Related papers: Efficient Feature Distillation for Zero-shot Annot…

Recently, CLIP has been applied to pixel-level zero-shot learning tasks via a two-stage scheme. The general idea is to first generate class-agnostic region proposals and then feed the cropped proposal regions to CLIP to utilize its…

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…

Zero-shot anomaly detection (ZSAD) methods entail detecting anomalies directly without access to any known normal or abnormal samples within the target item categories. Existing approaches typically rely on the robust generalization…

In recent years, large-scale deep models have achieved great success, but the huge computational complexity and massive storage requirements make it a great challenge to deploy them in resource-limited devices. As a model compression and…

Contrastive Language-Image Pre-training (CLIP) has been shown to improve zero-shot generalization capabilities of language and vision models. In this paper, we extend CLIP for efficient knowledge distillation, by utilizing embeddings as…

Zero-shot object detection (ZSD) aims to leverage semantic descriptions to localize and recognize objects of both seen and unseen classes. Existing ZSD works are mainly coarse-grained object detection, where the classes are visually quite…

Recently, many zero-shot learning (ZSL) methods focused on learning discriminative object features in an embedding feature space, however, the distributions of the unseen-class features learned by these methods are prone to be partly…

Zero-shot anomaly detection (ZSAD) requires detecting and localizing anomalies without access to target-class anomaly samples. Mainstream methods rely on vision-language models (VLMs) such as CLIP: they build hand-crafted or learned prompt…

Recent advancements in camera-based 3D object detection have introduced cross-modal knowledge distillation to bridge the performance gap with LiDAR 3D detectors, leveraging the precise geometric information in LiDAR point clouds. However,…

We present Distill CLIP (DCLIP), a fine-tuned variant of the CLIP model that enhances multimodal image-text retrieval while preserving the original model's strong zero-shot classification capabilities. CLIP models are typically constrained…

Knowledge distillation has been applied to image classification successfully. However, object detection is much more sophisticated and most knowledge distillation methods have failed on it. In this paper, we point out that in object…

Label assignment in object detection aims to assign targets, foreground or background, to sampled regions in an image. Unlike labeling for image classification, this problem is not well defined due to the object's bounding box. In this…

In an out-of-distribution (OOD) detection problem, samples of known classes(also called in-distribution classes) are used to train a special classifier. In testing, the classifier can (1) classify the test samples of known classes to their…

Knowledge Distillation (KD) has been used in image classification for model compression. However, rare studies apply this technology on single-stage object detectors. Focal loss shows that the accumulated errors of easily-classified samples…

Object detection is considered as one of the most challenging problems in computer vision, since it requires correct prediction of both classes and locations of objects in images. In this study, we define a more difficult scenario, namely…

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…

Most of the existing algorithms for zero-shot classification problems typically rely on the attribute-based semantic relations among categories to realize the classification of novel categories without observing any of their instances.…

Contrastive Language-Image Pre-training (CLIP) has become a promising language-supervised visual pre-training framework. This paper aims to distill small CLIP models supervised by a large teacher CLIP model. We propose several distillation…

Video object segmentation is a fundamental research problem in computer vision. Recent techniques have often applied attention mechanism to object representation learning from video sequences. However, due to temporal changes in the video…

Generalized Zero-shot Semantic Segmentation aims to segment both seen and unseen categories only under the supervision of the seen ones. To tackle this, existing methods adopt the large-scale Vision Language Models (VLMs) which obtain…