Related papers: Data Efficient Language-supervised Zero-shot Recog…

Vision-language models (VLMs), such as CLIP, have demonstrated impressive zero-shot capabilities for various downstream tasks. Their performance can be further enhanced through few-shot prompt tuning methods. However, current studies…

While deep learning, including Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs), has significantly advanced classification performance, its typical reliance on extensive annotated datasets presents a major obstacle in…

Foundation models like CLIP (Contrastive Language-Image Pretraining) have revolutionized vision-language tasks by enabling zero-shot and few-shot learning through cross-modal alignment. However, their computational complexity and large…

Securing a sufficient amount of paired data is important to train an image-text retrieval (ITR) model, but collecting paired data is very expensive. To address this issue, in this paper, we propose an active learning algorithm for ITR that…

Contrastive language-image pre-training (CLIP) has demonstrated remarkable zero-shot classification ability, namely image classification using novel text labels. Existing works have attempted to enhance CLIP by fine-tuning on downstream…

Recent years have witnessed an increasing interest in image-text contrastive modeling, exemplified by models such as Contrastive Language-Image Pretraining (CLIP). In this paper, we propose the TernaryCLIP, a lightweight computational…

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…

Contrastive Language-Image Pre-training (CLIP) has been the cornerstone for zero-shot classification, text-image retrieval, and text-image generation by aligning image and text modalities. Despite its widespread adoption, a significant…

In the field of vision-language contrastive learning, models such as CLIP capitalize on matched image-caption pairs as positive examples and leverage within-batch non-matching pairs as negatives. This approach has led to remarkable outcomes…

Recent works in dataset distillation seek to minimize training expenses by generating a condensed synthetic dataset that encapsulates the information present in a larger real dataset. These approaches ultimately aim to attain test accuracy…

Automatically describing audio-visual content with texts, namely video captioning, has received significant attention due to its potential applications across diverse fields. Deep neural networks are the dominant methods, offering…

Vision-language models pre-trained at large scale have shown unprecedented adaptability and generalization to downstream tasks. Although its discriminative potential has been widely explored, its reliability and uncertainty are still…

Global visual localization in LiDAR-maps, crucial for autonomous driving applications, remains largely unexplored due to the challenging issue of bridging the cross-modal heterogeneity gap. Popular multi-modal learning approach Contrastive…

Dataset distillation has emerged as a technique aiming to condense informative features from large, natural datasets into a compact and synthetic form. While recent advancements have refined this technique, its performance is bottlenecked…

Autonomous offroad driving is essential for applications like emergency rescue, military operations, and agriculture. Despite progress, systems struggle with high-speed vehicles exceeding 10m/s due to the need for accurate long-range (>…

Out-of-distribution detection (OOD) is a pivotal task for real-world applications that trains models to identify samples that are distributionally different from the in-distribution (ID) data during testing. Recent advances in AI,…

Contrastive pre-training on image-text pairs, exemplified by CLIP, becomes a standard technique for learning multi-modal visual-language representations. Although CLIP has demonstrated remarkable performance, training it from scratch on…

As pretrained transformer language models continue to achieve state-of-the-art performance, the Natural Language Processing community has pushed for advances in model compression and efficient attention mechanisms to address high…

Recent advances in training vision-language models have demonstrated unprecedented robustness and transfer learning effectiveness; however, standard computer vision datasets are image-only, and therefore not well adapted to such training…

When deployed for risk-sensitive tasks, deep neural networks must be able to detect instances with labels from outside the distribution for which they were trained. In this paper we present a novel framework to benchmark the ability of…