PMT-IQA: Progressive Multi-task Learning for Blind Image Quality Assessment

Blind image quality assessment (BIQA) remains challenging due to the diversity of distortion and image content variation, which complicate the distortion patterns crossing different scales and aggravate the difficulty of the regression problem for BIQA. However, existing BIQA methods often fail to consider multi-scale distortion patterns and image content, and little research has been done on learning strategies to make the regression model produce better performance. In this paper, we propose a simple yet effective Progressive Multi-Task Image Quality Assessment (PMT-IQA) model, which contains a multi-scale feature extraction module (MS) and a progressive multi-task learning module (PMT), to help the model learn complex distortion patterns and better optimize the regression issue to align with the law of human learning process from easy to hard. To verify the effectiveness of the proposed PMT-IQA model, we conduct experiments on four widely used public datasets, and the experimental results indicate that the performance of PMT-IQA is superior to the comparison approaches, and both MS and PMT modules improve the model's performance.

Unsupervised Domain Adaptation via Deep Hierarchical Optimal Transport

Unsupervised domain adaptation is a challenging task that aims to estimate a transferable model for unlabeled target domain by exploiting source labeled data. Optimal Transport (OT) based methods recently have been proven to be a promising direction for domain adaptation due to their competitive performance. However, most of these methods coarsely aligned source and target distributions, leading to the over-aligned problem where the category-discriminative information is mixed up although domain-invariant representations can be learned. In this paper, we propose a Deep Hierarchical Optimal Transport method (DeepHOT) for unsupervised domain adaptation. The main idea is to use hierarchical optimal transport to learn both domain-invariant and category-discriminative representations by mining the rich structural correlations among domain data. The DeepHOT framework consists of a domain-level OT and an image-level OT, where the latter is used as the ground distance metric for the former. The image-level OT captures structural associations of local image regions that are beneficial to image classification, while the domain-level OT learns domain-invariant representations by leveraging the underlying geometry of domains. However, due to the high computational complexity, the optimal transport based models are limited in some scenarios. To this end, we propose a robust and efficient implementation of the DeepHOT framework by approximating origin OT with sliced Wasserstein distance in image-level OT and using a mini-batch unbalanced optimal transport for domain-level OT. Extensive experiments show that DeepHOT surpasses the state-of-the-art methods in four benchmark datasets. Code will be released on GitHub.

Semantic Graph-enhanced Visual Network for Zero-shot Learning

Zero-shot learning uses semantic attributes to connect the search space of unseen objects. In recent years, although the deep convolutional network brings powerful visual modeling capabilities to the ZSL task, its visual features have severe pattern inertia and lack of representation of semantic relationships, which leads to severe bias and ambiguity. In response to this, we propose the Graph-based Visual-Semantic Entanglement Network to conduct graph modeling of visual features, which is mapped to semantic attributes by using a knowledge graph, it contains several novel designs: 1. it establishes a multi-path entangled network with the convolutional neural network (CNN) and the graph convolutional network (GCN), which input the visual features from CNN to GCN to model the implicit semantic relations, then GCN feedback the graph modeled information to CNN features; 2. it uses attribute word vectors as the target for the graph semantic modeling of GCN, which forms a self-consistent regression for graph modeling and supervise GCN to learn more personalized attribute relations; 3. it fuses and supplements the hierarchical visual-semantic features refined by graph modeling into visual embedding. By promoting the semantic linkage modeling of visual features, our method outperforms state-of-the-art approaches on multiple representative ZSL datasets: AwA2, CUB, and SUN.

Parallelized Training of Restricted Boltzmann Machines using Markov-Chain Monte Carlo Methods

Restricted Boltzmann Machine (RBM) is a generative stochastic neural network that can be applied to collaborative filtering technique used by recommendation systems. Prediction accuracy of the RBM model is usually better than that of other models for recommendation systems. However, training the RBM model involves Markov-Chain Monte Carlo (MCMC) method, which is computationally expensive. In this paper, we have successfully applied distributed parallel training using Horovod framework to improve the training time of the RBM model. Our tests show that the distributed training approach of the RBM model has a good scaling efficiency. We also show that this approach effectively reduces the training time to little over 12 minutes on 64 CPU nodes compared to 5 hours on a single CPU node. This will make RBM models more practically applicable in recommendation systems.

Densifying Assumed-sparse Tensors: Improving Memory Efficiency and MPI Collective Performance during Tensor Accumulation for Parallelized Training of Neural Machine Translation Models

Neural machine translation - using neural networks to translate human language - is an area of active research exploring new neuron types and network topologies with the goal of dramatically improving machine translation performance. Current state-of-the-art approaches, such as the multi-head attention-based transformer, require very large translation corpuses and many epochs to produce models of reasonable quality. Recent attempts to parallelize the official TensorFlow "Transformer" model across multiple nodes have hit roadblocks due to excessive memory use and resulting out of memory errors when performing MPI collectives. This paper describes modifications made to the Horovod MPI-based distributed training framework to reduce memory usage for transformer models by converting assumed-sparse tensors to dense tensors, and subsequently replacing sparse gradient gather with dense gradient reduction. The result is a dramatic increase in scale-out capability, with CPU-only scaling tests achieving 91% weak scaling efficiency up to 1200 MPI processes (300 nodes), and up to 65% strong scaling efficiency up to 400 MPI processes (200 nodes) using the Stampede2 supercomputer.

An Effective Way to Improve YouTube-8M Classification Accuracy in Google Cloud Platform

Large-scale datasets have played a significant role in progress of neural network and deep learning areas. YouTube-8M is such a benchmark dataset for general multi-label video classification. It was created from over 7 million YouTube videos (450,000 hours of video) and includes video labels from a vocabulary of 4716 classes (3.4 labels/video on average). It also comes with pre-extracted audio & visual features from every second of video (3.2 billion feature vectors in total). Google cloud recently released the datasets and organized 'Google Cloud & YouTube-8M Video Understanding Challenge' on Kaggle. Competitors are challenged to develop classification algorithms that assign video-level labels using the new and improved Youtube-8M V2 dataset. Inspired by the competition, we started exploration of audio understanding and classification using deep learning algorithms and ensemble methods. We built several baseline predictions according to the benchmark paper and public github tensorflow code. Furthermore, we improved global prediction accuracy (GAP) from base level 77% to 80.7% through approaches of ensemble.

Multi-agent Reinforcement Learning with Sparse Interactions by Negotiation and Knowledge Transfer

Reinforcement learning has significant applications for multi-agent systems, especially in unknown dynamic environments. However, most multi-agent reinforcement learning (MARL) algorithms suffer from such problems as exponential computation complexity in the joint state-action space, which makes it difficult to scale up to realistic multi-agent problems. In this paper, a novel algorithm named negotiation-based MARL with sparse interactions (NegoSI) is presented. In contrast to traditional sparse-interaction based MARL algorithms, NegoSI adopts the equilibrium concept and makes it possible for agents to select the non-strict Equilibrium Dominating Strategy Profile (non-strict EDSP) or Meta equilibrium for their joint actions. The presented NegoSI algorithm consists of four parts: the equilibrium-based framework for sparse interactions, the negotiation for the equilibrium set, the minimum variance method for selecting one joint action and the knowledge transfer of local Q-values. In this integrated algorithm, three techniques, i.e., unshared value functions, equilibrium solutions and sparse interactions are adopted to achieve privacy protection, better coordination and lower computational complexity, respectively. To evaluate the performance of the presented NegoSI algorithm, two groups of experiments are carried out regarding three criteria: steps of each episode (SEE), rewards of each episode (REE) and average runtime (AR). The first group of experiments is conducted using six grid world games and shows fast convergence and high scalability of the presented algorithm. Then in the second group of experiments NegoSI is applied to an intelligent warehouse problem and simulated results demonstrate the effectiveness of the presented NegoSI algorithm compared with other state-of-the-art MARL algorithms.