In Cross-Modal Domain-Incremental learning, the primary challenge lies in learning from varying data distributions and maintaining its performance on prior domains. However, existing methods often overlook the importance of shared knowledge across domains and the interaction between modalities is still insufficient. To address these issues, we propose Cross-Domain Consistency and Bidirectional Alignment (C2BA), a novel framework that enhances the model's generalization ability and improves the cross-modal integration in VLMs through two key components. We design a Cross-domain Global Consistency Constraint (CGCC) to stabilize domain-invariant representations during incremental training, preventing excessive shifts of shared distributions toward new domains. In addition, we design a Bidirectional Cross-Modal Attention (BCMA) module, which enables effective interaction between visual and textual features through a bidirectional attention mechanism, thereby reducing cross-modal discrepancies. Experiments on three benchmark datasets demonstrate that our method outperforms state-of-the-art exemplar-free and even exemplar-based approaches, achieving superior generalization and cross-modal interaction.

Source-free domain adaptation (SFDA), where only a pre-trained source model is used to adapt to the target distribution, is a more general approach to achieving domain adaptation in the real world. However, it can be challenging to capture the inherent structure of the target features accurately due to the lack of supervised information on the target domain. By analyzing the clustering performance of the target features, we show that they still contain core features related to discriminative attributes but lack the collation of semantic information. Inspired by this insight, we present Chaos to Order (CtO), a novel approach for SFDA that strives to constrain semantic credibility and propagate label information among target subpopulations. CtO divides the target data into inner and outlier samples based on the adaptive threshold of the learning state, customizing the learning strategy to fit the data properties best. Specifically, inner samples are utilized for learning intra-class structure thanks to their relatively well-clustered properties. The low-density outlier samples are regularized by input consistency to achieve high accuracy with respect to the ground truth labels. In CtO, by employing different learning strategies to propagate the labels from the inner local to outlier instances, it clusters the global samples from chaos to order. We further adaptively regulate the neighborhood affinity of the inner samples to constrain the local semantic credibility. In theoretical and empirical analyses, we demonstrate that our algorithm not only propagates from inner to outlier but also prevents local clustering from forming spurious clusters. Empirical evidence demonstrates that CtO outperforms the state of the arts on three public benchmarks: Office-31, Office-Home, and VisDA.

Automated driving object detection has always been a challenging task in computer vision due to environmental uncertainties. These uncertainties include significant differences in object sizes and encountering the class unseen. It may result in poor performance when traditional object detection models are directly applied to automated driving detection. Because they usually presume fixed categories of common traffic participants, such as pedestrians and cars. Worsely, the huge class imbalance between common and novel classes further exacerbates performance degradation. To address the issues stated, we propose OpenNet to moderate the class imbalance with the Balanced Loss, which is based on Cross Entropy Loss. Besides, we adopt an inductive layer based on gradient reshaping to fast learn new classes with limited samples during incremental learning. To against catastrophic forgetting, we employ normalized feature distillation. By the way, we improve multi-scale detection robustness and unknown class recognition through FPN and energy-based detection, respectively. The Experimental results upon the CODA dataset show that the proposed method can obtain better performance than that of the existing methods.

Deep reinforcement learning (RL) has achieved re-markable performance in sequential decision-making problems. However, it is a challenge for deep RL methods to extract task-relevant semantic information when interacting with limited data from the environment. In this paper, we propose Mix-up Consistent Cross Representations (MCCR), a novel self-supervised auxiliary task, which aims to improve data efficiency and encourage representation prediction. Specifically, we calculate the contrastive loss between low-dimensional and high-dimensional representations of different state observations to boost the mutual information between states, thus improving data efficiency. Furthermore, we employ a mixed strategy to generate intermediate samples, increasing data diversity and the smoothness of representations prediction in nearby timesteps. Experimental results show that MCCR achieves competitive results over the state-of-the-art approaches for complex control tasks in DeepMind Control Suite, notably improving the ability of pretrained encoders to generalize to unseen tasks.

Imporving the generalization ability of an agent is an important and challenging task in deep reinforcement learning (RL). Procedually generated environment is an important benchmark for testing generalization in deep RL. In this benchmark, each game consists of multiple levels, each level is an algorithmically created environment instance with a unique configuration of its factors of variation. Existing methods (e.g., regularization, data augmentation) for improving the generalization of RL agent do not learn well the invariant representation among multiple levels. Besides, existing methods for learning invariant representations in RL using adversarial training can only learn invariant information across two levels. To solve this problem, we propose Adversarial Discriminative Feature Separate (ADFS). First, ADFS design a new discriminator for distinguishing whether two observations belong to the same level. Thus, the policy encoder is encouraged to learn invariant information between multiple levels. Second, it separates the representation of observation into level-invariant features and level-discriminative features, so that correction of the optimization direction of the discriminator. The discriminative features are learned by reducing the similarity of specific features intra-levels and increasing that of inter-levels, respectively. Experimental results demonstrate that our method is quite competitive with existing state-of-the-art methods on Procgen Benchmark.

While Deep Neural Networks (DNNs) are achieving state-of-the-art performance on medical domains across a variety of tasks, the need for explainability of model predictions in these high-stakes tasks is still lacking. Current for the explainability in model predictions potentially relies on the supervised counterfactual generation that is time-consuming and direction uncontrollable. Yet, the counterfactual generation needs to be easy to implement and have a controllable direction. In light of this trend, we propose an approach for the unsupervised latent direction search of black-box models that are steerable to the user by enabling the user to effectively explore counterfactual generation in a directional way, without relying on domain- or data-specific assumptions. To identify these explainable directions, we use Principal Component Analysis (PCA), a general manifold learning framework to extract low-dimensional subspaces based on a local noise injection of the pre-trained generative model, so that a small perturbation in the subspaces would provide enough change in the resulting data. With experiments on three real-world CXR datasets involving 6 tasks, we find that our approach is capable of learning explainable predictions that discard unrelated confounding factors. Moreover, our method enables practitioners to edit directions to better understand which features are used for predictions.