Related papers: TRUST: Test-Time Refinement using Uncertainty-Guid…

Deep networks that rely on prototypes-interpretable representations that can be related to the model input-have gained significant attention for balancing high accuracy with inherent interpretability, which makes them suitable for critical…

Domain Generalization (DG) aims to enable models to generalize to unseen target domains by learning from multiple source domains. Existing DG methods primarily rely on convolutional neural networks (CNNs), which inherently learn texture…

Multimodal sentiment analysis (MSA) is an emerging research topic that aims to understand and recognize human sentiment or emotions through multiple modalities. However, in real-world dynamic scenarios, the distribution of target data is…

Since the era of deep learning, convolutional neural networks (CNNs) and vision transformers (ViTs) have been extensively studied and widely used in medical image classification tasks. Unfortunately, CNN's limitations in modeling long-range…

Recent advancements in State Space Models, notably Mamba, have demonstrated superior performance over the dominant Transformer models, particularly in reducing the computational complexity from quadratic to linear. Yet, difficulties in…

Test-time adaptation (TTA) aims to adapt models to maintain reliable performance on non-stationary test streams without requiring labeled data. Despite its empirical success, the learnability of TTA under non-stationary streams remains…

In the post-deep learning era, the Transformer architecture has demonstrated its powerful performance across pre-trained big models and various downstream tasks. However, the enormous computational demands of this architecture have deterred…

We present PlainMamba: a simple non-hierarchical state space model (SSM) designed for general visual recognition. The recent Mamba model has shown how SSMs can be highly competitive with other architectures on sequential data and initial…

Person re-identification (re-id), which aims to retrieve images of the same person in a given image from a database, is one of the most practical image recognition applications. In the real world, however, the environments that the images…

Transformers have demonstrated impressive results for 3D point cloud semantic segmentation. However, the quadratic complexity of transformer makes computation costs high, limiting the number of points that can be processed simultaneously…

Large pre-trained models have achieved outstanding results in sequence modeling. The Transformer block and its attention mechanism have been the main drivers of the success of these models. Recently, alternative architectures, such as…

Test-time adaptive (TTA) semantic segmentation adapts a source pre-trained image semantic segmentation model to unlabeled batches of target domain test images, different from real-world, where samples arrive one-by-one in an online fashion.…

Visual State Space Model (VMamba) has recently emerged as a promising architecture, exhibiting remarkable performance in various computer vision tasks. However, its robustness has not yet been thoroughly studied. In this paper, we delve…

Recently, test-time adaptation (TTA) has been proposed as a promising solution for addressing distribution shifts. It allows a base model to adapt to an unforeseen distribution during inference by leveraging the information from the batch…

In recent years, State Space Models (SSMs) with efficient hardware-aware designs, known as the Mamba deep learning models, have made significant progress in modeling long sequences such as language understanding. Therefore, building…

Continual Test-Time Adaptation (CTTA) task investigates effective domain adaptation under the scenario of continuous domain shifts during testing time. Due to the utilization of solely unlabeled samples, there exists significant uncertainty…

We propose Test-Time Augmentation (TTA) as an effective technique for addressing combinatorial optimization problems, including the Traveling Salesperson Problem. In general, deep learning models possessing the property of invariance, where…

Accurate medical image segmentation demands the integration of multi-scale information, spanning from local features to global dependencies. However, it is challenging for existing methods to model long-range global information, where…

Structured State Space Models (SSMs) have emerged as a transformative paradigm in sequence modeling, addressing critical limitations of Recurrent Neural Networks (RNNs) and Transformers, namely, vanishing gradients, sequential computation…

Pretrained vision-language models (VLMs) like CLIP show strong zero-shot performance but struggle with generalization under distribution shifts. Test-Time Adaptation (TTA) addresses this by adapting VLMs to unlabeled test data in new…