Inspired by human neurological structures for action anticipation, we present an action anticipation model that enables the prediction of plausible future actions by forecasting both the visual and temporal future. In contrast to current state-of-the-art methods which first learn a model to predict future video features and then perform action anticipation using these features, the proposed framework jointly learns to perform the two tasks, future visual and temporal representation synthesis, and early action anticipation. The joint learning framework ensures that the predicted future embeddings are informative to the action anticipation task. Furthermore, through extensive experimental evaluations we demonstrate the utility of using both visual and temporal semantics of the scene, and illustrate how this representation synthesis could be achieved through a recurrent Generative Adversarial Network (GAN) framework. Our model outperforms the current state-of-the-art methods on multiple datasets: UCF101, UCF101-24, UT-Interaction and TV Human Interaction.

/pdf/predicting-the-future-a-jointly-learnt-model-for-action-546fs93wzk.pdf

Predicting the Future: A Jointly Learnt Model for Action Anticipation

Defect detection on solid wood surface has two main problems: (1) the real-time performance of the available methods are poor despite good detection accuracy, and (2) the defect extraction process is complicated. Here, we propose a mixed, fully convolutional neural network (Mix-FCN) to detect the location of wood defects and classify the types of defects from the wood surface images automatically. The images were collected first by a data acquisition device developed in our laboratory. We then employed TensorFlow and Python language to construct a VGG16 model. We used two kinds of datasets (dataset1 and dataset2) to maximize the limited, collected data and enable the Mix-FCN to converge rapidly during training. The weights of the filters in front of the Mix-FCN during training were initialized from the trained VGG16 model. The weights of the VGG16 net were learned by dataset1. Our model was trained, validated, and tested by dataset 2. Overall classification accuracy (OCA), pixel accuracy (PA), mean intersection over union, detection rate, missing alarm, false alarm rate, and precision were used to evaluate the network, and the performance was good based on the seven evaluation indicators. We achieved 99.14% OCA and 91.31% PA, and a batch of 50 images required only 0.368 s of detection time. Our proposed method has better accuracy and less detection time compared to the previous methods of wood detection.

/pdf/a-fully-convolutional-neural-network-for-wood-defect-455fmter73.pdf

A Fully Convolutional Neural Network for Wood Defect Location and Identification

In this paper, we study how to make unsupervised cross-modal hashing (CMH) benefit from contrastive learning (CL) by overcoming two challenges. To be exact, i) to address the performance degradation issue caused by binary optimization for hashing, we propose a novel momentum optimizer that performs hashing operation learnable in CL, thus making on-the-shelf deep cross-modal hashing possible. In other words, our method does not involve binary-continuous relaxation like most existing methods, thus enjoying better retrieval performance; ii) to alleviate the influence brought by false-negative pairs (FNPs), we propose a Cross-modal Ranking Learning loss (CRL) which utilizes the discrimination from all instead of only the hard negative pairs, where FNP refers to the within-class pairs that wrongly treated as negative pairs. Thanks to such a global strategy, CRL endows our method with better performance because CRL will not overuse the FNPs while ignoring the true-negative pairs. To the best of our knowledge, the proposed method could be one of the first successful contrastive hashing methods. To demonstrate the effectiveness of the proposed method, we carry out experiments on five widely-used datasets compared with 15 state-of-the-art methods. 

Unsupervised Contrastive Cross-modal Hashing

In this paper, we study how to make unsupervised cross-modal hashing (CMH) benefit from contrastive learning (CL) by overcoming two challenges. To be exact, i) to address the performance degradation issue caused by binary optimization for hashing, we propose a novel momentum optimizer that performs hashing operation learnable in CL, thus making on-the-shelf deep cross-modal hashing possible. In other words, our method does not involve binary-continuous relaxation like most existing methods, thus enjoying better retrieval performance; ii) to alleviate the influence brought by false-negative pairs (FNPs), we propose a Cross-modal Ranking Learning loss (CRL) which utilizes the discrimination from all instead of only the hard negative pairs, where FNP refers to the within-class pairs that were wrongly treated as negative pairs. Thanks to such a global strategy, CRL endows our method with better performance because CRL will not overuse the FNPs while ignoring the true-negative pairs. To the best of our knowledge, the proposed method could be one of the first successful contrastive hashing methods. To demonstrate the effectiveness of the proposed method, we carry out experiments on five widely-used datasets compared with 13 state-of-the-art methods. The code is available at https://github.com/penghu-cs/UCCH.

Unsupervised Contrastive Cross-Modal Hashing

Automatic polyp recognition in endoscopic images is challenging because of the low contrast between polyps and the surrounding area, the fuzzy and irregular polyp borders, and varying imaging light conditions. In this article, we propose a novel densely connected convolutional network with “unbalanced discriminant (UD)” loss and “category sensitive (CS)” loss (DenseNet-UDCS) for the task. We first utilize densely connected convolutional network (DenseNet) as the basic framework to conduct end-to-end polyp recognition task. Then, the proposed dual constraints, UD loss and CS loss, are simultaneously incorporated into the DenseNet model to calculate discriminative and suitable image features. The UD loss in our network effectively captures classification errors from both majority and minority categories to deal with the strong data imbalance of polyp images and normal ones. The CS loss imposes the ratio of intraclass and interclass variations in the deep feature learning process to enable features with large interclass variation and small intraclass compactness. With the joint supervision of UD loss and CS loss, a robust DenseNet-UDCS model is trained to recognize polyps from endoscopic images. The experimental results achieved polyp recognition accuracy of 93.19%, showing that the proposed DenseNet-UDCS can accurately characterize the endoscopic images and recognize polyps from the images. In addition, our DenseNet-UDCS model is superior in detection accuracy in comparison with state-of-the-art polyp recognition methods. Note to Practitioners —Wireless capsule endoscopy (WCE) is a crucial diagnostic tool for polyp detection and therapeutic monitoring, thanks to its noninvasive, user-friendly, and nonpainful properties. A challenge in harnessing the enormous potential of the WCE to benefit the gastrointestinal (GI) patients is that it requires clinicians to analyze a huge number of images (about 50 000 images for each patient). We propose a novel automatic polyp recognition scheme, namely, DenseNet-UDCS model, by addressing practical image unbalanced problem and small interclass variances and large intraclass differences in the data set. The comprehensive experimental results demonstrate superior reliability and robustness of the proposed model compared to the other polyp recognition approaches. Our DenseNet-UDCS model can be further applied in the clinical practice to provide valuable diagnosis information for GI disease recognition and precision medicine.

Densely Connected Neural Network With Unbalanced Discriminant and Category Sensitive Constraints for Polyp Recognition

In this paper, we propose a new deep artificial neural network architecture for synthetic aperture radar target recognition codenamed DeepSAR-Net. Unlike most existing methods, this approach can learn discriminative features directly from the training data instead of requiring pre-specification or pre-selection by a human designer. Furthermore, our method is adaptable, and it is learning to recognize new targets which do not require lots of time and data resources. Experimental results on the MSTAR dataset show that the DeepSAR-Net framework yield dramatic improvement in SAR ATR compared with the state-of-the-art techniques.

DeepSAR-Net: Deep convolutional neural networks for SAR target recognition

Recently, unsupervised deep hashing has attracted increasing attention, mainly because of its potential ability to learn binary codes without identity annotations. However, because the labels are predicted by their pretext tasks, unsupervised deep hashing becomes unstable when learning with noisy labels. To mitigate this issue, we propose a simple but effective approach to self-supervised hash learning based on dual pseudo agreement. By adding a consistency constraint, our method can prevent corrupted labels and encourage generalization for effective knowledge distillation. Specifically, we use the refined pseudo labels as a stabilization constraint to train hash codes, which can implicitly encode semantic structures of the data into the learned Hamming space. Based on the stable pseudo labels, we propose a self-supervised hashing method with mutual information and noise contrastive loss. Throughout the process of hash learning, the stable pseudo labels and data distributions collaboratively work together as teachers to guide the binary codes learning process. Extensive experiments on three publicly available datasets demonstrate that the proposed method can consistently outperform state-of-the-art methods by large margins.

/pdf/contrastive-self-supervised-hashing-with-dual-pseudo-ydeow19ul0.pdf

Contrastive Self-Supervised Hashing With Dual Pseudo Agreement

Deep feature representation is widely used in various visual applications. However, the feature extracted by the convolutional neural networks (CNNs) is inappropriate for cosine similarity measurement. Because the classical CNNs are designed for classification rather than for similarity comparison. A novel cosine loss function for learning deep discriminative features, which are fit to the cosine similarity measurement, is designed. The loss can constrain the distribution of the features in the same class to be in a narrow angle region. Furthermore, a discriminative feature learning network framework and its corresponding two-stage learning method to learn the parameters is proposed. Experimental results show that the proposed method achieves state-of-the-art performance on the public Cifar10 and Market1501 datasets.

https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/el.2017.0523

Learning deep discriminative features based on cosine loss function

With the development of deep hashing learning, several end-to-end deep architectures have been proposed for fast image retrieval. However, learning to hash is essentially a mixed integer nonlinear optimisation problem with the non-deterministic polynomial-time (NP)-hard nature, which makes the standard back-propagation algorithm infeasible. A novel pairwise loss function with additional binary constraint via siamese network is proposed to improve the representation ability of hash codes. Compared to previous works, we force the output of each hidden node close to −1 or +1, which can produce more compact and discriminative hash codes. Extensive experimental results demonstrate that the method can generate more favourable results than existing state-of-the-art hash function learning methods with large margins.

Deep binary constraint hashing for fast image retrieval

The application of fine-grained image classification can be problematic due to subtle differences between classes. The existing global feature-based methods have worse accuracies than regional feature-based methods, because regional feature-based methods focus on the determination of differentiated features within local regions. To learn more discriminative global features, in this paper, we proposed the use of L2 normalization to tackle a neglected conflict between the widely used metric loss (triplet loss) and classification loss (softmax loss) in global feature-based methods. Furthermore, a multi-level metric learning network (MMLN) is proposed for fine-grained image classification based on global features. In the MMLN, multi-level metric learning objectives and classification objectives are present at multiple high-level layers. The multi-level metric learning objectives work together to supervise the network in order to learn highly discriminative features. In addition, a new probability aggregation strategy (PAS) is proposed to produce a fused prediction by combining the multi-level predictive probabilities. Experiments were conducted on three standard fine-grained classification datasets (CUB-200-2011, Stanford Cars, and FGVC-Aircraft). Results demonstrated that our MMLN achieved accuracies of 88.0%, 94.6% and 92.4% respectively and outperformed state-of-the-art methods, substantially improving fine-grained classification tasks. Besides, gradient-weighted class activation mapping (Grad-CAM) shows that the MMLN is able to pay more attention to the discriminative local regions due to the application of multi-level metric learning.

/pdf/multi-level-metric-learning-network-for-fine-grained-1z3dcfzsns.pdf

Multi-Level Metric Learning Network for Fine-Grained Classification

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Jiabao Wang

Author Tools

Chat about Author