Related papers: Understanding and Mitigating Miscalibration in Pro…
Calibrating deep learning models to yield uncertainty-aware predictions is crucial as deep neural networks get increasingly deployed in safety-critical applications. While existing post-hoc calibration methods achieve impressive results on…
Though CLIP-based prompt tuning significantly enhances pre-trained Vision-Language Models, existing research focuses on reconstructing the model architecture, e.g., additional loss calculation and meta-networks. These approaches generally…
Recent vision language models (VLMs) like CLIP have demonstrated impressive anomaly detection performance under significant distribution shift by utilizing high-level semantic information through text prompts. However, these models often…
Deep neural networks (DNNs) have made great strides in pushing the state-of-the-art in several challenging domains. Recent studies reveal that they are prone to making overconfident predictions. This greatly reduces the overall trust in…
Medical Vision-Language Models (Med-VLMs) have demonstrated remarkable performance across diverse medical imaging tasks by leveraging large-scale image-text pretraining. However, their confidence calibration is largely unexplored, and so…
Large-scale vision-language models (VLMs) such as CLIP exhibit strong zero-shot generalization, but adapting them to downstream tasks typically requires costly labeled data. Existing unsupervised self-training methods rely on…
One of the key technologies for the success of Large Language Models (LLMs) is preference alignment. However, a notable side effect of preference alignment is poor calibration: while the pre-trained models are typically well-calibrated,…
Contrastive language image pre-training (CLIP) is an essential component of building modern vision-language foundation models. While CLIP demonstrates remarkable zero-shot performance on downstream tasks, the multi-modal feature spaces…
Foundation models like CLIP and SAM have advanced computer vision and medical imaging via low-shot transfer learning, aiding CADD with limited data. However, their deployment faces two key challenges. \textit{distribution shift} where…
Vision-language models such as CLIP learn a generic text-image embedding from large-scale training data. A vision-language model can be adapted to a new classification task through few-shot prompt tuning. We find that such a prompt tuning…
Transfer learning enables the sharing of common knowledge among models for a variety of downstream tasks, but traditional methods suffer in limited training data settings and produce narrow models incapable of effectively generalizing under…
Post-training improves large language models (LLMs) but often worsens confidence calibration, leading to systematic overconfidence. Recent unsupervised post-hoc methods for post-trained LMs (PoLMs) mitigate this by aligning PoLM confidence…
Fine-tuned Large Language Models (LLMs) often demonstrate poor calibration, with their confidence scores misaligned with actual performance. While calibration has been extensively studied in models trained from scratch, the impact of LLMs'…
Deep neural networks (DNNs) have enabled astounding progress in several vision-based problems. Despite showing high predictive accuracy, recently, several works have revealed that they tend to provide overconfident predictions and thus are…
Few-shot, fine-grained classification in computer vision poses significant challenges due to the need to differentiate subtle class distinctions with limited data. This paper presents a novel method that enhances the Contrastive…
Prompt tuning, which adapts vision-language models by freezing model parameters and optimizing only the prompt, has proven effective for task-specific adaptations. The core challenge in prompt tuning is improving specialization for a…
Despite the recent progress in incremental learning, addressing catastrophic forgetting under distributional drift is still an open and important problem. Indeed, while state-of-the-art domain incremental learning (DIL) methods perform…
Contrastive Language-Image Pre-trained (CLIP) models have zero-shot ability of classifying an image belonging to "[CLASS]" by using similarity between the image and the prompt sentence "a [CONTEXT] of [CLASS]". Based on exhaustive text cues…
Dual-encoder Vision-Language Models (VLMs) such as CLIP are often characterized as bag-of-words systems due to their poor performance on compositional benchmarks. We argue that this limitation may stem less from deficient representations…
Model calibration aims to align confidence with prediction correctness. The Cross-Entropy (CE) loss is widely used for calibrator training, which enforces the model to increase confidence on the ground truth class. However, we find the CE…