相关论文: The Dark Side of Dataset Scaling: Evaluating Racia…

`Scale the model, scale the data, scale the GPU-farms' is the reigning sentiment in the world of generative AI today. While model scaling has been extensively studied, data scaling and its downstream impacts remain under explored. This is…

'Scale the model, scale the data, scale the compute' is the reigning sentiment in the world of generative AI today. While the impact of model scaling has been extensively studied, we are only beginning to scratch the surface of data scaling…

We provide an empirical investigation of the potential of pre-training vision-language models on an unprecedented scale: 100 billion examples. We find that model performance tends to saturate at this scale on many common Western-centric…

We have now entered the era of trillion parameter machine learning models trained on billion-sized datasets scraped from the internet. The rise of these gargantuan datasets has given rise to formidable bodies of critical work that has…

Deep learning based visual-linguistic multimodal models such as Contrastive Language Image Pre-training (CLIP) have become increasingly popular recently and are used within text-to-image generative models such as DALL-E and Stable…

Vision-language models (VLMs) deliver strong zero-shot recognition but frequently inherit social biases from their training data. We systematically disentangle three design factors -- model size, training-data scale, and training-data…

It is well known that the usefulness of a machine learning model is due to its ability to generalize to unseen data. This study uses three popular cyberbullying datasets to explore the effects of data, how it's collected, and how it's…

Despite the remarkable performance of foundation vision-language models, the shared representation space for text and vision can also encode harmful label associations detrimental to fairness. While prior work has uncovered bias in…

Multimodal AI models capable of associating images and text hold promise for numerous domains, ranging from automated image captioning to accessibility applications for blind and low-vision users. However, uncertainty about bias has in some…

Large vision-language contrastive models (VLCMs), such as CLIP, have become foundational, demonstrating remarkable success across a variety of downstream tasks. Despite their advantages, these models, akin to other foundational systems,…

Vision-language models trained on large-scale multimodal datasets show strong demographic biases, but the role of training data in producing these biases remains unclear. A major barrier has been the lack of demographic annotations in…

Face recognition algorithms, when used in the real world, can be very useful, but they can also be dangerous when biased toward certain demographics. So, it is essential to understand how these algorithms are trained and what factors affect…

Multilingual vision-language models (VLMs) promise universal image-text retrieval, yet their social biases remain underexplored. We perform the first systematic audit of four public multilingual CLIP variants: M-CLIP, NLLB-CLIP,…

Recent advances in the development of vision-language models (VLMs) are yielding remarkable success in recognizing visual semantic content, including impressive instances of compositional image understanding. Here, we introduce the novel…

Vision-language models (VLMs) excel in zero-shot recognition but their performance varies greatly across different visual concepts. For example, although CLIP achieves impressive accuracy on ImageNet (60-80%), its performance drops below…

Large multi-modal models (LMMs) hold the potential to usher in a new era of automated visual assistance for people who are blind or low vision (BLV). Yet, these models have not been systematically evaluated on data captured by BLV users. We…

The lack of reasoning capabilities in Vision-Language Models (VLMs) has remained at the forefront of research discourse. We posit that this behavior stems from a reporting bias in their training data. That is, how people communicate about…

Pre-trained representations are becoming crucial for many NLP and perception tasks. While representation learning in NLP has transitioned to training on raw text without human annotations, visual and vision-language representations still…

Vision-Language models (VLMs) that use contrastive language-image pre-training have shown promising zero-shot classification performance. However, their performance on imbalanced dataset is relatively poor, where the distribution of classes…

Vision-language models, like CLIP (Contrastive Language Image Pretraining), are becoming increasingly popular for a wide range of multimodal retrieval tasks. However, prior work has shown that large language and deep vision models can learn…