To mitigate the radiologist's workload, computer-aided diagnosis with the capability to review and analyze medical images is gradually deployed. Deep learning-based region of interest segmentation is among the most exciting use cases. However, this paradigm is restricted in real-world clinical applications due to poor robustness and generalization. The issue is more sinister with a lack of training data. In this paper, we address the challenge from the representation learning point of view. We investigate that the collapsed representations, as one of the main reasons which caused poor robustness and generalization, could be avoided through transfer learning. Therefore, we propose a novel two-stage framework for robust generalized segmentation. In particular, an unsupervised Tile-wise AutoEncoder (T-AE) pretraining architecture is coined to learn meaningful representation for improving the generalization and robustness of the downstream tasks. Furthermore, the learned knowledge is transferred to the segmentation benchmark. Coupled with an image reconstruction network, the representation keeps to be decoded, encouraging the model to capture more semantic features. Experiments of lung segmentation on multi chest X-ray datasets are conducted. Empirically, the related experimental results demonstrate the superior generalization capability of the proposed framework on unseen domains in terms of high performance and robustness to corruption, especially under the scenario of the limited training data.

In this paper, a CNN-based structure for time-frequency localization of audio signal information in the ASR acoustic model is proposed for Persian speech recognition. Research has shown that the receptive fields' time-frequency flexibility in some mammals' auditory neurons system improves recognition performance. Biosystems have inspired many artificial systems because of their high efficiency and performance, so time-frequency localization has been used extensively to improve system performance. In the last few years, much work has been done to localize time-frequency information in ASR systems, which has used the spatial immutability properties of methods such as TDNN, CNN and LSTM-RNN. However, most of these models have large parameter volumes and are challenging to train. In the structure we have designed, called Time-Frequency Convolutional Maxout Neural Network (TFCMNN), two parallel blocks consisting of 1D-CMNN each have weight sharing in one dimension, are applied simultaneously but independently to the feature vectors. Then their output is concatenated and applied to a fully connected Maxout network for classification. To improve the performance of this structure, we have used newly developed methods and models such as the maxout, Dropout, and weight normalization. Two experimental sets were designed and implemented on the Persian FARSDAT speech data set to evaluate the performance of this model compared to conventional 1D-CMNN models. According to the experimental results, the average recognition score of TFCMNN models is about 1.6% higher than the average of conventional models. In addition, the average training time of the TFCMNN models is about 17 hours lower than the average training time of traditional models. As a result, as mentioned in other references, time-frequency localization in ASR systems increases system accuracy and speeds up the model training process.

The goals of this paper are two-fold. The first goal is to serve as an expository tutorial on the working of deep learning models which emphasizes geometrical intuition about the reasons for success of deep learning. The second goal is to complement the current results on the expressive power of deep learning models and their loss surfaces with novel insights and results. In particular, we describe how deep neural networks carve out manifolds especially when the multiplication neurons are introduced. Multiplication is used in dot products and the attention mechanism and it is employed in capsule networks and self-attention based transformers. We also describe how random polynomial, random matrix, spin glass and computational complexity perspectives on the loss surfaces are interconnected.

We present a study of the manners by which Domain information has been incorporated when building models with Neural Networks. Integrating space data is uniquely important to the development of Knowledge understanding model, as well as other fields that aid in understanding information by utilizing the human-machine interface and Reinforcement Learning. On numerous such occasions, machine-based model development may profit essentially from the human information on the world encoded in an adequately exact structure. This paper inspects expansive ways to affect encode such information as sensible and mathematical limitations and portrays methods and results that came to a couple of subcategories under all of those methodologies.

Learning generalizable manipulation skills is central for robots to achieve task automation in environments with endless scene and object variations. However, existing robot learning environments are limited in both scale and diversity of 3D assets (especially of articulated objects), making it difficult to train and evaluate the generalization ability of agents over novel objects. In this work, we focus on object-level generalization and propose SAPIEN Manipulation Skill Benchmark (abbreviated as ManiSkill), a large-scale learning-from-demonstrations benchmark for articulated object manipulation with 3D visual input (point cloud and RGB-D image). ManiSkill supports object-level variations by utilizing a rich and diverse set of articulated objects, and each task is carefully designed for learning manipulations on a single category of objects. We equip ManiSkill with a large number of high-quality demonstrations to facilitate learning-from-demonstrations approaches and perform evaluations on baseline algorithms. We believe that ManiSkill can encourage the robot learning community to explore more on learning generalizable object manipulation skills.

Recent E-commerce applications benefit from the growth of deep learning techniques. However, we notice that many works attempt to maximize business objectives by closely matching offline labels which follow the supervised learning paradigm. This results in models obtain high offline performance in terms of Area Under Curve (AUC) and Normalized Discounted Cumulative Gain (NDCG), but cannot consistently increase the revenue metrics such as purchases amount of users. Towards the issues, we build a simulated search engine AESim that can properly give feedback by a well-trained discriminator for generated pages, as a dynamic dataset. Different from previous simulation platforms which lose connection with the real world, ours depends on the real data in AliExpress Search: we use adversarial learning to generate virtual users and use Generative Adversarial Imitation Learning (GAIL) to capture behavior patterns of users. Our experiments also show AESim can better reflect the online performance of ranking models than classic ranking metrics, implying AESim can play a surrogate of AliExpress Search and evaluate models without going online.

Intelligent resident surveillance is one of the most essential smart community services. The increasing demand for security needs surveillance systems to be able to detect anomalies in surveillance scenes. Employing high-capacity computational devices for intelligent surveillance in residential societies is costly and not feasible. Therefore, we propose anomaly detection for intelligent surveillance using CPU-only edge devices. A modular framework to capture object-level inferences and tracking is developed. To cope with partial occlusions, posture deformations, and complex scenes, we employed feature encoding and trajectory association governed by two metrices complementing to each other. The elements of an anomaly detection framework are optimized to run on CPU-only edge devices with sufficient frames per second (FPS). The experimental results indicate the proposed method is feasible and achieves satisfactory results in real-life scenarios.

Neural text generation models are typically trained by maximizing log-likelihood with the sequence cross entropy loss, which encourages an exact token-by-token match between a target sequence with a generated sequence. Such training objective is sub-optimal when the target sequence not perfect, e.g., when the target sequence is corrupted with noises, or when only weak sequence supervision is available. To address this challenge, we propose a novel Edit-Invariant Sequence Loss (EISL), which computes the matching loss of a target n-gram with all n-grams in the generated sequence. EISL draws inspirations from convolutional networks (ConvNets) which are shift-invariant to images, hence is robust to the shift of n-grams to tolerate edits in the target sequences. Moreover, the computation of EISL is essentially a convolution operation with target n-grams as kernels, which is easy to implement with existing libraries. To demonstrate the effectiveness of EISL, we conduct experiments on three tasks: machine translation with noisy target sequences, unsupervised text style transfer, and non-autoregressive machine translation. Experimental results show our method significantly outperforms cross entropy loss on these three tasks.

Extracting structured clinical information from free-text radiology reports can enable the use of radiology report information for a variety of critical healthcare applications. In our work, we present RadGraph, a dataset of entities and relations in full-text chest X-ray radiology reports based on a novel information extraction schema we designed to structure radiology reports. We release a development dataset, which contains board-certified radiologist annotations for 500 radiology reports from the MIMIC-CXR dataset (14,579 entities and 10,889 relations), and a test dataset, which contains two independent sets of board-certified radiologist annotations for 100 radiology reports split equally across the MIMIC-CXR and CheXpert datasets. Using these datasets, we train and test a deep learning model, RadGraph Benchmark, that achieves a micro F1 of 0.82 and 0.73 on relation extraction on the MIMIC-CXR and CheXpert test sets respectively. Additionally, we release an inference dataset, which contains annotations automatically generated by RadGraph Benchmark across 220,763 MIMIC-CXR reports (around 6 million entities and 4 million relations) and 500 CheXpert reports (13,783 entities and 9,908 relations) with mappings to associated chest radiographs. Our freely available dataset can facilitate a wide range of research in medical natural language processing, as well as computer vision and multi-modal learning when linked to chest radiographs.

It is a dynamic and threshold breaking time for advancing innovation across Conversational Artificial Intelligence, Computer Vision and Recommender Systems (RecSys), with NVIDIA accelerating new ground with the launch of TensorRT 8, alongside multiple RecSys competition successes - more on this news in depth shortly! But firstly, let's set the scene on exactly why this matters so much today. As we move into an Era of Convergence blending algorithm, engineering and culture alike, and reflecting both the level of integration and the increased pace of socio-technical change, it becomes imperative to manage the demands this inevitably creates - in order to optimise the vast opportunities. Deep learning is a case in point - applicable to a diverse and growing range of industries from medical devices through to conversational IVR and automated driving; and across a wide range of applications in production, including image and video analysis, natural language processing (NLP) and recommender systems. But as the number of applications increases so do the demands!