Related papers: Causal-Tune: Mining Causal Factors from Vision Fou…

Foundation models leverage large-scale pretraining to capture extensive knowledge, demonstrating generalization in a wide range of language tasks. By comparison, vision foundation models (VFMs) often exhibit uneven improvements across…

Event cameras offer superior sensitivity to high-speed motion and extreme lighting, making event-based monocular depth estimation a promising approach for robust 3D perception in challenging conditions. However, progress is severely…

Video grounding aims to localize the target moment in an untrimmed video corresponding to a given sentence query. Existing methods typically select the best prediction from a set of predefined proposals or directly regress the target span…

Deep learning has led to tremendous success in computer vision, largely due to Convolutional Neural Networks (CNNs). However, CNNs have been shown to be vulnerable to crafted adversarial perturbations. This vulnerability of adversarial…

Open-vocabulary segmentation models often struggle to generalize to unseen combinations of object categories and attributes, because fine-grained descriptions are typically encoded as holistic sentences that entangle multiple semantic…

Deep neural networks often suffer performance drops when test data distribution differs from training data. Domain Generalization (DG) aims to address this by focusing on domain-invariant features or augmenting data for greater diversity.…

The clinical utility of deep learning models for medical image segmentation is severely constrained by their inability to generalize to unseen domains. This failure is often rooted in the models learning spurious correlations between…

Traditional image segmentation methods, such as variational models based on partial differential equations (PDEs), offer strong mathematical interpretability and precise boundary modeling, but often suffer from sensitivity to parameter…

Vision Foundation Models (VFMs) pretrained on massive datasets exhibit impressive performance on various downstream tasks, especially with limited labeled target data. However, due to their high inference compute cost, these models cannot…

Video captioning aims to generate natural language sentences that describe the given video accurately. Existing methods obtain favorable generation by exploring richer visual representations in encode phase or improving the decoding…

In search of robust and generalizable machine learning models, Domain Generalization (DG) has gained significant traction during the past few years. The goal in DG is to produce models which continue to perform well when presented with data…

Recent advancements in video semantic segmentation have made substantial progress by exploiting temporal correlations. Nevertheless, persistent challenges, including redundant computation and the reliability of the feature propagation…

Feature selection is a crucial preprocessing step in data analytics and machine learning. Classical feature selection algorithms select features based on the correlations between predictive features and the class variable and do not attempt…

Large Vision Language Models (VLMs) effectively bridge the modality gap through extensive pretraining, acquiring sophisticated visual representations aligned with language. However, it remains underexplored whether these representations,…

Causality knowledge is vital to building robust AI systems. Deep learning models often perform poorly on tasks that require causal reasoning, which is often derived using some form of commonsense knowledge not immediately available in the…

Classifier-Free Guidance (CFG) is a fundamental technique in training conditional diffusion models. The common practice for CFG-based training is to use a single network to learn both conditional and unconditional noise prediction, with a…

Vision-language models (VLMs) often generate massive visual tokens that greatly increase inference latency and memory footprint; while training-free token pruning offers a practical remedy, existing methods still struggle to balance local…

Recent work has empirically shown that Vision-Language Models (VLMs) struggle to fully understand the compositional properties of the human language, usually modeling an image caption as a "bag of words". As a result, they perform poorly on…

Large-scale Vision-Language Models (VLMs) have achieved notable progress in aligning visual inputs with text. However, their ability to deeply understand the unique physical properties of non-RGB vision sensor images remains limited. In…

Visual Prompt Tuning (VPT) has become a promising solution for Parameter-Efficient Fine-Tuning (PEFT) approach for Vision Transformer (ViT) models by partially fine-tuning learnable tokens while keeping most model parameters frozen. Recent…