arXiv subjects

Rong Jin

Publications and source records attributed to Rong Jin.

At least 91 records · Page 5Linked to original sources

arXiv2022

CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation

Unsupervised domain adaptation (UDA) aims to transfer knowledge learned from a labeled source domain to a different unlabeled target domain. Most existing UDA methods focus on learning domain-invariant feature representation, either from the domain level or category level, using convolution neural networks (CNNs)-based frameworks. One fundamental problem for the category level based UDA is the production of pseudo labels for samples in target domain, which are usually too noisy for accurate domain alignment, inevitably compromising the UDA performance. With the success of Transformer in various tasks, we find that the cross-attention in Transformer is robust to the noisy input pairs for better feature alignment, thus in this paper Transformer is adopted for the challenging UDA task. Specifically, to generate accurate input pairs, we design a two-way center-aware labeling algorithm to produce pseudo labels for target samples. Along with the pseudo labels, a weight-sharing triple-branch transformer framework is proposed to apply self-attention and cross-attention for source/target feature learning and source-target domain alignment, respectively. Such design explicitly enforces the framework to learn discriminative domain-specific and domain-invariant representations simultaneously. The proposed method is dubbed CDTrans (cross-domain transformer), and it provides one of the first attempts to solve UDA tasks with a pure transformer solution. Experiments show that our proposed method achieves the best performance on public UDA datasets, e.g. VisDA-2017 and DomainNet. Code and models are available at https://github.com/CDTrans/CDTrans.

cs.CV↗

arXiv2022

Entroformer: A Transformer-based Entropy Model for Learned Image Compression

One critical component in lossy deep image compression is the entropy model, which predicts the probability distribution of the quantized latent representation in the encoding and decoding modules. Previous works build entropy models upon convolutional neural networks which are inefficient in capturing global dependencies. In this work, we propose a novel transformer-based entropy model, termed Entroformer, to capture long-range dependencies in probability distribution estimation effectively and efficiently. Different from vision transformers in image classification, the Entroformer is highly optimized for image compression, including a top-k self-attention and a diamond relative position encoding. Meanwhile, we further expand this architecture with a parallel bidirectional context model to speed up the decoding process. The experiments show that the Entroformer achieves state-of-the-art performance on image compression while being time-efficient.

eess.IV↗

arXiv2022

Rethinking Supervised Pre-training for Better Downstream Transferring

The pretrain-finetune paradigm has shown outstanding performance on many applications of deep learning, where a model is pre-trained on a upstream large dataset (e.g. ImageNet), and is then fine-tuned to different downstream tasks. Though for most cases, the pre-training stage is conducted based on supervised methods, recent works on self-supervised pre-training have shown powerful transferability and even outperform supervised pre-training on multiple downstream tasks. It thus remains an open question how to better generalize supervised pre-training model to downstream tasks. In this paper, we argue that the worse transferability of existing supervised pre-training methods arise from the negligence of valuable intra-class semantic difference. This is because these methods tend to push images from the same class close to each other despite of the large diversity in their visual contents, a problem to which referred as "overfit of upstream tasks". To alleviate this problem, we propose a new supervised pre-training method based on Leave-One-Out K-Nearest-Neighbor, or LOOK for short. It relieves the problem of overfitting upstream tasks by only requiring each image to share its class label with most of its k nearest neighbors, thus allowing each class to exhibit a multi-mode distribution and consequentially preserving part of intra-class difference for better transferring to downstream tasks. We developed efficient implementation of the proposed method that scales well to large datasets. Experimental studies on multiple downstream tasks show that LOOK outperforms other state-of-the-art methods for supervised and self-supervised pre-training.

cs.CV↗

arXiv2022

Effective Model Sparsification by Scheduled Grow-and-Prune Methods

Deep neural networks (DNNs) are effective in solving many real-world problems. Larger DNN models usually exhibit better quality (e.g., accuracy) but their excessive computation results in long inference time. Model sparsification can reduce the computation and memory cost while maintaining model quality. Most existing sparsification algorithms unidirectionally remove weights, while others randomly or greedily explore a small subset of weights in each layer for pruning. The limitations of these algorithms reduce the level of achievable sparsity. In addition, many algorithms still require pre-trained dense models and thus suffer from large memory footprint. In this paper, we propose a novel scheduled grow-and-prune (GaP) methodology without having to pre-train a dense model. It addresses the shortcomings of the previous works by repeatedly growing a subset of layers to dense and then pruning them back to sparse after some training. Experiments show that the models pruned using the proposed methods match or beat the quality of the highly optimized dense models at 80% sparsity on a variety of tasks, such as image classification, objective detection, 3D object part segmentation, and translation. They also outperform other state-of-the-art (SOTA) methods for model sparsification. As an example, a 90% non-uniform sparse ResNet-50 model obtained via GaP achieves 77.9% top-1 accuracy on ImageNet, improving the previous SOTA results by 1.5%. Code available at: https://github.com/boone891214/GaP.

cs.CV↗

arXiv2022

Graph Convolution for Re-ranking in Person Re-identification

Nowadays, deep learning is widely applied to extract features for similarity computation in person re-identification (re-ID) and have achieved great success. However, due to the non-overlapping between training and testing IDs, the difference between the data used for model training and the testing data makes the performance of learned feature degraded during testing. Hence, re-ranking is proposed to mitigate this issue and various algorithms have been developed. However, most of existing re-ranking methods focus on replacing the Euclidean distance with sophisticated distance metrics, which are not friendly to downstream tasks and hard to be used for fast retrieval of massive data in real applications. In this work, we propose a graph-based re-ranking method to improve learned features while still keeping Euclidean distance as the similarity metric. Inspired by graph convolution networks, we develop an operator to propagate features over an appropriate graph. Since graph is the essential key for the propagation, two important criteria are considered for designing the graph, and three different graphs are explored accordingly. Furthermore, a simple yet effective method is proposed to generate a profile vector for each tracklet in videos, which helps extend our method to video re-ID. Extensive experiments on three benchmark data sets, e.g., Market-1501, Duke, and MARS, demonstrate the effectiveness of our proposed approach.

cs.CV↗

arXiv2022

Scaled ReLU Matters for Training Vision Transformers

Vision transformers (ViTs) have been an alternative design paradigm to convolutional neural networks (CNNs). However, the training of ViTs is much harder than CNNs, as it is sensitive to the training parameters, such as learning rate, optimizer and warmup epoch. The reasons for training difficulty are empirically analysed in ~\cite{xiao2021early}, and the authors conjecture that the issue lies with the \textit{patchify-stem} of ViT models and propose that early convolutions help transformers see better. In this paper, we further investigate this problem and extend the above conclusion: only early convolutions do not help for stable training, but the scaled ReLU operation in the \textit{convolutional stem} (\textit{conv-stem}) matters. We verify, both theoretically and empirically, that scaled ReLU in \textit{conv-stem} not only improves training stabilization, but also increases the diversity of patch tokens, thus boosting peak performance with a large margin via adding few parameters and flops. In addition, extensive experiments are conducted to demonstrate that previous ViTs are far from being well trained, further showing that ViTs have great potential to be a better substitute of CNNs.

cs.CV↗

arXiv2022

Learning Accurate Entropy Model with Global Reference for Image Compression

In recent deep image compression neural networks, the entropy model plays a critical role in estimating the prior distribution of deep image encodings. Existing methods combine hyperprior with local context in the entropy estimation function. This greatly limits their performance due to the absence of a global vision. In this work, we propose a novel Global Reference Model for image compression to effectively leverage both the local and the global context information, leading to an enhanced compression rate. The proposed method scans decoded latents and then finds the most relevant latent to assist the distribution estimating of the current latent. A by-product of this work is the innovation of a mean-shifting GDN module that further improves the performance. Experimental results demonstrate that the proposed model outperforms the rate-distortion performance of most of the state-of-the-art methods in the industry.

eess.IV↗

arXiv2021

ELSA: Enhanced Local Self-Attention for Vision Transformer

Self-attention is powerful in modeling long-range dependencies, but it is weak in local finer-level feature learning. The performance of local self-attention (LSA) is just on par with convolution and inferior to dynamic filters, which puzzles researchers on whether to use LSA or its counterparts, which one is better, and what makes LSA mediocre. To clarify these, we comprehensively investigate LSA and its counterparts from two sides: \emph{channel setting} and \emph{spatial processing}. We find that the devil lies in the generation and application of spatial attention, where relative position embeddings and the neighboring filter application are key factors. Based on these findings, we propose the enhanced local self-attention (ELSA) with Hadamard attention and the ghost head. Hadamard attention introduces the Hadamard product to efficiently generate attention in the neighboring case, while maintaining the high-order mapping. The ghost head combines attention maps with static matrices to increase channel capacity. Experiments demonstrate the effectiveness of ELSA. Without architecture / hyperparameter modification, drop-in replacing LSA with ELSA boosts Swin Transformer \cite{swin} by up to +1.4 on top-1 accuracy. ELSA also consistently benefits VOLO \cite{volo} from D1 to D5, where ELSA-VOLO-D5 achieves 87.2 on the ImageNet-1K without extra training images. In addition, we evaluate ELSA in downstream tasks. ELSA significantly improves the baseline by up to +1.9 box Ap / +1.3 mask Ap on the COCO, and by up to +1.9 mIoU on the ADE20K. Code is available at \url{https://github.com/damo-cv/ELSA}.

cs.CV↗

arXiv2021

Decoupling and Recoupling Spatiotemporal Representation for RGB-D-based Motion Recognition

Decoupling spatiotemporal representation refers to decomposing the spatial and temporal features into dimension-independent factors. Although previous RGB-D-based motion recognition methods have achieved promising performance through the tightly coupled multi-modal spatiotemporal representation, they still suffer from (i) optimization difficulty under small data setting due to the tightly spatiotemporal-entangled modeling;(ii) information redundancy as it usually contains lots of marginal information that is weakly relevant to classification; and (iii) low interaction between multi-modal spatiotemporal information caused by insufficient late fusion. To alleviate these drawbacks, we propose to decouple and recouple spatiotemporal representation for RGB-D-based motion recognition. Specifically, we disentangle the task of learning spatiotemporal representation into 3 sub-tasks: (1) Learning high-quality and dimension independent features through a decoupled spatial and temporal modeling network. (2) Recoupling the decoupled representation to establish stronger space-time dependency. (3) Introducing a Cross-modal Adaptive Posterior Fusion (CAPF) mechanism to capture cross-modal spatiotemporal information from RGB-D data. Seamless combination of these novel designs forms a robust spatialtemporal representation and achieves better performance than state-of-the-art methods on four public motion datasets. Our code is available at https://github.com/damo-cv/MotionRGBD.

cs.CV↗

arXiv2021

A Novel Convergence Analysis for Algorithms of the Adam Family

Since its invention in 2014, the Adam optimizer has received tremendous attention. On one hand, it has been widely used in deep learning and many variants have been proposed, while on the other hand their theoretical convergence property remains to be a mystery. It is far from satisfactory in the sense that some studies require strong assumptions about the updates, which are not necessarily applicable in practice, while other studies still follow the original problematic convergence analysis of Adam, which was shown to be not sufficient to ensure convergence. Although rigorous convergence analysis exists for Adam, they impose specific requirements on the update of the adaptive step size, which are not generic enough to cover many other variants of Adam. To address theses issues, in this extended abstract, we present a simple and generic proof of convergence for a family of Adam-style methods (including Adam, AMSGrad, Adabound, etc.). Our analysis only requires an increasing or large "momentum" parameter for the first-order moment, which is indeed the case used in practice, and a boundness condition on the adaptive factor of the step size, which applies to all variants of Adam under mild conditions of stochastic gradients. We also establish a variance diminishing result for the used stochastic gradient estimators. Indeed, our analysis of Adam is so simple and generic that it can be leveraged to establish the convergence for solving a broader family of non-convex optimization problems, including min-max, compositional, and bilevel optimization problems. For the full (earlier) version of this extended abstract, please refer to arXiv:2104.14840.

cs.LG↗

arXiv2021

ParamCrop: Parametric Cubic Cropping for Video Contrastive Learning

The central idea of contrastive learning is to discriminate between different instances and force different views from the same instance to share the same representation. To avoid trivial solutions, augmentation plays an important role in generating different views, among which random cropping is shown to be effective for the model to learn a generalized and robust representation. Commonly used random crop operation keeps the distribution of the difference between two views unchanged along the training process. In this work, we show that adaptively controlling the disparity between two augmented views along the training process enhances the quality of the learned representation. Specifically, we present a parametric cubic cropping operation, ParamCrop, for video contrastive learning, which automatically crops a 3D cubic by differentiable 3D affine transformations. ParamCrop is trained simultaneously with the video backbone using an adversarial objective and learns an optimal cropping strategy from the data. The visualizations show that ParamCrop adaptively controls the center distance and the IoU between two augmented views, and the learned change in the disparity along the training process is beneficial to learning a strong representation. Extensive ablation studies demonstrate the effectiveness of the proposed ParamCrop on multiple contrastive learning frameworks and video backbones. Codes and models will be available.

cs.CV↗

arXiv2021

Self-Supervised Pre-Training for Transformer-Based Person Re-Identification

Transformer-based supervised pre-training achieves great performance in person re-identification (ReID). However, due to the domain gap between ImageNet and ReID datasets, it usually needs a larger pre-training dataset (e.g. ImageNet-21K) to boost the performance because of the strong data fitting ability of the transformer. To address this challenge, this work targets to mitigate the gap between the pre-training and ReID datasets from the perspective of data and model structure, respectively. We first investigate self-supervised learning (SSL) methods with Vision Transformer (ViT) pretrained on unlabelled person images (the LUPerson dataset), and empirically find it significantly surpasses ImageNet supervised pre-training models on ReID tasks. To further reduce the domain gap and accelerate the pre-training, the Catastrophic Forgetting Score (CFS) is proposed to evaluate the gap between pre-training and fine-tuning data. Based on CFS, a subset is selected via sampling relevant data close to the down-stream ReID data and filtering irrelevant data from the pre-training dataset. For the model structure, a ReID-specific module named IBN-based convolution stem (ICS) is proposed to bridge the domain gap by learning more invariant features. Extensive experiments have been conducted to fine-tune the pre-training models under supervised learning, unsupervised domain adaptation (UDA), and unsupervised learning (USL) settings. We successfully downscale the LUPerson dataset to 50% with no performance degradation. Finally, we achieve state-of-the-art performance on Market-1501 and MSMT17. For example, our ViT-S/16 achieves 91.3%/89.9%/89.6% mAP accuracy on Market1501 for supervised/UDA/USL ReID. Codes and models will be released to https://github.com/michuanhaohao/TransReID-SSL.

cs.CV↗

arXiv2021

Achieving Human Parity on Visual Question Answering

The Visual Question Answering (VQA) task utilizes both visual image and language analysis to answer a textual question with respect to an image. It has been a popular research topic with an increasing number of real-world applications in the last decade. This paper describes our recent research of AliceMind-MMU (ALIbaba's Collection of Encoder-decoders from Machine IntelligeNce lab of Damo academy - MultiMedia Understanding) that obtains similar or even slightly better results than human being does on VQA. This is achieved by systematically improving the VQA pipeline including: (1) pre-training with comprehensive visual and textual feature representation; (2) effective cross-modal interaction with learning to attend; and (3) A novel knowledge mining framework with specialized expert modules for the complex VQA task. Treating different types of visual questions with corresponding expertise needed plays an important role in boosting the performance of our VQA architecture up to the human level. An extensive set of experiments and analysis are conducted to demonstrate the effectiveness of the new research work.

cs.CL↗

arXiv2021

An Online Method for A Class of Distributionally Robust Optimization with Non-Convex Objectives

In this paper, we propose a practical online method for solving a class of distributionally robust optimization (DRO) with non-convex objectives, which has important applications in machine learning for improving the robustness of neural networks. In the literature, most methods for solving DRO are based on stochastic primal-dual methods. However, primal-dual methods for DRO suffer from several drawbacks: (1) manipulating a high-dimensional dual variable corresponding to the size of data is time expensive; (2) they are not friendly to online learning where data is coming sequentially. To address these issues, we consider a class of DRO with an KL divergence regularization on the dual variables, transform the min-max problem into a compositional minimization problem, and propose practical duality-free online stochastic methods without requiring a large mini-batch size. We establish the state-of-the-art complexities of the proposed methods with and without a Polyak-Łojasiewicz (PL) condition of the objective. Empirical studies on large-scale deep learning tasks (i) demonstrate that our method can speed up the training by more than 2 times than baseline methods and save days of training time on a large-scale dataset with $\sim$ 265K images, and (ii) verify the supreme performance of DRO over Empirical Risk Minimization (ERM) on imbalanced datasets. Of independent interest, the proposed method can be also used for solving a family of stochastic compositional problems with state-of-the-art complexities.

cs.LG↗

arXiv2021

Dash: Semi-Supervised Learning with Dynamic Thresholding

While semi-supervised learning (SSL) has received tremendous attentions in many machine learning tasks due to its successful use of unlabeled data, existing SSL algorithms use either all unlabeled examples or the unlabeled examples with a fixed high-confidence prediction during the training progress. However, it is possible that too many correct/wrong pseudo labeled examples are eliminated/selected. In this work we develop a simple yet powerful framework, whose key idea is to select a subset of training examples from the unlabeled data when performing existing SSL methods so that only the unlabeled examples with pseudo labels related to the labeled data will be used to train models. The selection is performed at each updating iteration by only keeping the examples whose losses are smaller than a given threshold that is dynamically adjusted through the iteration. Our proposed approach, Dash, enjoys its adaptivity in terms of unlabeled data selection and its theoretical guarantee. Specifically, we theoretically establish the convergence rate of Dash from the view of non-convex optimization. Finally, we empirically demonstrate the effectiveness of the proposed method in comparison with state-of-the-art over benchmarks.

cs.LG↗

arXiv2021

Weakly Supervised Representation Learning with Coarse Labels

With the development of computational power and techniques for data collection, deep learning demonstrates a superior performance over most existing algorithms on visual benchmark data sets. Many efforts have been devoted to studying the mechanism of deep learning. One important observation is that deep learning can learn the discriminative patterns from raw materials directly in a task-dependent manner. Therefore, the representations obtained by deep learning outperform hand-crafted features significantly. However, for some real-world applications, it is too expensive to collect the task-specific labels, such as visual search in online shopping. Compared to the limited availability of these task-specific labels, their coarse-class labels are much more affordable, but representations learned from them can be suboptimal for the target task. To mitigate this challenge, we propose an algorithm to learn the fine-grained patterns for the target task, when only its coarse-class labels are available. More importantly, we provide a theoretical guarantee for this. Extensive experiments on real-world data sets demonstrate that the proposed method can significantly improve the performance of learned representations on the target task, when only coarse-class information is available for training. Code is available at \url{https://github.com/idstcv/CoIns}.

cs.CV↗

arXiv2021

Zen-NAS: A Zero-Shot NAS for High-Performance Deep Image Recognition

Accuracy predictor is a key component in Neural Architecture Search (NAS) for ranking architectures. Building a high-quality accuracy predictor usually costs enormous computation. To address this issue, instead of using an accuracy predictor, we propose a novel zero-shot index dubbed Zen-Score to rank the architectures. The Zen-Score represents the network expressivity and positively correlates with the model accuracy. The calculation of Zen-Score only takes a few forward inferences through a randomly initialized network, without training network parameters. Built upon the Zen-Score, we further propose a new NAS algorithm, termed as Zen-NAS, by maximizing the Zen-Score of the target network under given inference budgets. Within less than half GPU day, Zen-NAS is able to directly search high performance architectures in a data-free style. Comparing with previous NAS methods, the proposed Zen-NAS is magnitude times faster on multiple server-side and mobile-side GPU platforms with state-of-the-art accuracy on ImageNet. Our source code and pre-trained models are released on https://github.com/idstcv/ZenNAS.

cs.CV↗

arXiv2021

Why Does Multi-Epoch Training Help?

Stochastic gradient descent (SGD) has become the most attractive optimization method in training large-scale deep neural networks due to its simplicity, low computational cost in each updating step, and good performance. Standard excess risk bounds show that SGD only needs to take one pass over the training data and more passes could not help to improve the performance. Empirically, it has been observed that SGD taking more than one pass over the training data (multi-pass SGD) has much better excess risk bound performance than the SGD only taking one pass over the training data (one-pass SGD). However, it is not very clear that how to explain this phenomenon in theory. In this paper, we provide some theoretical evidences for explaining why multiple passes over the training data can help improve performance under certain circumstance. Specifically, we consider smooth risk minimization problems whose objective function is non-convex least squared loss. Under Polyak-Lojasiewicz (PL) condition, we establish faster convergence rate of excess risk bound for multi-pass SGD than that for one-pass SGD.

cs.LG↗