Related papers: Data Adaptive Traceback for Vision-Language Founda…
Low-light conditions not only hamper human visual experience but also degrade the model's performance on downstream vision tasks. While existing works make remarkable progress on day-night domain adaptation, they rely heavily on domain…
To facilitate zero-shot generalization in taskoriented dialog, this paper proposes Language Models as Data (LAD). LAD is a paradigm for creating diverse and accurate synthetic data which conveys the necessary structural constraints and can…
Pre-trained vision-language models (VLMs) like CLIP have demonstrated impressive zero-shot performance on a wide range of downstream computer vision tasks. However, there still exists a considerable performance gap between these models and…
Integrating image and text data through multi-modal learning has emerged as a new approach in medical imaging research, following its successful deployment in computer vision. While considerable efforts have been dedicated to establishing…
Pretrained on web-scale open data, VLMs offer powerful capabilities for solving downstream tasks after being adapted to task-specific labeled data. Yet, data labeling can be expensive and may demand domain expertise. Active Learning (AL)…
Adapting pre-trained models to open classes is a challenging problem in machine learning. Vision-language models fully explore the knowledge of text modality, demonstrating strong zero-shot recognition performance, which is naturally suited…
We study few-shot learning in natural language domains. Compared to many existing works that apply either metric-based or optimization-based meta-learning to image domain with low inter-task variance, we consider a more realistic setting,…
Semantic Image Interpretation is the task of extracting a structured semantic description from images. This requires the detection of visual relationships: triples (subject,relation,object) describing a semantic relation between a subject…
Domain adaptation (DA) addresses the challenge of transferring knowledge from a source domain to a target domain where image data distributions may differ. Existing DA methods often require access to source domain data, adversarial…
A large gap exists between fully-supervised object detection and weakly-supervised object detection. To narrow this gap, some methods consider knowledge transfer from additional fully-supervised dataset. But these methods do not fully…
Vision-language supervision has made remarkable strides in learning visual representations from textual guidance. In digital pathology, vision-language models (VLM), pre-trained on curated datasets of histological image-captions, have been…
Most previous few-shot learning algorithms are based on meta-training with fake few-shot tasks as training samples, where large labeled base classes are required. The trained model is also limited by the type of tasks. In this paper we…
Transferring knowledge from task-agnostic pre-trained deep models for downstream tasks is an important topic in computer vision research. Along with the growth of computational capacity, we now have open-source vision-language pre-trained…
Adversarial learning baselines for domain adaptation (DA) approaches in the context of semantic segmentation are under explored in semi-supervised framework. These baselines involve solely the available labeled target samples in the…
Recent research tries to extend image restoration capabilities from human perception to machine perception, thereby enhancing the performance of high-level vision tasks in degraded environments. These methods, primarily based on supervised…
This work proposes a robust Partial Domain Adaptation (PDA) framework that mitigates the negative transfer problem by incorporating a robust target-supervision strategy. It leverages ensemble learning and includes diverse, complementary…
Test-time task adaptation in few-shot learning aims to adapt a pre-trained task-agnostic model for capturing taskspecific knowledge of the test task, rely only on few-labeled support samples. Previous approaches generally focus on…
Change detection visual question answering (CDVQA) requires answering text queries by reasoning about semantic changes in bi-temporal remote sensing images. A straightforward approach is to boost CDVQA performance with generic…
Recent work has shown that monolingual masked language models learn to represent data-driven notions of language variation which can be used for domain-targeted training data selection. Dataset genre labels are already frequently available,…
Recent neural models for image captioning usually employ an encoder-decoder framework with an attention mechanism. However, the attention mechanism in such a framework aligns one single (attended) image feature vector to one caption word,…