Related papers: Efficient Test-time Adaptive Object Detection via …
Few-shot object detection (FSOD), which aims at learning a generic detector that can adapt to unseen tasks with scarce training samples, has witnessed consistent improvement recently. However, most existing methods ignore the efficiency…
The goal of the challenge is to develop a test-time adaptation (TTA) method, which could adapt the model to gradually changing domains in video sequences for semantic segmentation task. It is based on a synthetic driving video dataset -…
The performance of deep learning models depends heavily on test samples at runtime, and shifts from the training data distribution can significantly reduce accuracy. Test-time adaptation (TTA) addresses this by adapting models during…
We study the problem of few-shot out-of-distribution (OOD) detection, which aims to detect OOD samples from unseen categories during inference time with only a few labeled in-domain (ID) samples. Existing methods mainly focus on training…
Optical Coherence Tomography(OCT) is a non-invasive technique capturing cross-sectional area of the retina in micro-meter resolutions. It has been widely used as a auxiliary imaging reference to detect eye-related pathology and predict…
We present a new domain adaptive self-training pipeline, named ST3D, for unsupervised domain adaptation on 3D object detection from point clouds. First, we pre-train the 3D detector on the source domain with our proposed random object…
Fundus images are essential for the early screening and detection of eye diseases. While deep learning models using fundus images have significantly advanced the diagnosis of multiple eye diseases, variations in images from different…
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…
Segmenting images is critical for visual understanding but demands extensive pixel-level annotations. Foundational models have enabled new paradigms for predicting new classes guided by textual prompts, without annotations from the target…
Test Time Adaptation (TTA) addresses the problem of distribution shift by adapting a pretrained model to a new domain during inference. When faced with challenging shifts, most methods collapse and perform worse than the original pretrained…
The sheer size of modern neural networks makes model serving a serious computational challenge. A popular class of compression techniques overcomes this challenge by pruning or sparsifying the weights of pretrained networks. While useful,…
Convolutional neural networks (CNNs) often suffer from poor performance when tested on target data that differs from the training (source) data distribution, particularly in medical imaging applications where variations in imaging protocols…
Existing point-cloud based 3D object detectors use convolution-like operators to process information in a local neighbourhood with fixed-weight kernels and aggregate global context hierarchically. However, non-local neural networks and…
We propose a domain adaptation approach for object detection. We introduce a two-step method: the first step makes the detector robust to low-level differences and the second step adapts the classifiers to changes in the high-level…
Test-time adaptation (TTA) enables a pre-trained model to adapt online to an unlabeled test stream under distribution shift. While most TTA research focuses on the adaptation objective, practical streams also depend critically on the memory…
In this paper, we present PCoTTA, an innovative, pioneering framework for Continual Test-Time Adaptation (CoTTA) in multi-task point cloud understanding, enhancing the model's transferability towards the continually changing target domain.…
Continual Test-Time Adaptation (CTTA) aims to adapt a pretrained model to ever-changing environments during the test time under continuous domain shifts. Most existing CTTA approaches are based on the Mean Teacher (MT) structure, which…
Domain adaptation (DA) techniques help deep learning models generalize across data shifts for point cloud semantic segmentation (PCSS). Test-time adaptation (TTA) allows direct adaptation of a pre-trained model to unlabeled data during…
Pre-training & fine-tuning can enhance the transferring efficiency and performance in visual tasks. Recent delta-tuning methods provide more options for visual classification tasks. Despite their success, existing visual delta-tuning art…
The high computational demands of Vision Transformers (ViTs) in processing a large number of tokens often constrain their practical application in analyzing medical images. This research proposes a Prompt-driven Adaptive Token ({\it PrATo})…