Deep class-incremental learning: A survey
Deep models, eg, CNNs and Vision Transformers, have achieved impressive achievements
in many vision tasks in the closed world. However, novel classes emerge from time to time in …
in many vision tasks in the closed world. However, novel classes emerge from time to time in …
Fine-tuning can distort pretrained features and underperform out-of-distribution
When transferring a pretrained model to a downstream task, two popular methods are full
fine-tuning (updating all the model parameters) and linear probing (updating only the last …
fine-tuning (updating all the model parameters) and linear probing (updating only the last …
Optimizing prompts for text-to-image generation
Well-designed prompts can guide text-to-image models to generate amazing images.
However, the performant prompts are often model-specific and misaligned with user input …
However, the performant prompts are often model-specific and misaligned with user input …
Lst: Ladder side-tuning for parameter and memory efficient transfer learning
Fine-tuning large pre-trained models on downstream tasks has been adopted in a variety of
domains recently. However, it is costly to update the entire parameter set of large pre-trained …
domains recently. However, it is costly to update the entire parameter set of large pre-trained …
Robust fine-tuning of zero-shot models
Large pre-trained models such as CLIP or ALIGN offer consistent accuracy across a range of
data distributions when performing zero-shot inference (ie, without fine-tuning on a specific …
data distributions when performing zero-shot inference (ie, without fine-tuning on a specific …
Vl-adapter: Parameter-efficient transfer learning for vision-and-language tasks
Recently, fine-tuning language models pre-trained on large text corpora have provided huge
improvements on vision-and-language (V&L) tasks as well as on pure language tasks …
improvements on vision-and-language (V&L) tasks as well as on pure language tasks …
Is synthetic data from generative models ready for image recognition?
Recent text-to-image generation models have shown promising results in generating high-
fidelity photo-realistic images. Though the results are astonishing to human eyes, how …
fidelity photo-realistic images. Though the results are astonishing to human eyes, how …
Self-regulating prompts: Foundational model adaptation without forgetting
Prompt learning has emerged as an efficient alternative for fine-tuning foundational models,
such as CLIP, for various downstream tasks. Conventionally trained using the task-specific …
such as CLIP, for various downstream tasks. Conventionally trained using the task-specific …
Prompting visual-language models for efficient video understanding
Image-based visual-language (I-VL) pre-training has shown great success for learning joint
visual-textual representations from large-scale web data, revealing remarkable ability for …
visual-textual representations from large-scale web data, revealing remarkable ability for …
Exploring visual prompts for adapting large-scale models
H Bahng, A Jahanian, S Sankaranarayanan… - arXiv preprint arXiv …, 2022 - arxiv.org
We investigate the efficacy of visual prompting to adapt large-scale models in vision.
Following the recent approach from prompt tuning and adversarial reprogramming, we learn …
Following the recent approach from prompt tuning and adversarial reprogramming, we learn …