Related papers: Conformal Prediction for Zero-Shot Models
The learning objective of vision-language approach of CLIP does not effectively account for the noisy many-to-many correspondences found in web-harvested image captioning datasets, which contributes to its compute and data inefficiency. To…
Class-incremental learning (CIL) enables models to continuously learn new categories from sequential tasks without forgetting previously acquired knowledge. While recent advances in vision-language models such as CLIP have demonstrated…
Deep Learning (DL) is undergoing a paradigm shift with the emergence of foundation models. In this work, we focus on Contrastive Language-Image Pre-training (CLIP), a Vision-Language foundation model that achieves high accuracy across…
This paper considers contrastive training for cross-modal 0-shot transfer wherein a pre-trained model in one modality is used for representation learning in another domain using pairwise data. The learnt models in the latter domain can then…
Vision-language foundation models have been incredibly successful in a wide range of downstream computer vision tasks using adaptation methods. However, due to the high cost of obtaining pre-training datasets, pairs with weak image-text…
Annotating 3D LiDAR point clouds for perception tasks is fundamental for many applications e.g., autonomous driving, yet it still remains notoriously labor-intensive. Pretraining-finetuning approach can alleviate the labeling burden by…
Image-text contrastive learning models such as CLIP have demonstrated strong task transfer ability. The high generality and usability of these visual models is achieved via a web-scale data collection process to ensure broad concept…
The potential for zero-shot generalization in vision-language (V-L) models such as CLIP has spurred their widespread adoption in addressing numerous downstream tasks. Previous methods have employed test-time prompt tuning to adapt the model…
Foundation models have exhibited unprecedented capabilities in tackling many domains and tasks. Models such as CLIP are currently widely used to bridge cross-modal representations, and text-to-image diffusion models are arguably the leading…
Long-tailed multi-label visual recognition poses a significant challenge, as images typically contain multiple labels with highly imbalanced class distributions, leading to biased models that favor head classes while underperforming on tail…
Deep neural networks have achieved remarkable success across a variety of tasks, yet they often suffer from unreliable probability estimates. As a result, they can be overconfident in their predictions. Conformal Prediction (CP) offers a…
Conformal prediction is a distribution-free uncertainty quantification method that has gained popularity in the machine learning community due to its finite-sample guarantees and ease of use. Its most common variant, dubbed split conformal…
Pre-trained vision-language models (e.g., CLIP) have shown promising zero-shot generalization in many downstream tasks with properly designed text prompts. Instead of relying on hand-engineered prompts, recent works learn prompts using the…
Pre-trained vision-language models such as contrastive language-image pre-training (CLIP) have demonstrated a remarkable generalizability, which has enabled a wide range of applications represented by zero-shot classification. However,…
Contrastive Vision-Language Pre-training(CLIP) demonstrates impressive zero-shot capability. The key to improve the adaptation of CLIP to downstream task with few exemplars lies in how to effectively model and transfer the useful knowledge…
Transduction is a powerful paradigm that leverages the structure of unlabeled data to boost predictive accuracy. We present TransCLIP, a novel and computationally efficient transductive approach designed for Vision-Language Models (VLMs).…
Contrastive vision-language models (e.g. CLIP) are typically created by updating all the parameters of a vision model and language model through contrastive training. Can such models be created by a small number of parameter updates to an…
Traditional 3D segmentation methods can only recognize a fixed range of classes that appear in the training set, which limits their application in real-world scenarios due to the lack of generalization ability. Large-scale visual-language…
Calibration of deep learning models is crucial to their trustworthiness and safe usage, and as such, has been extensively studied in supervised classification models, with methods crafted to decrease miscalibration. However, there has yet…
This paper addresses the critical issue of miscalibration in CLIP-based model adaptation, particularly in the challenging scenario of out-of-distribution (OOD) samples, which has been overlooked in the existing literature on CLIP…