Multi-task learning aims at solving multiple machine learning tasks at the same time. A good solution to a multi-task learning problem should be generalizable in addition to being Pareto optimal. In this paper, we provide some insights on understanding the trade-off between Pareto efficiency and generalization as a result of parameterization in multi-task deep learning models. As a multi-objective optimization problem, enough parameterization is needed for handling task conflicts in a constrained solution space; however, from a multi-task generalization perspective, over-parameterization undermines the benefit of learning a shared representation which helps harder tasks or tasks with limited training examples. A delicate balance between multi-task generalization and multi-objective optimization is therefore needed for finding a better trade-off between efficiency and generalization. To this end, we propose a method of under-parameterized self-auxiliaries for multi-task models to achieve the best of both worlds. It is task-agnostic and works with other multi-task learning algorithms. Empirical results show that small towers of under-parameterized self-auxiliaries can make big differences in improving Pareto efficiency in various multi-task applications.
While high-resolution pathology images lend themselves well to `data hungry' deep learning algorithms, obtaining exhaustive annotations on these images is a major challenge. In this paper, we propose a self-supervised CNN approach to leverage unlabeled data for learning generalizable and domain invariant representations in pathology images. The proposed approach, which we term as Self-Path, is a multi-task learning approach where the main task is tissue classification and pretext tasks are a variety of self-supervised tasks with labels inherent to the input data. We introduce novel domain specific self-supervision tasks that leverage contextual, multi-resolution and semantic features in pathology images for semi-supervised learning and domain adaptation. We investigate the effectiveness of Self-Path on 3 different pathology datasets. Our results show that Self-Path with the domain-specific pretext tasks achieves state-of-the-art performance for semi-supervised learning when small amounts of labeled data are available. Further, we show that Self-Path improves domain adaptation for classification of histology image patches when there is no labeled data available for the target domain. This approach can potentially be employed for other applications in computational pathology, where annotation budget is often limited or large amount of unlabeled image data is available.
Tacotron-based end-to-end speech synthesis has shown remarkable voice quality. However, the rendering of prosody in the synthesized speech remains to be improved, especially for long sentences, where prosodic phrasing errors can occur frequently. In this paper, we extend the Tacotron-based speech synthesis framework to explicitly model the prosodic phrase breaks. We propose a multi-task learning scheme for Tacotron training, that optimizes the system to predict both Mel spectrum and phrase breaks. To our best knowledge, this is the first implementation of multi-task learning for Tacotron based TTS with a prosodic phrasing model. Experiments show that our proposed training scheme consistently improves the voice quality for both Chinese and Mongolian systems.
Diabetic retinopathy (DR) screening is instrumental in preventing blindness, but faces a scaling challenge as the number of diabetic patients rises. Risk stratification for the development of DR may help optimize screening intervals to reduce costs while improving vision-related outcomes. We created and validated two versions of a deep learning system (DLS) to predict the development of mild-or-worse ("Mild+") DR in diabetic patients undergoing DR screening. The two versions used either three-fields or a single field of color fundus photographs (CFPs) as input. The training set was derived from 575,431 eyes, of which 28,899 had known 2-year outcome, and the remaining were used to augment the training process via multi-task learning. Validation was performed on both an internal validation set (set A; 7,976 eyes; 3,678 with known outcome) and an external validation set (set B; 4,762 eyes; 2,345 with known outcome). For predicting 2-year development of DR, the 3-field DLS had an area under the receiver operating characteristic curve (AUC) of 0.79 (95%CI, 0.78-0.81) on validation set A. On validation set B (which contained only a single field), the 1-field DLS's AUC was 0.70 (95%CI, 0.67-0.74). The DLS was prognostic even after adjusting for available risk factors (p<0.001). When added to the risk factors, the 3-field DLS improved the AUC from 0.72 (95%CI, 0.68-0.76) to 0.81 (95%CI, 0.77-0.84) in validation set A, and the 1-field DLS improved the AUC from 0.62 (95%CI, 0.58-0.66) to 0.71 (95%CI, 0.68-0.75) in validation set B. The DLSs in this study identified prognostic information for DR development from CFPs. This information is independent of and more informative than the available risk factors.
Semi-supervised techniques have removed the barriers of large scale labelled set by exploiting unlabelled data to improve the performance of a model. In this paper, we propose a semi-supervised deep multi-task classification and localization approach HydraMix-Net in the field of medical imagining where labelling is time consuming and costly. Firstly, the pseudo labels are generated using the model's prediction on the augmented set of unlabelled image with averaging. The high entropy predictions are further sharpened to reduced the entropy and are then mixed with the labelled set for training. The model is trained in multi-task learning manner with noise tolerant joint loss for classification localization and achieves better performance when given limited data in contrast to a simple deep model. On DLBCL data it achieves 80\% accuracy in contrast to simple CNN achieving 70\% accuracy when given only 100 labelled examples.
Dialogue state tracking is a key part of a task-oriented dialogue system, which estimates the user's goal at each turn of the dialogue. In this paper, we propose the Point-Or-Generate Dialogue State Tracker (POGD). POGD solves the dialogue state tracking task in two perspectives: 1) point out explicitly expressed slot values from the user's utterance, and 2) generate implicitly expressed ones based on slot-specific contexts. It also shares parameters across all slots, which achieves knowledge sharing and gains scalability to large-scale across-domain dialogues. Moreover, the training process of its submodules is formulated as a multi-task learning procedure to further promote its capability of generalization. Experiments show that POGD not only obtains state-of-the-art results on both WoZ 2.0 and MultiWoZ 2.0 datasets but also has good generalization on unseen values and new slots.
State-of-the-art self-supervised learning approaches for monocular depth estimation usually suffer from scale ambiguity. They do not generalize well when applied on distance estimation for complex projection models such as in fisheye and omnidirectional cameras. This paper introduces a novel multi-task learning strategy to improve self-supervised monocular distance estimation on fisheye and pinhole camera images. Our contribution to this work is threefold: Firstly, we introduce a novel distance estimation network architecture using a self-attention based encoder coupled with robust semantic feature guidance to the decoder that can be trained in a one-stage fashion. Secondly, we integrate a generalized robust loss function, which improves performance significantly while removing the need for hyperparameter tuning with the reprojection loss. Finally, we reduce the artifacts caused by dynamic objects violating static world assumptions using a semantic masking strategy. We significantly improve upon the RMSE of previous work on fisheye by 25% reduction in RMSE. As there is little work on fisheye cameras, we evaluated the proposed method on KITTI using a pinhole model. We achieved state-of-the-art performance among self-supervised methods without requiring an external scale estimation.
We propose a new approach to Human Activity Evaluation (HAE) in long videos using graph-based multi-task modeling. Previous works in activity evaluation either directly compute a metric using a detected skeleton or use the scene information to regress the activity score. These approaches are insufficient for accurate activity assessment since they only compute an average score over a clip, and do not consider the correlation between the joints and body dynamics. Moreover, they are highly scene-dependent which makes the generalizability of these methods questionable. We propose a novel multi-task framework for HAE that utilizes a Graph Convolutional Network backbone to embed the interconnections between human joints in the features. In this framework, we solve the Human Activity Segmentation (HAS) problem as an auxiliary task to improve activity assessment. The HAS head is powered by an Encoder-Decoder Temporal Convolutional Network to semantically segment long videos into distinct activity classes, whereas, HAE uses a Long-Short-Term-Memory-based architecture. We evaluate our method on the UW-IOM and TUM Kitchen datasets and discuss the success and failure cases in these two datasets.
Information on speaker characteristics can be useful as side information in improving speaker recognition accuracy. However, such information is often private. This paper investigates how privacy-preserving learning can improve a speaker verification system, by enabling the use of privacy-sensitive speaker data to train an auxiliary classification model that predicts vocal characteristics of speakers. In particular, this paper explores the utility achieved by approaches which combine different federated learning and differential privacy mechanisms. These approaches make it possible to train a central model while protecting user privacy, with users' data remaining on their devices. Furthermore, they make learning on a large population of speakers possible, ensuring good coverage of speaker characteristics when training a model. The auxiliary model described here uses features extracted from phrases which trigger a speaker verification system. From these features, the model predicts speaker characteristic labels considered useful as side information. The knowledge of the auxiliary model is distilled into a speaker verification system using multi-task learning, with the side information labels predicted by this auxiliary model being the additional task. This approach results in a 6% relative improvement in equal error rate over a baseline system.
We consider the design of two-pass voice trigger detection systems. We focus on the networks in the second pass that are used to re-score candidate segments obtained from the first-pass. Our baseline is an acoustic model(AM), with BiLSTM layers, trained by minimizing the CTC loss. We replace the BiLSTM layers with self-attention layers. Results on internal evaluation sets show that self-attention networks yield better accuracy while requiring fewer parameters. We add an auto-regressive decoder network on top of the self-attention layers and jointly minimize the CTC loss on the encoder and the cross-entropy loss on the decoder. This design yields further improvements over the baseline. We retrain all the models above in a multi-task learning(MTL) setting, where one branch of a shared network is trained as an AM, while the second branch classifies the whole sequence to be true-trigger or not. Results demonstrate that networks with self-attention layers yield $\sim$60% relative reduction in false reject rates for a given false-alarm rate, while requiring 10% fewer parameters. When trained in the MTL setup, self-attention networks yield further accuracy improvements. On-device measurements show that we observe 70% relative reduction in inference time. Additionally, the proposed network architectures are $\sim$5X faster to train.
We present MultiCheXNet, an end-to-end Multi-task learning model, that is able to take advantage of different X-rays data sets of Pneumonia-like diseases in one neural architecture, performing three tasks at the same time; diagnosis, segmentation and localization. The common encoder in our architecture can capture useful common features present in the different tasks. The common encoder has another advantage of efficient computations, which speeds up the inference time compared to separate models. The specialized decoders heads can then capture the task-specific features. We employ teacher forcing to address the issue of negative samples that hurt the segmentation and localization performance. Finally,we employ transfer learning to fine tune the classifier on unseen pneumonia-like diseases. The MTL architecture can be trained on joint or dis-joint labeled data sets. The training of the architecture follows a carefully designed protocol, that pre trains different sub-models on specialized datasets, before being integrated in the joint MTL model. Our experimental setup involves variety of data sets, where the baseline performance of the 3 tasks is compared to the MTL architecture performance. Moreover, we evaluate the transfer learning mode to COVID-19 data set,both from individual classifier model, and from MTL architecture classification head.
The E-commerce platform has become the principal battleground where people search, browse and pay for whatever they want. Critical as is to improve the online shopping experience for customers and merchants, how to find a proper approach for user intent prediction are paid great attention in both industry and academia. In this paper, we propose a novel user intent prediction model, TPG-DNN, to complete the challenging task, which is based on adaptive gated recurrent unit (GRU) loss function with multi-task learning. We creatively use the GRU structure and total probability formula as the loss function to model the users' whole online purchase process. Besides, the multi-task weight adjustment mechanism can make the final loss function dynamically adjust the importance between different tasks through data variance. According to the test result of experiments conducted on Taobao daily and promotion data sets, the proposed model performs much better than existing click through rate (CTR) models. At present, the proposed user intent prediction model has been widely used for the coupon allocation, advertisement and recommendation on Taobao platform, which greatly improve the user experience and shopping efficiency, and benefit the gross merchandise volume (GMV) promotion as well.
Learning two tasks in a single shared function has some benefits. Firstly by acquiring information from the second task, the shared function leverages useful information that could have been neglected or underestimated in the first task. Secondly, it helps to generalize the function that can be learned using generally applicable information for both tasks. To fully enjoy these benefits, Multi-task Learning (MTL) has long been researched in various domains such as computer vision, language understanding, and speech synthesis. While MTL benefits from the positive transfer of information from multiple tasks, in a real environment, tasks inevitably have a conflict between them during the learning phase, called negative transfer. The negative transfer hampers function from achieving the optimality and degrades the performance. To solve the problem of the task conflict, previous works only suggested partial solutions that are not fundamental, but ad-hoc. A common approach is using a weighted sum of losses. The weights are adjusted to induce positive transfer. Paradoxically, this kind of solution acknowledges the problem of negative transfer and cannot remove it unless the weight of the task is set to zero. Therefore, these previous methods had limited success. In this paper, we introduce a novel approach that can drive positive transfer and suppress negative transfer by leveraging class-wise weights in the learning process. The weights act as an arbitrator of the fundamental unit of information to determine its positive or negative status to the main task.
Adopting Convolutional Neural Networks (CNNs) in the daily routine of primary diagnosis requires not only near-perfect precision, but also a sufficient degree of generalization to data acquisition shifts and transparency. Existing CNN models act as black boxes, not ensuring to the physicians that important diagnostic features are used by the model. Building on top of successfully existing techniques such as multi-task learning, domain adversarial training and concept-based interpretability, this paper addresses the challenge of introducing diagnostic factors in the training objectives. Here we show that our architecture, by learning end-to-end an uncertainty-based weighting combination of multi-task and adversarial losses, is encouraged to focus on pathology features such as density and pleomorphism of nuclei, e.g. variations in size and appearance, while discarding misleading features such as staining differences. Our results on breast lymph node tissue show significantly improved generalization in the detection of tumorous tissue, with best average AUC 0.89 (0.01) against the baseline AUC 0.86 (0.005). By applying the interpretability technique of linearly probing intermediate representations, we also demonstrate that interpretable pathology features such as nuclei density are learned by the proposed CNN architecture, confirming the increased transparency of this model. This result is a starting point towards building interpretable multi-task architectures that are robust to data heterogeneity. Our code is available at https://github.com/maragraziani/multitask_adversarial
The attributes of object contours has great significance for instance segmentation task. However, most of the current popular deep neural networks do not pay much attention to the object edge information. Inspired by the human annotation process when making instance segmentation datasets, in this paper, we propose Mask Point R-CNN aiming at promoting the neural network's attention to the object boundary. Specifically, we innovatively extend the original human keypoint detection task to the contour point detection of any object. Based on this analogy, we present an contour point detection auxiliary task to Mask R-CNN, which can boost the gradient flow between different tasks by effectively using feature fusion strategies and multi-task joint training. As a consequence, the model will be more sensitive to the edges of the object and can capture more geometric features. Quantitatively, the experimental results show that our approach outperforms vanilla Mask R-CNN by 3.8\% on Cityscapes dataset and 0.8\% on COCO dataset.
We study the problem of symmetry detection of 3D shapes from single-view RGB-D images, where severely missing data renders geometric detection approach infeasible. We propose an end-to-end deep neural network which is able to predict both reflectional and rotational symmetries of 3D objects present in the input RGB-D image. Directly training a deep model for symmetry prediction, however, can quickly run into the issue of overfitting. We adopt a multi-task learning approach. Aside from symmetry axis prediction, our network is also trained to predict symmetry correspondences. In particular, given the 3D points present in the RGB-D image, our network outputs for each 3D point its symmetric counterpart corresponding to a specific predicted symmetry. In addition, our network is able to detect for a given shape multiple symmetries of different types. We also contribute a benchmark of 3D symmetry detection based on single-view RGB-D images. Extensive evaluation on the benchmark demonstrates the strong generalization ability of our method, in terms of high accuracy of both symmetry axis prediction and counterpart estimation. In particular, our method is robust in handling unseen object instances with large variation in shape, multi-symmetry composition, as well as novel object categories.
Multi-task learning (MTL) significantly pre-dates the deep learning era, and it has seen a resurgence in the past few years as researchers have been applying MTL to deep learning solutions for natural language tasks. While steady MTL research has always been present, there is a growing interest driven by the impressive successes published in the related fields of transfer learning and pre-training, such as BERT, and the release of new challenge problems, such as GLUE and the NLP Decathlon (decaNLP). These efforts place more focus on how weights are shared across networks, evaluate the re-usability of network components and identify use cases where MTL can significantly outperform single-task solutions. This paper strives to provide a comprehensive survey of the numerous recent MTL contributions to the field of natural language processing and provide a forum to focus efforts on the hardest unsolved problems in the next decade. While novel models that improve performance on NLP benchmarks are continually produced, lasting MTL challenges remain unsolved which could hold the key to better language understanding, knowledge discovery and natural language interfaces.
With a proliferation of generic domain-adaptation approaches, we report a simple yet effective technique for learning difficult per-pixel 2.5D and 3D regression representations of articulated people. We obtained strong sim-to-real domain generalization for the 2.5D DensePose estimation task and the 3D human surface normal estimation task. On the multi-person DensePose MSCOCO benchmark, our approach outperforms the state-of-the-art methods which are trained on real images that are densely labelled. This is an important result since obtaining human manifold's intrinsic uv coordinates on real images is time consuming and prone to labeling noise. Additionally, we present our model's 3D surface normal predictions on the MSCOCO dataset that lacks any real 3D surface normal labels. The key to our approach is to mitigate the "Inter-domain Covariate Shift" with a carefully selected training batch from a mixture of domain samples, a deep batch-normalized residual network, and a modified multi-task learning objective. Our approach is complementary to existing domain-adaptation techniques and can be applied to other dense per-pixel pose estimation problems.
The classical approach to non-linear regression in physics, is to take a mathematical model describing the functional dependence of the dependent variable from a set of independent variables, and then, using non-linear fitting algorithms, extract the parameters used in the modeling. Particularly challenging are real systems, characterized by several additional influencing factors related to specific components, like electronics or optical parts. In such cases, to make the model reproduce the data, empirically determined terms are built-in the models to compensate for the impossibility of modeling things that are, by construction, impossible to model. A new approach to solve this issue is to use neural networks, particularly feed-forward architectures with a sufficient number of hidden layers and an appropriate number of output neurons, each responsible for predicting the desired variables. Unfortunately, feed-forward neural networks (FFNNs) usually perform less efficiently when applied to multi-dimensional regression problems, that is when they are required to predict simultaneously multiple variables that depend from the input dataset in fundamentally different ways. To address this problem, we propose multi-task learning (MTL) architectures. These are characterized by multiple branches of task-specific layers, which have as input the output of a common set of layers. To demonstrate the power of this approach for multi-dimensional regression, the method is applied to luminescence sensing. Here the MTL architecture allows predicting multiple parameters, the oxygen concentration and the temperature, from a single set of measurements.
We propose a novel framework for creating large-scale photorealistic datasets of indoor scenes, with ground truth geometry, material, lighting and semantics. Our goal is to make the dataset creation process widely accessible, transforming scans into photorealistic datasets with high-quality ground truth for appearance, layout, semantic labels, high quality spatially-varying BRDF and complex lighting, including direct, indirect and visibility components. This enables important applications in inverse rendering, scene understanding and robotics. We show that deep networks trained on the proposed dataset achieve competitive performance for shape, material and lighting estimation on real images, enabling photorealistic augmented reality applications, such as object insertion and material editing. We also show our semantic labels may be used for segmentation and multi-task learning. Finally, we demonstrate that our framework may also be integrated with physics engines, to create virtual robotics environments with unique ground truth such as friction coefficients and correspondence to real scenes. The dataset and all the tools to create such datasets will be made publicly available.