Related papers: Robustifying Vision Transformer without Retraining…

Prior to the deployment of robotic systems, pre-training the deep-recognition models on all potential visual cases is infeasible in practice. Hence, test-time adaptation (TTA) allows the model to adapt itself to novel environments and…

Visual-language models (VLMs) like CLIP exhibit strong generalization but struggle with distribution shifts at test time. Existing training-free test-time adaptation (TTA) methods operate strictly within CLIP's original feature space,…

Machine learning methods strive to acquire a robust model during the training process that can effectively generalize to test samples, even in the presence of distribution shifts. However, these methods often suffer from performance…

We present CLAMP-ViT, a data-free post-training quantization method for vision transformers (ViTs). We identify the limitations of recent techniques, notably their inability to leverage meaningful inter-patch relationships, leading to the…

We propose an adaptation to the training of Vision Transformers (ViTs) that allows for an explicit modeling of objects during the attention computation. This is achieved by adding a new branch to selected attention layers that computes an…

Visual domain adaptation (DA) seeks to transfer trained models to unseen, unlabeled domains across distribution shift, but approaches typically focus on adapting convolutional neural network architectures initialized with supervised…

Transformers have emerged as a competitive alternative to convnets in vision tasks, yet they lack the architectural inductive bias of convnets, which may hinder their potential performance. Specifically, Vision Transformers (ViTs) are not…

Pre-trained vision-language models (VLMs), exemplified by CLIP, demonstrate remarkable adaptability across zero-shot classification tasks without additional training. However, their performance diminishes in the presence of domain shifts.…

Vision Transformer(ViT) is one of the most widely used models in the computer vision field with its great performance on various tasks. In order to fully utilize the ViT-based architecture in various applications, proper visualization…

Vision Transformers (ViTs) have achieved state-of-the-art performance in image classification, yet their attention mechanisms often remain opaque and exhibit dense, non-structured behaviors. In this work, we adapt our previously proposed…

Contrastive Language-Image Pretraining (CLIP) excels at learning generalizable image representations but often falls short in zero-shot inference on certain downstream datasets. Test-time adaptation (TTA) mitigates this issue by adjusting…

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…

Continual Test-Time Adaptation (CTTA) is an emerging and challenging task where a model trained in a source domain must adapt to continuously changing conditions during testing, without access to the original source data. CTTA is prone to…

Vision Transformer (ViT) models, utilizing self-attention mechanisms, have demonstrated robust generalization capabilities across various vision tasks, including image classification. However, these models, typically pretrained on general…

Vision-language models (VLMs) such as CLIP achieve strong zero-shot recognition but degrade significantly under \textit{temporally evolving distribution shifts} common in real-world scenarios (e.g., gradual illumination or seasonal…

Recently, plain vision Transformers (ViTs) have shown impressive performance on various computer vision tasks, thanks to their strong modeling capacity and large-scale pretraining. However, they have not yet conquered the problem of image…

Face anti-spoofing (FAS) or presentation attack detection is an essential component of face recognition systems deployed in security-critical applications. Existing FAS methods have poor generalizability to unseen spoof types, camera…

Video editing is a critical component of content creation that transforms raw footage into coherent works aligned with specific visual and narrative objectives. Existing approaches face two major challenges: temporal inconsistencies due to…

We propose a low-rank adaptation method for training privacy-preserving vision transformer (ViT) models that efficiently freezes pre-trained ViT model weights. In the proposed method, trainable rank decomposition matrices are injected into…

Fully test-time adaptation aims to adapt the network model based on sequential analysis of input samples during the inference stage to address the cross-domain performance degradation problem of deep neural networks. This work is based on…