Related papers: A Hierarchical Semantic Distillation Framework for…
Knowledge distillation offers a promising path to transfer reasoning capabilities from large teacher models to efficient student models; however, existing token-level on-policy distillation methods require token-level alignment between the…
While fine-tuning based methods for few-shot object detection have achieved remarkable progress, a crucial challenge that has not been addressed well is the potential class-specific overfitting on base classes and sample-specific…
An object detector's ability to detect and flag \textit{novel} objects during open-world deployments is critical for many real-world applications. Unfortunately, much of the work in open object detection today is disjointed and fails to…
Large vision-language models have achieved outstanding performance, but their size and computational requirements make their deployment on resource-constrained devices and time-sensitive tasks impractical. Model distillation, the process of…
Multimodal Large Language Models (MLLMs) still struggle with fine-grained visual understanding, where answers often depend on small but decisive evidence in the full image. We observe a regional-to-global perception gap: the same MLLM…
Image-text contrastive models like CLIP have wide applications in zero-shot classification, image-text retrieval, and transfer learning. However, they often struggle on compositional visio-linguistic tasks (e.g., attribute-binding or…
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…
State-of-the-art vision pretraining methods rely on image-level self-distillation from object-centric datasets such as ImageNet, implicitly assuming each image contains a single object. This assumption does not always hold: many ImageNet…
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…
Detecting 3D objects from multi-view images is a fundamental problem in 3D computer vision. Recently, significant breakthrough has been made in multi-view 3D detection tasks. However, the unprecedented detection performance of these vision…
Open-vocabulary semantic segmentation (OVSS) employs pixel-level vision-language alignment to associate category-related prompts with corresponding pixels. A key challenge is enhancing the multimodal dense prediction capability,…
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…
Detecting objects based on language information is a popular task that includes Open-Vocabulary object Detection (OVD) and Referring Expression Comprehension (REC). In this paper, we advance them to a more practical setting called Described…
Self-supervised representation learning has proved to be a valuable component for out-of-distribution (OoD) detection with only the texts of in-distribution (ID) examples. These approaches either train a language model from scratch or…
In real applications, new object classes often emerge after the detection model has been trained on a prepared dataset with fixed classes. Due to the storage burden and the privacy of old data, sometimes it is impractical to train the model…
Open-vocabulary 3D object detection (OV-3DDet) aims to localize and recognize both seen and previously unseen object categories within any new 3D scene. While language and vision foundation models have achieved success in handling various…
Object detection has achieved remarkable accuracy through deep learning, yet these improvements often come with increased computational cost, limiting deployment on resource-constrained devices. Knowledge Distillation (KD) provides an…
Open-vocabulary 3D instance segmentation seeks to segment and classify instances beyond the annotated label space. Existing methods typically map 3D instances to 2D RGB-D images, and then employ vision-language models (VLMs) for…
Existing studies typically investigate domain shift and category shift as independent problems, however, in real-world scenarios, the two types of shifts often occur simultaneously and interact, leading to significant degradation in…
We propose a new setting for detecting unseen objects called Zero-shot Annotation object Detection (ZAD). It expands the zero-shot object detection setting by allowing the novel objects to exist in the training images and restricts the…