Related papers: Interpretable Foreground Object Search As Knowledg…
Few-shot object detection (FSOD) aims to detect objects with limited samples for novel classes, while relying on abundant data for base classes. Existing FSOD approaches, predominantly built on the Faster R-CNN detector, entangle objectness…
Open-world object detection (OWOD) requires incrementally detecting known categories while reliably identifying unknown objects. Existing methods primarily focus on improving unknown recall, yet overlook interpretability, often leading to…
Overlapping object perception aims to decouple the randomly overlapping foreground-background features, extracting foreground features while suppressing background features, which holds significant application value in fields such as…
Enabling Visual Semantic Models to effectively handle multi-view description matching has been a longstanding challenge. Existing methods typically learn a set of embeddings to find the optimal match for each view's text and compute…
The goal of few-shot fine-grained image classification is to recognize rarely seen fine-grained objects in the query set, given only a few samples of this class in the support set. Previous works focus on learning discriminative image…
Current multi-modal models exhibit a notable misalignment with the human visual system when identifying objects that are visually assimilated into the background. Our observations reveal that these multi-modal models cannot distinguish…
Recent advances in self-supervised visual representation learning have paved the way for unsupervised methods tackling tasks such as object discovery and instance segmentation. However, discovering objects in an image with no supervision is…
Long document retrieval aims to fetch query-relevant documents from a large-scale collection, where knowledge distillation has become de facto to improve a retriever by mimicking a heterogeneous yet powerful cross-encoder. However, in…
Due to the high inter-class similarity caused by the complex composition and the co-existing objects across scenes, numerous studies have explored object semantic knowledge within scenes to improve scene recognition. However, a resulting…
Image classification is a fundamental computer vision task and an important baseline for deep metric learning. In decades efforts have been made on enhancing image classification accuracy by using deep learning models while less attention…
Conventional approaches to object instance re-identification rely on matching appearances of the target objects among a set of frames. However, learning appearances of the objects alone might fail when there are multiple objects with…
Knowledge distillation is commonly employed to compress neural networks, reducing the inference costs and memory footprint. In the scenario of homogenous architecture, feature-based methods have been widely validated for their…
Visual question answering is a multimodal task that requires the joint comprehension of visual and textual information. However, integrating visual and textual semantics solely through attention layers is insufficient to comprehensively…
Few-shot Semantic Segmentation(FSS)aim to adapt a pre-trained model to new classes with as few as a single labeled training sample per class. The existing prototypical work used in natural image scenarios biasedly focus on capturing…
Open-vocabulary 6D object pose estimation empowers robots to manipulate arbitrary unseen objects guided solely by natural language. However, a critical limitation of existing approaches is their reliance on unconstrained global matching…
A thorough comprehension of image content demands a complex grasp of the interactions that may occur in the natural world. One of the key issues is to describe the visual relationships between objects. When dealing with real world data,…
Recent progress in contrastive learning has revolutionized unsupervised representation learning. Concretely, multiple views (augmentations) from the same image are encouraged to map to the similar embeddings, while views from different…
In natural image matting, the goal is to estimate the opacity of the foreground object in the image. This opacity controls the way the foreground and background is blended in transparent regions. In recent years, advances in deep learning…
We propose an end-to-end learning framework for generating foreground object segmentations. Given a single novel image, our approach produces pixel-level masks for all "object-like" regions---even for object categories never seen during…
The human vision and perception system is inherently incremental where new knowledge is continually learned over time whilst existing knowledge is retained. On the other hand, deep learning networks are ill-equipped for incremental…