PyTorchKR Papers

최신 논문

총 2,786편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2209.14996

Multiple Modes for Continual Learning

Adapting model parameters to incoming streams of data is a crucial factor to deep learning scalability. Interestingly, prior continual learning strategies in online settings inadvertently anchor their updated parameters to a local parameter subspace to remember old tasks, else drift away from the subspace and forget. From this observation, we formulate a trade-off between constructing multiple parameter modes and allocating tasks per mode. Mode-Optimized Task Allocation (MOTA), our contributed adaptation strategy, trains multiple modes in parallel, then optimizes task allocation per mode. We empirically demonstrate improvements over baseline continual learning strategies and across varying distribution shifts, namely sub-population, domain, and task shift.

arXiv:2209.15007공식 코드 · Papers with Code

Understanding Collapse in Non-Contrastive Siamese Representation Learning

Contrastive methods have led a recent surge in the performance of self-supervised representation learning (SSL). Recent methods like BYOL or SimSiam purportedly distill these contrastive methods down to their essence, removing bells and whistles, including the negative examples, that do not contribute to downstream performance. These "non-contrastive" methods work surprisingly well without using negatives even though the global minimum lies at trivial collapse. We empirically analyze these non-contrastive methods and find that SimSiam is extraordinarily sensitive to dataset and model size. In particular, SimSiam representations undergo partial dimensional collapse if the model is too small relative to the dataset size. We propose a metric to measure the degree of this collapse and show that it can be used to forecast the downstream task performance without any fine-tuning or labels. We further analyze architectural design choices and their effect on the downstream performance. Finally, we demonstrate that shifting to a continual learning setting acts as a regularizer and prevents collapse, and a hybrid between continual and multi-epoch training can improve linear probe accuracy by as many as 18 percentage points using ResNet-18 on ImageNet. Our project page is at https://alexanderli.com/noncontrastive-ssl/.

arXiv:2209.14774공식 코드 · Papers with Code

RECALL: Rehearsal-free Continual Learning for Object Classification

Convolutional neural networks show remarkable results in classification but struggle with learning new things on the fly. We present a novel rehearsal-free approach, where a deep neural network is continually learning new unseen object categories without saving any data of prior sequences. Our approach is called RECALL, as the network recalls categories by calculating logits for old categories before training new ones. These are then used during training to avoid changing the old categories. For each new sequence, a new head is added to accommodate the new categories. To mitigate forgetting, we present a regularization strategy where we replace the classification with a regression. Moreover, for the known categories, we propose a Mahalanobis loss that includes the variances to account for the changing densities between known and unknown categories. Finally, we present a novel dataset for continual learning, especially suited for object recognition on a mobile robot (HOWS-CL-25), including 150,795 synthetic images of 25 household object categories. Our approach RECALL outperforms the current state of the art on CORe50 and iCIFAR-100 and reaches the best performance on HOWS-CL-25.

arXiv:2209.13900

Disentangling Transfer in Continual Reinforcement Learning

The ability of continual learning systems to transfer knowledge from previously seen tasks in order to maximize performance on new tasks is a significant challenge for the field, limiting the applicability of continual learning solutions to realistic scenarios. Consequently, this study aims to broaden our understanding of transfer and its driving forces in the specific case of continual reinforcement learning. We adopt SAC as the underlying RL algorithm and Continual World as a suite of continuous control tasks. We systematically study how different components of SAC (the actor and the critic, exploration, and data) affect transfer efficacy, and we provide recommendations regarding various modeling options. The best set of choices, dubbed ClonEx-SAC, is evaluated on the recent Continual World benchmark. ClonEx-SAC achieves 87% final success rate compared to 80% of PackNet, the best method in the benchmark. Moreover, the transfer grows from 0.18 to 0.54 according to the metric provided by Continual World.

arXiv:2209.13917공식 코드 · Papers with Code

A simple but strong baseline for online continual learning: Repeated Augmented Rehearsal

Online continual learning (OCL) aims to train neural networks incrementally from a non-stationary data stream with a single pass through data. Rehearsal-based methods attempt to approximate the observed input distributions over time with a small memory and revisit them later to avoid forgetting. Despite its strong empirical performance, rehearsal methods still suffer from a poor approximation of the loss landscape of past data with memory samples. This paper revisits the rehearsal dynamics in online settings. We provide theoretical insights on the inherent memory overfitting risk from the viewpoint of biased and dynamic empirical risk minimization, and examine the merits and limits of repeated rehearsal. Inspired by our analysis, a simple and intuitive baseline, Repeated Augmented Rehearsal (RAR), is designed to address the underfitting-overfitting dilemma of online rehearsal. Surprisingly, across four rather different OCL benchmarks, this simple baseline outperforms vanilla rehearsal by 9%-17% and also significantly improves state-of-the-art rehearsal-based methods MIR, ASER, and SCR. We also demonstrate that RAR successfully achieves an accurate approximation of the loss landscape of past data and high-loss ridge aversion in its learning trajectory. Extensive ablation studies are conducted to study the interplay between repeated and augmented rehearsal and reinforcement learning (RL) is applied to dynamically adjust the hyperparameters of RAR to balance the stability-plasticity trade-off online. Code is available at https://github.com/YaqianZhang/RepeatedAugmentedRehearsal

arXiv:2209.12241공식 코드 · Papers with Code

Exploring Example Influence in Continual Learning

Continual Learning (CL) sequentially learns new tasks like human beings, with the goal to achieve better Stability (S, remembering past tasks) and Plasticity (P, adapting to new tasks). Due to the fact that past training data is not available, it is valuable to explore the influence difference on S and P among training examples, which may improve the learning pattern towards better SP. Inspired by Influence Function (IF), we first study example influence via adding perturbation to example weight and computing the influence derivation. To avoid the storage and calculation burden of Hessian inverse in neural networks, we propose a simple yet effective MetaSP algorithm to simulate the two key steps in the computation of IF and obtain the S- and P-aware example influence. Moreover, we propose to fuse two kinds of example influence by solving a dual-objective optimization problem, and obtain a fused influence towards SP Pareto optimality. The fused influence can be used to control the update of model and optimize the storage of rehearsal. Empirical results show that our algorithm significantly outperforms state-of-the-art methods on both task- and class-incremental benchmark CL datasets.

arXiv:2209.11469

Optimizing Class Distribution in Memory for Multi-Label Online Continual Learning

Online continual learning, especially when task identities and task boundaries are unavailable, is a challenging continual learning setting. One representative kind of methods for online continual learning is replay-based methods, in which a replay buffer called memory is maintained to keep a small part of past samples for overcoming catastrophic forgetting. When tackling with online continual learning, most existing replay-based methods focus on single-label problems in which each sample in the data stream has only one label. But multi-label problems may also happen in the online continual learning setting in which each sample may have more than one label. In the online setting with multi-label samples, the class distribution in data stream is typically highly imbalanced, and it is challenging to control class distribution in memory since changing the number of samples belonging to one class may affect the number of samples belonging to other classes. But class distribution in memory is critical for replay-based memory to get good performance, especially when the class distribution in data stream is highly imbalanced. In this paper, we propose a simple but effective method, called optimizing class distribution in memory (OCDM), for multi-label online continual learning. OCDM formulates the memory update mechanism as an optimization problem and updates the memory by solving this problem. Experiments on two widely used multi-label datasets show that OCDM can control the class distribution in memory well and can outperform other state-of-the-art methods.

arXiv:2209.09839공식 코드 · Papers with Code

Improving Replay-Based Continual Semantic Segmentation with Smart Data Selection

Continual learning for Semantic Segmentation (CSS) is a rapidly emerging field, in which the capabilities of the segmentation model are incrementally improved by learning new classes or new domains. A central challenge in Continual Learning is overcoming the effects of catastrophic forgetting, which refers to the sudden drop in accuracy on previously learned tasks after the model is trained on new classes or domains. In continual classification this challenge is often overcome by replaying a small selection of samples from previous tasks, however replay is rarely considered in CSS. Therefore, we investigate the influences of various replay strategies for semantic segmentation and evaluate them in class- and domain-incremental settings. Our findings suggest that in a class-incremental setting, it is critical to achieve a uniform distribution for the different classes in the buffer to avoid a bias towards newly learned classes. In the domain-incremental setting, it is most effective to select buffer samples by uniformly sampling from the distribution of learned feature representations or by choosing samples with median entropy. Finally, we observe that the effective sampling methods help to decrease the representation shift significantly in early layers, which is a major cause of forgetting in domain-incremental learning.

arXiv:2209.09476공식 코드 · Papers with Code

SparCL: Sparse Continual Learning on the Edge

Existing work in continual learning (CL) focuses on mitigating catastrophic forgetting, i.e., model performance deterioration on past tasks when learning a new task. However, the training efficiency of a CL system is under-investigated, which limits the real-world application of CL systems under resource-limited scenarios. In this work, we propose a novel framework called Sparse Continual Learning(SparCL), which is the first study that leverages sparsity to enable cost-effective continual learning on edge devices. SparCL achieves both training acceleration and accuracy preservation through the synergy of three aspects: weight sparsity, data efficiency, and gradient sparsity. Specifically, we propose task-aware dynamic masking (TDM) to learn a sparse network throughout the entire CL process, dynamic data removal (DDR) to remove less informative training data, and dynamic gradient masking (DGM) to sparsify the gradient updates. Each of them not only improves efficiency, but also further mitigates catastrophic forgetting. SparCL consistently improves the training efficiency of existing state-of-the-art (SOTA) CL methods by at most 23X less training FLOPs, and, surprisingly, further improves the SOTA accuracy by at most 1.7%. SparCL also outperforms competitive baselines obtained from adapting SOTA sparse training methods to the CL setting in both efficiency and accuracy. We also evaluate the effectiveness of SparCL on a real mobile phone, further indicating the practical potential of our method.

arXiv:2209.08660공식 코드 · Papers with Code

Learn the Time to Learn: Replay Scheduling in Continual Learning

Replay methods are known to be successful at mitigating catastrophic forgetting in continual learning scenarios despite having limited access to historical data. However, storing historical data is cheap in many real-world settings, yet replaying all historical data is often prohibited due to processing time constraints. In such settings, we propose that continual learning systems should learn the time to learn and schedule which tasks to replay at different time steps. We first demonstrate the benefits of our proposal by using Monte Carlo tree search to find a proper replay schedule, and show that the found replay schedules can outperform fixed scheduling policies when combined with various replay methods in different continual learning settings. Additionally, we propose a framework for learning replay scheduling policies with reinforcement learning. We show that the learned policies can generalize better in new continual learning scenarios compared to equally replaying all seen tasks, without added computational cost. Our study reveals the importance of learning the time to learn in continual learning, which brings current research closer to real-world needs.

arXiv:2209.08709

BOME! Bilevel Optimization Made Easy: A Simple First-Order Approach

Bilevel optimization (BO) is useful for solving a variety of important machine learning problems including but not limited to hyperparameter optimization, meta-learning, continual learning, and reinforcement learning. Conventional BO methods need to differentiate through the low-level optimization process with implicit differentiation, which requires expensive calculations related to the Hessian matrix. There has been a recent quest for first-order methods for BO, but the methods proposed to date tend to be complicated and impractical for large-scale deep learning applications. In this work, we propose a simple first-order BO algorithm that depends only on first-order gradient information, requires no implicit differentiation, and is practical and efficient for large-scale non-convex functions in deep learning. We provide non-asymptotic convergence analysis of the proposed method to stationary points for non-convex objectives and present empirical results that show its superior practical performance.

arXiv:2209.07863공식 코드 · Papers with Code

Expanding continual few-shot learning benchmarks to include recognition of specific instances

Continual learning and few-shot learning are important frontiers in progress toward broader Machine Learning (ML) capabilities. Recently, there has been intense interest in combining both. One of the first examples to do so was the Continual few-shot Learning (CFSL) framework of Antoniou et al. arXiv:2004.11967. In this study, we extend CFSL in two ways that capture a broader range of challenges, important for intelligent agent behaviour in real-world conditions. First, we increased the number of classes by an order of magnitude, making the results more comparable to standard continual learning experiments. Second, we introduced an 'instance test' which requires recognition of specific instances of classes -- a capability of animal cognition that is usually neglected in ML. For an initial exploration of ML model performance under these conditions, we selected representative baseline models from the original CFSL work and added a model variant with replay. As expected, learning more classes is more difficult than the original CFSL experiments, and interestingly, the way in which image instances and classes are presented affects classification performance. Surprisingly, accuracy in the baseline instance test is comparable to other classification tasks, but poor given significant occlusion and noise. The use of replay for consolidation substantially improves performance for both types of tasks, but particularly for the instance test.

arXiv:2209.07712

Continual Learning with Dependency Preserving Hypernetworks

Humans learn continually throughout their lifespan by accumulating diverse knowledge and fine-tuning it for future tasks. When presented with a similar goal, neural networks suffer from catastrophic forgetting if data distributions across sequential tasks are not stationary over the course of learning. An effective approach to address such continual learning (CL) problems is to use hypernetworks which generate task dependent weights for a target network. However, the continual learning performance of existing hypernetwork based approaches are affected by the assumption of independence of the weights across the layers in order to maintain parameter efficiency. To address this limitation, we propose a novel approach that uses a dependency preserving hypernetwork to generate weights for the target network while also maintaining the parameter efficiency. We propose to use recurrent neural network (RNN) based hypernetwork that can generate layer weights efficiently while allowing for dependencies across them. In addition, we propose novel regularisation and network growth techniques for the RNN based hypernetwork to further improve the continual learning performance. To demonstrate the effectiveness of the proposed methods, we conducted experiments on several image classification continual learning tasks and settings. We found that the proposed methods based on the RNN hypernetworks outperformed the baselines in all these CL settings and tasks.

arXiv:2209.08023

Continual Learning for Class- and Domain-Incremental Semantic Segmentation

The field of continual deep learning is an emerging field and a lot of progress has been made. However, concurrently most of the approaches are only tested on the task of image classification, which is not relevant in the field of intelligent vehicles. Only recently approaches for class-incremental semantic segmentation were proposed. However, all of those approaches are based on some form of knowledge distillation. At the moment there are no investigations on replay-based approaches that are commonly used for object recognition in a continual setting. At the same time while unsupervised domain adaption for semantic segmentation gained a lot of traction, investigations regarding domain-incremental learning in an continual setting is not well-studied. Therefore, the goal of our work is to evaluate and adapt established solutions for continual object recognition to the task of semantic segmentation and to provide baseline methods and evaluation protocols for the task of continual semantic segmentation. We firstly introduce evaluation protocols for the class- and domain-incremental segmentation and analyze selected approaches. We show that the nature of the task of semantic segmentation changes which methods are most effective in mitigating forgetting compared to image classification. Especially, in class-incremental learning knowledge distillation proves to be a vital tool, whereas in domain-incremental learning replay methods are the most effective method.

arXiv:2209.06107

Online Continual Learning via the Meta-learning Update with Multi-scale Knowledge Distillation and Data Augmentation

Continual learning aims to rapidly and continually learn the current task from a sequence of tasks. Compared to other kinds of methods, the methods based on experience replay have shown great advantages to overcome catastrophic forgetting. One common limitation of this method is the data imbalance between the previous and current tasks, which would further aggravate forgetting. Moreover, how to effectively address the stability-plasticity dilemma in this setting is also an urgent problem to be solved. In this paper, we overcome these challenges by proposing a novel framework called Meta-learning update via Multi-scale Knowledge Distillation and Data Augmentation (MMKDDA). Specifically, we apply multiscale knowledge distillation to grasp the evolution of long-range and short-range spatial relationships at different feature levels to alleviate the problem of data imbalance. Besides, our method mixes the samples from the episodic memory and current task in the online continual training procedure, thus alleviating the side influence due to the change of probability distribution. Moreover, we optimize our model via the meta-learning update resorting to the number of tasks seen previously, which is helpful to keep a better balance between stability and plasticity. Finally, our experimental evaluation on four benchmark datasets shows the effectiveness of the proposed MMKDDA framework against other popular baselines, and ablation studies are also conducted to further analyze the role of each component in our framework.

arXiv:2209.05946공식 코드 · Papers with Code

OmDet: Large-scale vision-language multi-dataset pre-training with multimodal detection network

The advancement of object detection (OD) in open-vocabulary and open-world scenarios is a critical challenge in computer vision. This work introduces OmDet, a novel language-aware object detection architecture, and an innovative training mechanism that harnesses continual learning and multi-dataset vision-language pre-training. Leveraging natural language as a universal knowledge representation, OmDet accumulates a "visual vocabulary" from diverse datasets, unifying the task as a language-conditioned detection framework. Our multimodal detection network (MDN) overcomes the challenges of multi-dataset joint training and generalizes to numerous training datasets without manual label taxonomy merging. We demonstrate superior performance of OmDet over strong baselines in object detection in the wild, open-vocabulary detection, and phrase grounding, achieving state-of-the-art results. Ablation studies reveal the impact of scaling the pre-training visual vocabulary, indicating a promising direction for further expansion to larger datasets. The effectiveness of our deep fusion approach is underscored by its ability to learn jointly from multiple datasets, enhancing performance through knowledge sharing.

arXiv:2209.05245

Continual learning benefits from multiple sleep mechanisms: NREM, REM, and Synaptic Downscaling

Learning new tasks and skills in succession without losing prior learning (i.e., catastrophic forgetting) is a computational challenge for both artificial and biological neural networks, yet artificial systems struggle to achieve parity with their biological analogues. Mammalian brains employ numerous neural operations in support of continual learning during sleep. These are ripe for artificial adaptation. Here, we investigate how modeling three distinct components of mammalian sleep together affects continual learning in artificial neural networks: (1) a veridical memory replay process observed during non-rapid eye movement (NREM) sleep; (2) a generative memory replay process linked to REM sleep; and (3) a synaptic downscaling process which has been proposed to tune signal-to-noise ratios and support neural upkeep. We find benefits from the inclusion of all three sleep components when evaluating performance on a continual learning CIFAR-100 image classification benchmark. Maximum accuracy improved during training and catastrophic forgetting was reduced during later tasks. While some catastrophic forgetting persisted over the course of network training, higher levels of synaptic downscaling lead to better retention of early tasks and further facilitated the recovery of early task accuracy during subsequent training. One key takeaway is that there is a trade-off at hand when considering the level of synaptic downscaling to use - more aggressive downscaling better protects early tasks, but less downscaling enhances the ability to learn new tasks. Intermediate levels can strike a balance with the highest overall accuracies during training. Overall, our results both provide insight into how to adapt sleep components to enhance artificial continual learning systems and highlight areas for future neuroscientific sleep research to further such systems.

arXiv:2209.04840

Continual Learning for Pose-Agnostic Object Recognition in 3D Point Clouds

Continual Learning aims to learn multiple incoming new tasks continually, and to keep the performance of learned tasks at a consistent level. However, existing research on continual learning assumes the pose of the object is pre-defined and well-aligned. For practical application, this work focuses on pose-agnostic continual learning tasks, where the object's pose changes dynamically and unpredictably. The point cloud augmentation adopted from past approaches would sharply rise with the task increment in the continual learning process. To address this problem, we inject the equivariance as the additional prior knowledge into the networks. We proposed a novel continual learning model that effectively distillates previous tasks' geometric equivariance information. The experiments show that our method overcomes the challenge of pose-agnostic scenarios in several mainstream point cloud datasets. We further conduct ablation studies to evaluate the validation of each component of our approach.

arXiv:2209.04425

The Role Of Biology In Deep Learning

Artificial neural networks took a lot of inspiration from their biological counterparts in becoming our best machine perceptual systems. This work summarizes some of that history and incorporates modern theoretical neuroscience into experiments with artificial neural networks from the field of deep learning. Specifically, iterative magnitude pruning is used to train sparsely connected networks with 33x fewer weights without loss in performance. These are used to test and ultimately reject the hypothesis that weight sparsity alone improves image noise robustness. Recent work mitigated catastrophic forgetting using weight sparsity, activation sparsity, and active dendrite modeling. This paper replicates those findings, and extends the method to train convolutional neural networks on a more challenging continual learning task. The code has been made publicly available.

arXiv:2209.04212

Selecting Related Knowledge via Efficient Channel Attention for Online Continual Learning

Continual learning aims to learn a sequence of tasks by leveraging the knowledge acquired in the past in an online-learning manner while being able to perform well on all previous tasks, this ability is crucial to the artificial intelligence (AI) system, hence continual learning is more suitable for most real-word and complex applicative scenarios compared to the traditional learning pattern. However, the current models usually learn a generic representation base on the class label on each task and an effective strategy is selected to avoid catastrophic forgetting. We postulate that selecting the related and useful parts only from the knowledge obtained to perform each task is more effective than utilizing the whole knowledge. Based on this fact, in this paper we propose a new framework, named Selecting Related Knowledge for Online Continual Learning (SRKOCL), which incorporates an additional efficient channel attention mechanism to pick the particular related knowledge for every task. Our model also combines experience replay and knowledge distillation to circumvent the catastrophic forgetting. Finally, extensive experiments are conducted on different benchmarks and the competitive experimental results demonstrate that our proposed SRKOCL is a promised approach against the state-of-the-art.