Related papers: Are we pretraining it right? Digging deeper into v…
Generative text-to-image models enable us to synthesize unlimited amounts of images in a controllable manner, spurring many recent efforts to train vision models with synthetic data. However, every synthetic image ultimately originates from…
Vision language models (VLMs) like CLIP show stellar zero-shot capability on classification benchmarks. However, selecting the VLM with the highest performance on the unlabeled downstream task is non-trivial. Existing VLM selection methods…
Vision-language instruction tuning achieves two main purposes: learning visual concepts and learning visual skills. In this paper, we found that vision-language benchmarks fall into the dichotomy of mainly benefiting from training on…
Language model pre-training has proven to be useful in many language understanding tasks. In this paper, we investigate whether it is still helpful to add the self-training method in the pre-training step and the fine-tuning step. Towards…
Multi-camera systems are indispensable in movies, TV shows, and other media. Selecting the appropriate camera at every timestamp has a decisive impact on production quality and audience preferences. Learning-based view recommendation…
Vision Language Models (VLMs) are increasingly deployed across downstream tasks, yet their training data often encode social biases that surface in outputs. Unlike humans, who interpret images through contextual and social cues, VLMs…
Pre-trained language models have recently emerged as a powerful tool for fine-tuning a variety of language tasks. Ideally, when models are pre-trained on large amount of data, they are expected to gain implicit knowledge. In this paper, we…
With the great success of pre-trained models, the pretrain-then-finetune paradigm has been widely adopted on downstream tasks for source code understanding. However, compared to costly training a large-scale model from scratch, how to…
Self-supervised learning methods are gaining increasing traction in computer vision due to their recent success in reducing the gap with supervised learning. In natural language processing (NLP) self-supervised learning and transformers are…
We propose Strongly Supervised pre-training with ScreenShots (S4) - a novel pre-training paradigm for Vision-Language Models using data from large-scale web screenshot rendering. Using web screenshots unlocks a treasure trove of visual and…
Contrastive pretraining on image-text pairs from the web is one of the most popular large-scale pretraining strategies for vision backbones, especially in the context of large multimodal models. At the same time, image captioning on this…
In this work, we provide a broad comparative analysis of strategies for pre-training audio understanding models for several tasks in the music domain, including labelling of genre, era, origin, mood, instrumentation, key, pitch, vocal…
Since a vast number of tables can be easily collected from web pages, spreadsheets, PDFs, and various other document types, a flurry of table pre-training frameworks have been proposed following the success of text and images, and they have…
We investigate the utility of pretraining by contrastive self supervised learning on both natural-scene and medical imaging datasets when the unlabeled dataset size is small, or when the diversity within the unlabeled set does not lead to…
Pre-training on large-scale datasets and then fine-tuning on downstream tasks have become a standard practice in deep learning. However, pre-training data often contain label noise that may adversely affect the generalization of the model.…
Pretraining Neural Language Models (NLMs) over a large corpus involves chunking the text into training examples, which are contiguous text segments of sizes processable by the neural architecture. We highlight a bias introduced by this…
Medical visual question answering (Med-VQA) is a machine learning task that aims to create a system that can answer natural language questions based on given medical images. Although there has been rapid progress on the general VQA task,…
This work concerns video-language pre-training and representation learning. In this now ubiquitous training scheme, a model first performs pre-training on paired videos and text (e.g., video clips and accompanied subtitles) from a large…
Many approaches have been proposed to use diffusion models to augment training datasets for downstream tasks, such as classification. However, diffusion models are themselves trained on large datasets, often with noisy annotations, and it…
Vision-language models have become increasingly powerful for tasks that require an understanding of both visual and linguistic elements, bridging the gap between these modalities. In the context of multimodal clinical AI, there is a growing…