Long-tailed class-incremental learning (LT-CIL) aims to learn new classes continuously from a long-tailed data stream, while simultaneously dealing with challenges such as imbalanced learning of tail classes and catastrophic for-getting. To address these challenges, most existing methods employ a two-stage strategy by initializing model training from scratch with further balanced knowledge driven cali-bration. This strategy faces challenges in deriving discrim-inative features from cold-started backbones for the long-tailed distribution of data, consequently leading to relatively diminished performance. In this paper, with the pow-erful feature extraction capability of pre-trained foundation models, we have achieved a one-stage approach that de-livers superior performance. Specifically, we propose Dy-namic Adapter Tuning (DAT), which employs a dynamic adapter cache mechanism to adapt a pre-trained model to learn tasks sequentially. The adapter in the cache is either dynamically selected or created according to task similar-ity, and further compactified with the new task's adapter to mitigate cross-task and cross-class gaps in LT-CIL, sig-nificantly alleviating catastrophic forgetting and imbalance learning issues, respectively. With extensive experimental validation, our method consistently achieves state-of-the-art performance under the challenging LT-CIL setting.

Class incremental learning (CIL) endeavors to acquire new knowledge continuously from an unending data stream while retaining previously acquired knowledge. Since the amount of new data is significantly smaller than that of old data, existing methods struggle to strike a balance between acquiring new knowledge and retaining previously learned knowledge, leading to substantial performance degradation. To tackle such a dilemma, in this paper, we propose the Contrastive Complementary Augmentation Learning (CoLA) method, which mitigates the aliasing of distributions in incremental tasks. Specifically, we introduce a novel yet effective supervised contrastive learning module with instance- and class-level augmentation during base training. For the instance-level augmentation method, we spatially segment the image at different scales, creating spatial pyramid contrastive pairs to obtain more robust feature representations. Meanwhile, the class-level augmentation method randomly mixes images within the mini-batch, facilitating the learning of compact and more easily adaptable decision boundaries. In this way, we only need to train the classifier to maintain competitive performance during the incremental phases. Furthermore, we also propose CoLA+ to further enhance the proposed method with relaxed limitations on data storage. Extensive experiments demonstrate that our method achieves state-of-the-art performance on different benchmarks.

Continual test-time domain adaptation aims to adapt a source pre-trained model to a continually changing target domain without using any source data. Unfortunately, existing methods based on pseudo-label learning suffer from the changing target domain environment, and the quality of generated pseudo-labels is attenuated due to the domain shift, leading to instantaneous negative learning and long-term knowledge forgetting. To solve these problems, in this paper, we propose a simple yet effective framework for exploring safety supervision with three elaborate strategies: Label Safety, Sample Safety, and Parameter Safety. Firstly, to select reliable pseudo-labels, we define and adjust the confidence threshold in a self-adaptive manner according to the test-time learning status. Secondly, a soft-weighted contrastive learning module is presented to explore the highly-correlated samples and discriminate uncorrelated ones, improving the instantaneous efficiency of the model. Finally, we frame a Soft Weight Alignment strategy to normalize the distance between the parameters of the adapted model and the source pre-trained model, which alleviates the long-term problem of knowledge forgetting and significantly improves the accuracy of the adapted model in the late adaptation stage. Extensive experimental results demonstrate that our method achieves state-of-the-art performance on several benchmark datasets.

Online class-incremental continual learning aims to learn new classes continually from a never-ending and single-pass data stream, while not forgetting the learned knowledge of old classes. Existing replay-based methods have shown promising performance by storing a subset of old class data. Unfortunately, these methods only focus on selecting samples from the memory bank for replay and ignore the adequate exploration of semantic information in the single-pass data stream, leading to poor classification accuracy. In this paper, we propose a novel yet effective framework for online class-incremental continual learning, which considers not only the selection of stored samples, but also the full exploration of the data stream. Specifically, we propose a gradient-based sample selection strategy, which selects the stored samples whose gradients generated in the network are most interfered by the new incoming samples. We believe such samples are beneficial for updating the neural network based on back gradient propagation. More importantly, we seek to explore the semantic information between two different views of training images by maximizing their mutual information, which is conducive to the improvement of classification accuracy. Extensive experimental results demonstrate that our method achieves state-of-the-art performance on a variety of benchmark datasets. Our code is available on https://github.com/YananGu/DVC.

Abstract Low‐light enhancement is a crucial task in computer vision because of the limited dynamic range of digital imaging devices in poor lighting conditions. Images taken under low‐light conditions often suffer from insufficient brightness and severe noise. At present, many models based on convolutional neural networks have been proposed to enhance low‐light images. However, most models treat the features on different channels equally, which is not conducive to models learning hierarchical features. Consequently, the method proposed a channel splitting attention network (CSAN) that divides the shallow features into two branches, the residual and dense branches, transmitting different information. Residual branching facilitates feature reuse, while dense branching promotes the exploration of new features. In addition, CSAN uses merge‐and‐run mappings to assist information integration between different branches and distinguishes the information contained in different branch features through an attention module designed in this paper. Multiple experiment results show that the method proposed is superior to state‐of‐the‐art methods in qualitative and quantitative evaluation. Furthermore, CSAN can better suppress chromaticity aberration while enhancing low‐light images.

Although deep neural networks have achieved amazing results on instance segmentation, they are still ill-equipped when they are required to learn new tasks incrementally. Concretely, they suffer from “catastrophic forgetting”, an abrupt degradation of performance on old classes with the initial training data missing. Moreover, they are subjected to a negative transfer problem on new classes, which renders the model unable to update its knowledge while preserving the previous knowledge. To address these problems, we propose an incremental instance segmentation method that consists of three networks: Former Teacher Network (FTN), Current Student Network (CSN) and Current Teacher Network (CTN). Specifically, FTN supervises CSN to preserve the previous knowledge, and CTN supervises CSN to adapt to new classes. The supervision of two teacher networks is achieved by a distillation loss function for instances, bounding boxes, and classes. In addition, we adjust the supervision weights of different teacher networks to balance between the knowledge preservation for former classes and the adaption to new classes. Extensive experimental results on PASCAL 2012 SBD and COCO datasets show the effectiveness of the proposed method.