on the module controller for further regularizing the training of our CVLNM. Extensive experiments on the MS-COCO dataset show that our CVLNM is more effective, \eg, achieving a new state-of-the-art 129.5 CIDEr-D, and more robust, \eg, being less likely to overfit to dataset bias and suffering less when fewer training samples are available. Codes are available at \url{https://github.com/GCYZSL/CVLMN}
Image-goal navigation is a challenging task, as it requires the agent to navigate to a target indicated by an image in a previously unseen scene. Current methods introduce diverse memory mechanisms which save navigation history to solve this task. However, these methods use all observations in the memory for generating navigation actions without considering which fraction of this memory is informative. To address this limitation, we present the MemoNav, a novel memory mechanism for image-goal navigation, which retains the agent's informative short-term memory and long-term memory to improve the navigation performance on a multi-goal task. The node features on the agent's topological map are stored in the short-term memory, as these features are dynamically updated. To aid the short-term memory, we also generate long-term memory by continuously aggregating the short-term memory via a graph attention module. The MemoNav retains the informative fraction of the short-term memory via a forgetting module based on a Transformer decoder and then incorporates this retained short-term memory and the long-term memory into working memory. Lastly, the agent uses the working memory for action generation. We evaluate our model on a new multi-goal navigation dataset. The experimental results show that the MemoNav outperforms the SoTA methods by a large margin with a smaller fraction of navigation history. The results also empirically show that our model is less likely to be trapped in a deadlock, which further validates that the MemoNav improves the agent's navigation efficiency by reducing redundant steps.
This paper tackles the problem of novel category discovery (NCD), which aims to discriminate unknown categories in large-scale image collections. The NCD task is challenging due to the closeness to the real-world scenarios, where we have only encountered some partial classes and images. Unlike other works on the NCD, we leverage the prototypes to emphasize the importance of category discrimination and alleviate the issue of missing annotations of novel classes. Concretely, we propose a novel adaptive prototype learning method consisting of two main stages: prototypical representation learning and prototypical self-training. In the first stage, we obtain a robust feature extractor, which could serve for all images with base and novel categories. This ability of instance and category discrimination of the feature extractor is boosted by self-supervised learning and adaptive prototypes. In the second stage, we utilize the prototypes again to rectify offline pseudo labels and train a final parametric classifier for category clustering. We conduct extensive experiments on four benchmark datasets and demonstrate the effectiveness and robustness of the proposed method with state-of-the-art performance.
Compositional Zero-Shot Learning (CZSL) aims to recognize unseen compositions formed from seen state and object during training. Since the same state may be various in the visual appearance while entangled with different objects, CZSL is still a challenging task. Some methods recognize state and object with two trained classifiers, ignoring the impact of the interaction between object and state; the other methods try to learn the joint representation of the state-object compositions, leading to the domain gap between seen and unseen composition sets. In this paper, we propose a novel Siamese Contrastive Embedding Network (SCEN) (Code: https://github.com/XDUxyLi/SCEN-master) for unseen composition recognition. Considering the entanglement between state and object, we embed the visual feature into a Siamese Contrastive Space to capture prototypes of them separately, alleviating the interaction between state and object. In addition, we design a State Transition Module (STM) to increase the diversity of training compositions, improving the robustness of the recognition model. Extensive experiments indicate that our method significantly outperforms the state-of-the-art approaches on three challenging benchmark datasets, including the recent proposed C-QGA dataset.
Online exams via video conference software like Zoom have been adopted in many schools due to COVID-19. While it is convenient, it is challenging for teachers to supervise online exams from simultaneously displayed student Zoom windows. In this paper, we propose iExam, an intelligent online exam monitoring and analysis system that can not only use face detection to assist invigilators in real-time student identification, but also be able to detect common abnormal behaviors (including face disappearing, rotating faces, and replacing with a different person during the exams) via a face recognition-based post-exam video analysis. To build such a novel system in its first kind, we overcome three challenges. First, we discover a lightweight approach to capturing exam video streams and analyzing them in real time. Second, we utilize the left-corner names that are displayed on each student's Zoom window and propose an improved OCR (optical character recognition) technique to automatically gather the ground truth for the student faces with dynamic positions. Third, we perform several experimental comparisons and optimizations to efficiently shorten the training and testing time required on teachers' PC. Our evaluation shows that iExam achieves high accuracy, 90.4% for real-time face detection and 98.4% for post-exam face recognition, while maintaining acceptable runtime performance. We have made iExam's source code available at https://github.com/VPRLab/iExam.
To achieve accurate and robust object detection in the real-world scenario, various forms of images are incorporated, such as color, thermal, and depth. However, multimodal data often suffer from the position shift problem, i.e., the image pair is not strictly aligned, making one object has different positions in different modalities. For the deep learning method, this problem makes it difficult to fuse multimodal features and puzzles the convolutional neural network (CNN) training. In this article, we propose a general multimodal detector named aligned region CNN (AR-CNN) to tackle the position shift problem. First, a region feature (RF) alignment module with adjacent similarity constraint is designed to consistently predict the position shift between two modalities and adaptively align the cross-modal RFs. Second, we propose a novel region of interest (RoI) jitter strategy to improve the robustness to unexpected shift patterns. Third, we present a new multimodal feature fusion method that selects the more reliable feature and suppresses the less useful one via feature reweighting. In addition, by locating bounding boxes in both modalities and building their relationships, we provide novel multimodal labeling named KAIST-Paired. Extensive experiments on 2-D and 3-D object detection, RGB-T, and RGB-D datasets demonstrate the effectiveness and robustness of our method.
Segmenting unseen objects is a crucial ability for the robot since it may encounter new environments during the operation. Recently, a popular solution is leveraging RGB-D features of large-scale synthetic data and directly applying the model to unseen real-world scenarios. However, even though depth data have fair generalization ability, the domain shift due to the Sim2Real gap is inevitable, which presents a key challenge to the unseen object instance segmentation (UOIS) model. To tackle this problem, we re-emphasize the adaptation process across Sim2Real domains in this paper. Specifically, we propose a framework to conduct the Fully Test-time RGB-D Embeddings Adaptation (FTEA) based on parameters of the BatchNorm layer. To construct the learning objective for test-time back-propagation, we propose a novel non-parametric entropy objective that can be implemented without explicit classification layers. Moreover, we design a cross-modality knowledge distillation module to encourage the information transfer during test time. The proposed method can be efficiently conducted with test-time images, without requiring annotations or revisiting the large-scale synthetic training data. Besides significant time savings, the proposed method consistently improves segmentation results on both overlap and boundary metrics, achieving state-of-the-art performances on two real-world RGB-D image datasets. We hope our work could draw attention to the test-time adaptation and reveal a promising direction for robot perception in unseen environments.
We propose an end-to-end image compression and analysis model with Transformers, targeting to the cloud-based image classification application. Instead of placing an existing Transformer-based image classification model directly after an image codec, we aim to redesign the Vision Transformer (ViT) model to perform image classification from the compressed features and facilitate image compression with the long-term information from the Transformer. Specifically, we first replace the patchify stem (i.e., image splitting and embedding) of the ViT model with a lightweight image encoder modelled by a convolutional neural network. The compressed features generated by the image encoder are injected convolutional inductive bias and are fed to the Transformer for image classification bypassing image reconstruction. Meanwhile, we propose a feature aggregation module to fuse the compressed features with the selected intermediate features of the Transformer, and feed the aggregated features to a deconvolutional neural network for image reconstruction. The aggregated features can obtain the long-term information from the self-attention mechanism of the Transformer and improve the compression performance. The rate-distortion-accuracy optimization problem is finally solved by a two-step training strategy. Experimental results demonstrate the effectiveness of the proposed model in both the image compression and the classification tasks.
Action quality assessment (AQA) from videos is a challenging vision task since the relation between videos and action scores is difficult to model. Thus, action quality assessment has been widely studied in the literature. Traditionally, AQA task is treated as a regression problem to learn the underlying mappings between videos and action scores. More recently, the method of uncertainty score distribution learning (USDL) made success due to the introduction of label distribution learning (LDL). But USDL does not apply to dataset with continuous labels and needs a fixed variance in training. In this paper, to address the above problems, we further develop Distribution Auto-Encoder (DAE). DAE takes both advantages of regression algorithms and label distribution learning (LDL).Specifically, it encodes videos into distributions and uses the reparameterization trick in variational auto-encoders (VAE) to sample scores, which establishes a more accurate mapping between videos and scores. Meanwhile, a combined loss is constructed to accelerate the training of DAE. DAE-MT is further proposed to deal with AQA on multi-task datasets. We evaluate our DAE approach on MTL-AQA and JIGSAWS datasets. Experimental results on public datasets demonstrate that our method achieves state-of-the-arts under the Spearman's Rank Correlation: 0.9449 on MTL-AQA and 0.73 on JIGSAWS.