Related papers: SegDebias: Test-Time Bias Mitigation for ViT-Based…
Recent approaches have shown that large-scale vision-language models such as CLIP can improve semantic segmentation performance. These methods typically aim for pixel-level vision-language alignment, but often rely on low resolution image…
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…
Pretrained vision-language models, such as CLIP, show promising zero-shot performance across a wide variety of datasets. For closed-set classification tasks, however, there is an inherent limitation: CLIP image encoders are typically…
Despite the success of large-scale pretrained Vision-Language Models (VLMs) especially CLIP in various open-vocabulary tasks, their application to semantic segmentation remains challenging, producing noisy segmentation maps with…
Vision-Language Models like CLIP create aligned embedding spaces for text and images, making it possible for anyone to build a visual classifier by simply naming the classes they want to distinguish. However, a model that works well in one…
Large-scale vision-language models such as CLIP achieve strong zero-shot recognition but struggle with classes that are rarely seen during pretraining, including newly emerging entities and culturally specific categories. We introduce…
The CLIP model has demonstrated significant advancements in aligning visual and language modalities through large-scale pre-training on image-text pairs, enabling strong zero-shot classification and retrieval capabilities on various…
Vision-language foundation models have exhibited remarkable success across a multitude of downstream tasks due to their scalability on extensive image-text paired data. However, these models also display significant limitations when applied…
Dense visual prediction tasks have been constrained by their reliance on predefined categories, limiting their applicability in real-world scenarios where visual concepts are unbounded. While Vision-Language Models (VLMs) like CLIP have…
Vision models with high overall accuracy often exhibit systematic errors in specific scenarios, posing potential serious safety concerns. Diagnosing bugs of vision models is gaining increased attention, however traditional diagnostic…
Multi-label classification is crucial for comprehensive image understanding, yet acquiring accurate annotations is challenging and costly. To address this, a recent study suggests exploiting unsupervised multi-label classification…
Vision-language model (VLM) embeddings have been shown to encode biases present in their training data, such as societal biases that prescribe negative characteristics to members of various racial and gender identities. VLMs are being…
The Contrastive Language-Image Pre-Training (CLIP) model excels in few-shot learning by aligning visual and textual representations. Our study shows that template-sample similarity (TSS), defined as the resemblance between a text template…
Multimodal models like CLIP have gained significant attention due to their remarkable zero-shot performance across various tasks. However, studies have revealed that CLIP can inadvertently learn spurious associations between target…
Vision-language models, such as CLIP, have shown impressive generalization capacities when using appropriate text descriptions. While optimizing prompts on downstream labeled data has proven effective in improving performance, these methods…
Vision-language models (VLMs) like CLIP exhibit strong zero-shot capabilities but often fail to generalize under distribution shifts. Test-time adaptation (TTA) allows models to update at inference time without labeled data, typically via…
Labeling large image datasets with attributes such as facial age or object type is tedious and sometimes infeasible. Supervised machine learning methods provide a highly accurate solution, but require manual labels which are often…
The emergence of CLIP has opened the way for open-world image perception. The zero-shot classification capabilities of the model are impressive but are harder to use for dense tasks such as image segmentation. Several methods have proposed…
Pre-trained vision-language models learn massive data to model unified representations of images and natural languages, which can be widely applied to downstream machine learning tasks. In addition to zero-shot inference, in order to better…
With the popularity of foundational models, parameter efficient fine tuning has become the defacto approach to leverage pretrained models to perform downstream tasks. Taking inspiration from recent advances in large language models, Visual…