相关论文: Class-Aware Prototype Learning with Negative Contr…

Vision-language models (VLMs), such as CLIP, have gained popularity for their strong open vocabulary classification performance, but they are prone to assigning high confidence scores to misclassifications, limiting their reliability in…

Lifelong learning is critical for embodied agents in open-world environments, where reinforcement learning fine-tuning has emerged as an important paradigm to enable Vision-Language-Action (VLA) models to master dexterous manipulation…

Learning discriminative 3D representations that generalize well to unknown testing categories is an emerging requirement for many real-world 3D applications. Existing well-established methods often struggle to attain this goal due to…

Test-time adaptation (TTA) aims to adapt a model, initially trained on training data, to test data with potential distribution shifts. Most existing TTA methods focus on classification problems. The pronounced success of classification…

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…

Contrastive Self-supervised Learning (CSL) is a practical solution that learns meaningful visual representations from massive data in an unsupervised approach. The ordinary CSL embeds the features extracted from neural networks onto…

Pretrained VLMs exhibit strong zero-shot classification capabilities, but their predictions degrade significantly under common image corruptions. To improve robustness, many test-time adaptation (TTA) methods adopt positive data…

Vision-language-action (VLA) models achieve strong in-distribution performance but degrade sharply under novel camera viewpoints and visual perturbations. We show that this brittleness primarily arises from misalignment in Spatial Modeling,…

Vision-language representation learning largely benefits from image-text alignment through contrastive losses (e.g., InfoNCE loss). The success of this alignment strategy is attributed to its capability in maximizing the mutual information…

Vision-language pre-training (VLP) methods are blossoming recently, and its crucial goal is to jointly learn visual and textual features via a transformer-based architecture, demonstrating promising improvements on a variety of…

Visual Place Recognition (VPR) has evolved from handcrafted descriptors to deep learning approaches, yet significant challenges remain. Current approaches, including Vision Foundation Models (VFMs) and Multimodal Large Language Models…

Test-time adaptation paradigm provides flexibility towards domain shifts by performing immediate adaptation on unlabeled target data from the source model. Vision-Language Models (VLMs) leverage their generalization capabilities for diverse…

Convolutional neural networks (CNNs) have been widely used for image classification. Despite its high accuracies, CNN has been shown to be easily fooled by some adversarial examples, indicating that CNN is not robust enough for pattern…

Visual Question Answering (VQA) systems are notoriously brittle under distribution shifts and data scarcity. While previous solutions-such as ensemble methods and data augmentation-can improve performance in isolation, they fail to…

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…

Vision-Language Models (VLMs) show promise as zero-shot goal-conditioned value functions, but their frozen pre-trained representations limit generalization and temporal reasoning. We introduce VITA, a zero-shot value function learning…

Large-scale pretrained vision-language models like CLIP have demonstrated remarkable zero-shot image classification capabilities across diverse domains. To enhance CLIP's performance while preserving the zero-shot paradigm, various…

While Large Language Models (LLMs) have exhibited remarkable emergent capabilities through extensive pre-training, they still face critical limitations in generalizing to specialized domains and handling diverse linguistic variations, known…

Test-time adaptation (TTA) aims to adapt a pre-trained model to a new test domain without access to source data after deployment. Existing approaches typically rely on self-training with pseudo-labels since ground-truth cannot be obtained…

Novel Class Discovery aims to utilise prior knowledge of known classes to classify and discover unknown classes from unlabelled data. Existing NCD methods for images primarily rely on visual features, which suffer from limitations such as…