Related papers: SPLAT: Semantic Pixel-Level Adaptation Transforms …
Recent advances in unsupervised domain adaptation have shown the effectiveness of adversarial training to adapt features across domains, endowing neural networks with the capability of being tested on a target domain without requiring any…
Large pre-trained vision-language models (VLMs), such as CLIP, have shown unprecedented zero-shot performance across a wide range of tasks. Nevertheless, these models may be unreliable under distributional shifts, as their performance is…
Data-driven based approaches, in spite of great success in many tasks, have poor generalization when applied to unseen image domains, and require expensive cost of annotation especially for dense pixel prediction tasks such as semantic…
Domain adaptive object detection aims to adapt detection models to domains where annotated data is unavailable. Existing methods have been proposed to address the domain gap using the semi-supervised student-teacher framework. However, a…
Autonomous robotic systems applied to new domains require an abundance of expensive, pixel-level dense labels to train robust semantic segmentation models under full supervision. This study proposes a model-agnostic Depth Edge Alignment…
Vision-language models (VLMs), e.g., CLIP, have shown remarkable potential in zero-shot image classification. However, adapting these models to new domains remains challenging, especially in unsupervised settings where labeled data is…
In the presence of large sets of labeled data, Deep Learning (DL) has accomplished extraordinary triumphs in the avenue of computer vision, particularly in object classification and recognition tasks. However, DL cannot always perform well…
Deep learning approaches for semantic segmentation rely primarily on supervised learning approaches and require substantial efforts in producing pixel-level annotations. Further, such approaches may perform poorly when applied to unseen…
Semantic segmentation is essential for comprehending images, but the process necessitates a substantial amount of detailed annotations at the pixel level. Acquiring such annotations can be costly in the real-world. Unsupervised domain…
This paper describes a novel method of training a semantic segmentation model for scene recognition of agricultural mobile robots exploiting publicly available datasets of outdoor scenes that are different from the target greenhouse…
Recently, DEtection TRansformer (DETR), an end-to-end object detection pipeline, has achieved promising performance. However, it requires large-scale labeled data and suffers from domain shift, especially when no labeled data is available…
Recent advances in deep learning have led to the development of accurate and efficient models for various computer vision applications such as classification, segmentation, and detection. However, learning highly accurate models relies on…
Many methods of semantic image segmentation have borrowed the success of open compound domain adaptation. They minimize the style gap between the images of source and target domains, more easily predicting the accurate pseudo annotations…
Vanilla pixel-level classifiers for semantic segmentation are based on a certain paradigm, involving the inner product of fixed prototypes obtained from the training set and pixel features in the test image. This approach, however,…
The generalization power of deep-learning models is dependent on rich-labelled data. This supervision using large-scaled annotated information is restrictive in most real-world scenarios where data collection and their annotation involve…
Can we detect common objects in a variety of image domains without instance-level annotations? In this paper, we present a framework for a novel task, cross-domain weakly supervised object detection, which addresses this question. For this…
Image segmentation is a powerful computer vision technique for scene understanding. However, real-world deployment is stymied by the need for high-quality, meticulously labeled datasets. Synthetic data provides high-quality labels while…
One of the key criticisms of deep learning is that large amounts of expensive and difficult-to-acquire training data are required in order to train models with high performance and good generalization capabilities. Focusing on the task of…
Domain adaptation (DA) has drawn high interests for its capacity to adapt a model trained on labeled source data to perform well on unlabeled or weakly labeled target data from a different domain. Most common DA techniques require the…
We study the domain adaptation problem with label shift in this work. Under the label shift context, the marginal distribution of the label varies across the training and testing datasets, while the conditional distribution of features…