Related papers: Comprehensive Multi-Modal Prototypes are Simple an…
Vision-language object detectors (VLODs) such as YOLO-World and Grounding DINO exhibit strong zero-shot generalization, but their performance degrades under distribution shift. Test-time adaptation (TTA) offers a practical way to adapt…
Open-Vocabulary object detectors can generalize to an unrestricted set of categories through simple textual prompting. However, adapting these models to rare classes or reinforcing their abilities on multiple specialized domains remains…
Pre-training & fine-tuning can enhance the transferring efficiency and performance in visual tasks. Recent delta-tuning methods provide more options for visual classification tasks. Despite their success, existing visual delta-tuning art…
Open-Vocabulary Object Detection (OVOD) has achieved remarkable success in generalizing to novel categories. However, this success often rests on the implicit assumption of domain stationarity. In this work, we provide a principled revisit…
Open-vocabulary object detection (OVOD) aims to detect both seen and unseen categories, yet existing methods often struggle to generalize to novel objects due to limited integration of global and local contextual cues. We propose…
Open-vocabulary 3D object detection (OV-3Det) aims to generalize beyond the limited number of base categories labeled during the training phase. The biggest bottleneck is the scarcity of annotated 3D data, whereas 2D image datasets are…
Existing open-vocabulary object detectors typically enlarge their vocabulary sizes by leveraging different forms of weak supervision. This helps generalize to novel objects at inference. Two popular forms of weak-supervision used in…
Current point-cloud detection methods have difficulty detecting the open-vocabulary objects in the real world, due to their limited generalization capability. Moreover, it is extremely laborious and expensive to collect and fully annotate a…
Vision-language models such as CLIP have boosted the performance of open-vocabulary object detection, where the detector is trained on base categories but required to detect novel categories. Existing methods leverage CLIP's strong…
In recent years, object detection has achieved significant progress, especially in the field of open-vocabulary object detection. Unlike traditional methods that rely on predefined categories, open-vocabulary approaches can detect arbitrary…
Open-vocabulary detectors are proposed to locate and recognize objects in novel classes. However, variations in vision-aware language vocabulary data used for open-vocabulary learning can lead to unfair and unreliable evaluations. Recent…
Monocular 3D object detection typically relies on pseudo-labeling techniques to reduce dependency on real-world annotations. Recent advances demonstrate that deterministic linguistic cues can serve as effective auxiliary weak supervision…
Vision-language models (VLMs) have made significant progress in image classification by training with large-scale paired image-text data. Their performances largely depend on the prompt quality. While recent methods show that visual…
Recent vision-language pre-training models have exhibited remarkable generalization ability in zero-shot recognition tasks. Previous open-vocabulary 3D scene understanding methods mostly focus on training 3D models using either image or…
Multi-camera 3D object detection aims to detect and localize objects in 3D space using multiple cameras, which has attracted more attention due to its cost-effectiveness trade-off. However, these methods often struggle with the lack of…
The choice of input text prompt plays a critical role in the performance of Vision-Language Pretrained (VLP) models such as CLIP. We present APoLLo, a unified multi-modal approach that combines Adapter and Prompt learning for…
The ability to recognize, localize and track dynamic objects in a scene is fundamental to many real-world applications, such as self-driving and robotic systems. Yet, traditional multiple object tracking (MOT) benchmarks rely only on a few…
Recent advancements in multimodal vision models have highlighted limitations in late-stage feature fusion and suboptimal query selection for hybrid prompts open-world segmentation, alongside constraints from caption-derived vocabularies. To…
Recent open-vocabulary detectors achieve promising performance with abundant region-level annotated data. In this work, we show that an open-vocabulary detector co-training with a large language model by generating image-level detailed…
In recent years, soft prompt learning methods have been proposed to fine-tune large-scale vision-language pre-trained models for various downstream tasks. These methods typically combine learnable textual tokens with class tokens as input…