Hand Image Understanding via Deep Multi-Task Learning

Analyzing and understanding hand information from multimedia materials like images or videos is important for many real world applications and remains active in research community. There are various works focusing on recovering hand information from single image, however, they usually solve a single task, for example, hand mask segmentation, 2D/3D hand pose estimation, or hand mesh reconstruction and perform not well in challenging scenarios. To further improve the performance of these tasks, we propose a novel Hand Image Understanding (HIU) framework to extract comprehensive information of the hand object from a single RGB image, by jointly considering the relationships between these tasks. To achieve this goal, a cascaded multi-task learning (MTL) backbone is designed to estimate the 2D heat maps, to learn the segmentation mask, and to generate the intermediate 3D information encoding, followed by a coarse-to-fine learning paradigm and a self-supervised learning strategy. Qualitative experiments demonstrate that our approach is capable of recovering reasonable mesh representations even in challenging situations. Quantitatively, our method significantly outperforms the state-of-the-art approaches on various widely-used datasets, in terms of diverse evaluation metrics.

Copy and Paste method based on Pose for Re-identification

Re-identification (ReID) aims at matching objects in surveillance cameras with different viewpoints. It's developing very fast, but there is no processing method for the ReID task in multiple scenarios at this stage. However, this dose happen all the time in real life, such as the security scenarios. This paper explores a new scenario of Re-identification, which differs in perspective, background, and pose(walking or cycling). Obviously, ordinary ReID processing methods cannot handle this scenario well. As we all know, the best way to deal with that it is to introduce image datasets in this scanario, But this one is very expensive. To solve this problem, this paper proposes a simple and effective way to generate images in some new scenario, which is named Copy and Paste method based on Pose(CPP). The CPP is a method based on key point detection, using copy and paste, to composite a new semantic image dataset in two different semantic image datasets. Such as, we can use pedestrians and bicycles to generate some images that shows the same person rides on different bicycles. The CPP is suitable for ReID tasks in new scenarios and it outperforms state-of-the-art on the original datasets in original ReID tasks. Specifically, it can also have better generalization performance for third-party public datasets. Code and Datasets which composited by the CPP will be available in the future.

OLR 2021 Challenge: Datasets, Rules and Baselines

This paper introduces the sixth Oriental Language Recognition (OLR) 2021 Challenge, which intends to improve the performance of language recognition systems and speech recognition systems within multilingual scenarios. The data profile, four tasks, two baselines, and the evaluation principles are introduced in this paper. In addition to the Language Identification (LID) tasks, multilingual Automatic Speech Recognition (ASR) tasks are introduced to OLR 2021 Challenge for the first time. The challenge this year focuses on more practical and challenging problems, with four tasks: (1) constrained LID, (2) unconstrained LID, (3) constrained multilingual ASR, (4) unconstrained multilingual ASR. Baselines for LID tasks and multilingual ASR tasks are provided, respectively. The LID baseline system is an extended TDNN x-vector model constructed with Pytorch. A transformer-based end-to-end model is provided as the multilingual ASR baseline system. These recipes will be online published, and available for participants to construct their own LID or ASR systems. The baseline results demonstrate that those tasks are rather challenging and deserve more effort to achieve better performance.

Copy and Paste method based on Pose for ReID

Re-identification(ReID) aims at matching objects in surveillance cameras with different viewpoints. It's developing very fast, but there is no processing method for the ReID task in multiple scenarios at this stage. However, this dose happen all the time in real life, such as the security scenarios. This paper explores a new scenario of Re-identification, which differs in perspective, background, and pose(walking or cycling). Obviously, ordinary ReID processing methods cannot handle this scenario well. As we all konw, the best way to deal with that it is to introduce image datasets in this scanario, But this one is very expensive. To solve this problem, this paper proposes a simple and effective way to generate images in some new scenario, which is named Copy and Paste method based on Pose(CPP). The CPP is a method based on key point detection, using copy and paste, to composite a new semantic image dataset in two different semantic image datasets. Such as, we can use pedestrians and bicycles to generate some images that shows the same person rides on different bicycles. The CPP is suitable for ReID tasks in new scenarios and it outperforms state-of-the-art on the original datasets in original ReID tasks. Specifically, it can also have better generalization performance for third-party public datasets. Code and Datasets which composited by the CPP will be available in the future.

Evaluating Modules in Graph Contrastive Learning

The recent emergence of contrastive learning approaches facilitates the research on graph representation learning (GRL), introducing graph contrastive learning (GCL) into the literature. These methods contrast semantically similar and dissimilar sample pairs to encode the semantics into node or graph embeddings. However, most existing works only performed model-level evaluation, and did not explore the combination space of modules for more comprehensive and systematic studies. For effective module-level evaluation, we propose a framework that decomposes GCL models into four modules: (1) a sampler to generate anchor, positive and negative data samples (nodes or graphs); (2) an encoder and a readout function to get sample embeddings; (3) a discriminator to score each sample pair (anchor-positive and anchor-negative); and (4) an estimator to define the loss function. Based on this framework, we conduct controlled experiments over a wide range of architectural designs and hyperparameter settings on node and graph classification tasks. Specifically, we manage to quantify the impact of a single module, investigate the interaction between modules, and compare the overall performance with current model architectures. Our key findings include a set of module-level guidelines for GCL, e.g., simple samplers from LINE and DeepWalk are strong and robust; an MLP encoder associated with Sum readout could achieve competitive performance on graph classification. Finally, we release our implementations and results as OpenGCL, a modularized toolkit that allows convenient reproduction, standard model and module evaluation, and easy extension.

SAS: Self-Augmented Strategy for Language Model Pre-training

The core of a self-supervised learning method for pre-training language models includes the design of appropriate data augmentation and corresponding pre-training task(s). Most data augmentations in language model pre-training are context-independent. The seminal contextualized augmentation recently proposed by the ELECTRA requires a separate generator, which leads to extra computation cost as well as the challenge in adjusting the capability of its generator relative to that of the other model component(s). We propose a self-augmented strategy (SAS) that uses a single forward pass through the model to augment the input data for model training in the next epoch. Essentially our strategy eliminates a separate generator network and uses only one network to generate the data augmentation and undertake two pre-training tasks (the MLM task and the RTD task) jointly, which naturally avoids the challenge in adjusting the generator's capability as well as reduces the computation cost. Additionally, our SAS is a general strategy such that it can seamlessly incorporate many new techniques emerging recently or in the future, such as the disentangled attention mechanism recently proposed by the DeBERTa model. Our experiments show that our SAS is able to outperform the ELECTRA and other state-of-the-art models in the GLUE tasks with the same or less computation cost.

Projection-free Graph-based Classifier Learning using Gershgorin Disc Perfect Alignment

In semi-supervised graph-based binary classifier learning, a subset of known labels $\hat{x}_i$ are used to infer unknown labels, assuming that the label signal $x$ is smooth with respect to a similarity graph specified by a Laplacian matrix. When restricting labels $x_i$ to binary values, the problem is NP-hard. While a conventional semi-definite programming (SDP) relaxation can be solved in polynomial time using, for example, the alternating direction method of multipliers (ADMM), the complexity of iteratively projecting a candidate matrix $M$ onto the positive semi-definite (PSD) cone ($M \succeq 0$) remains high. In this paper, leveraging a recent linear algebraic theory called Gershgorin disc perfect alignment (GDPA), we propose a fast projection-free method by solving a sequence of linear programs (LP) instead. Specifically, we first recast the SDP relaxation to its SDP dual, where a feasible solution $H \succeq 0$ can be interpreted as a Laplacian matrix corresponding to a balanced signed graph sans the last node. To achieve graph balance, we split the last node into two that respectively contain the original positive and negative edges, resulting in a new Laplacian $\bar{H}$. We repose the SDP dual for solution $\bar{H}$, then replace the PSD cone constraint $\bar{H} \succeq 0$ with linear constraints derived from GDPA -- sufficient conditions to ensure $\bar{H}$ is PSD -- so that the optimization becomes an LP per iteration. Finally, we extract predicted labels from our converged LP solution $\bar{H}$. Experiments show that our algorithm enjoyed a $40\times$ speedup on average over the next fastest scheme while retaining comparable label prediction performance.

Rethinking Re-Sampling in Imbalanced Semi-Supervised Learning

Semi-Supervised Learning (SSL) has shown its strong ability in utilizing unlabeled data when labeled data is scarce. However, most SSL algorithms work under the assumption that the class distributions are balanced in both training and test sets. In this work, we consider the problem of SSL on class-imbalanced data, which better reflects real-world situations but has only received limited attention so far. In particular, we decouple the training of the representation and the classifier, and systematically investigate the effects of different data re-sampling techniques when training the whole network including a classifier as well as fine-tuning the feature extractor only. We find that data re-sampling is of critical importance to learn a good classifier as it increases the accuracy of the pseudo-labels, in particular for the minority classes in the unlabeled data. Interestingly, we find that accurate pseudo-labels do not help when training the feature extractor, rather contrariwise, data re-sampling harms the training of the feature extractor. This finding is against the general intuition that wrong pseudo-labels always harm the model performance in SSL. Based on these findings, we suggest to re-think the current paradigm of having a single data re-sampling strategy and develop a simple yet highly effective Bi-Sampling (BiS) strategy for SSL on class-imbalanced data. BiS implements two different re-sampling strategies for training the feature extractor and the classifier and integrates this decoupled training into an end-to-end framework... Code will be released at https://github.com/TACJu/Bi-Sampling.

Markdowns in E-Commerce Fresh Retail: A Counterfactual Prediction and Multi-Period Optimization Approach

In this paper, by leveraging abundant observational transaction data, we propose a novel data-driven and interpretable pricing approach for markdowns, consisting of counterfactual prediction and multi-period price optimization. Firstly, we build a semi-parametric structural model to learn individual price elasticity and predict counterfactual demand. This semi-parametric model takes advantage of both the predictability of nonparametric machine learning model and the interpretability of economic model. Secondly, we propose a multi-period dynamic pricing algorithm to maximize the overall profit of a perishable product over its finite selling horizon. Different with the traditional approaches that use the deterministic demand, we model the uncertainty of counterfactual demand since it inevitably has randomness in the prediction process. Based on the stochastic model, we derive a sequential pricing strategy by Markov decision process, and design a two-stage algorithm to solve it. The proposed algorithm is very efficient. It reduces the time complexity from exponential to polynomial. Experimental results show the advantages of our pricing algorithm, and the proposed framework has been successfully deployed to the well-known e-commerce fresh retail scenario - Freshippo.

Learning to Reconstruct 3D Non-Cuboid Room Layout from a Single RGB Image

Single-image room layout reconstruction aims to reconstruct the enclosed 3D structure of a room from a single image. Most previous work relies on the cuboid-shape prior. This paper considers a more general indoor assumption, i.e., the room layout consists of a single ceiling, a single floor, and several vertical walls. To this end, we first employ Convolutional Neural Networks to detect planes and vertical lines between adjacent walls. Meanwhile, estimating the 3D parameters for each plane. Then, a simple yet effective geometric reasoning method is adopted to achieve room layout reconstruction. Furthermore, we optimize the 3D plane parameters to reconstruct a geometrically consistent room layout between planes and lines. The experimental results on public datasets validate the effectiveness and efficiency of our method.