Understanding and improving visual prompting: A label-map** perspective
We revisit and advance visual prompting (VP), an input prompting technique for vision tasks.
VP can reprogram a fixed, pre-trained source model to accomplish downstream tasks in the …
VP can reprogram a fixed, pre-trained source model to accomplish downstream tasks in the …
Model sparsity can simplify machine unlearning
In response to recent data regulation requirements, machine unlearning (MU) has emerged
as a critical process to remove the influence of specific examples from a given model …
as a critical process to remove the influence of specific examples from a given model …
Unleashing the power of data tsunami: A comprehensive survey on data assessment and selection for instruction tuning of language models
Instruction tuning plays a critical role in aligning large language models (LLMs) with human
preference. Despite the vast amount of open instruction datasets, naively training a LLM on …
preference. Despite the vast amount of open instruction datasets, naively training a LLM on …
When does bias transfer in transfer learning?
Using transfer learning to adapt a pre-trained" source model" to a downstream" target task"
can dramatically increase performance with seemingly no downside. In this work, we …
can dramatically increase performance with seemingly no downside. In this work, we …
On the trade-off of intra-/inter-class diversity for supervised pre-training
Pre-training datasets are critical for building state-of-the-art machine learning models,
motivating rigorous study on their impact on downstream tasks. In this work, we study the …
motivating rigorous study on their impact on downstream tasks. In this work, we study the …
Discovering bugs in vision models using off-the-shelf image generation and captioning
Automatically discovering failures in vision models under real-world settings remains an
open challenge. This work demonstrates how off-the-shelf, large-scale, image-to-text and …
open challenge. This work demonstrates how off-the-shelf, large-scale, image-to-text and …
Selectivity drives productivity: efficient dataset pruning for enhanced transfer learning
Massive data is often considered essential for deep learning applications, but it also incurs
significant computational and infrastructural costs. Therefore, dataset pruning (DP) has …
significant computational and infrastructural costs. Therefore, dataset pruning (DP) has …
Know your self-supervised learning: A survey on image-based generative and discriminative training
Although supervised learning has been highly successful in improving the state-of-the-art in
the domain of image-based computer vision in the past, the margin of improvement has …
the domain of image-based computer vision in the past, the margin of improvement has …